agentic-qe 3.7.8 → 3.7.10

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
Files changed (569) hide show
  1. package/.claude/skills/.validation/README.md +111 -111
  2. package/.claude/skills/.validation/examples/chaos-engineering-output.example.json +530 -530
  3. package/.claude/skills/.validation/examples/performance-testing-output.example.json +252 -252
  4. package/.claude/skills/.validation/examples/security-testing-output.example.json +413 -413
  5. package/.claude/skills/.validation/examples/testability-scoring-output.example.json +350 -350
  6. package/.claude/skills/.validation/schemas/skill-eval.schema.json +462 -462
  7. package/.claude/skills/.validation/schemas/skill-frontmatter.schema.json +341 -341
  8. package/.claude/skills/.validation/schemas/skill-output-meta.schema.json +199 -199
  9. package/.claude/skills/.validation/schemas/skill-output.template.json +610 -610
  10. package/.claude/skills/.validation/skill-validation-mcp-integration.md +250 -250
  11. package/.claude/skills/.validation/templates/eval.template.yaml +366 -366
  12. package/.claude/skills/.validation/templates/schemas/output.json +145 -145
  13. package/.claude/skills/.validation/templates/security-testing-eval.template.yaml +725 -725
  14. package/.claude/skills/.validation/templates/skill-frontmatter.example.yaml +225 -225
  15. package/.claude/skills/.validation/test-data/invalid-output.json +5 -5
  16. package/.claude/skills/.validation/test-data/minimal-output.json +9 -9
  17. package/.claude/skills/.validation/test-data/sample-output.json +73 -73
  18. package/.claude/skills/a11y-ally/evals/a11y-ally.yaml +376 -376
  19. package/.claude/skills/a11y-ally/schemas/output.json +549 -549
  20. package/.claude/skills/accessibility-testing/evals/accessibility-testing.yaml +719 -719
  21. package/.claude/skills/accessibility-testing/schemas/output.json +776 -776
  22. package/.claude/skills/accessibility-testing/test-data/sample-output.json +191 -191
  23. package/.claude/skills/agentic-quality-engineering/schemas/output.json +577 -577
  24. package/.claude/skills/api-testing-patterns/evals/api-testing-patterns.yaml +696 -696
  25. package/.claude/skills/api-testing-patterns/schemas/output.json +845 -845
  26. package/.claude/skills/aqe-v2-v3-migration/schemas/output.json +513 -513
  27. package/.claude/skills/brutal-honesty-review/schemas/output.json +291 -291
  28. package/.claude/skills/bug-reporting-excellence/schemas/output.json +288 -288
  29. package/.claude/skills/chaos-engineering-resilience/evals/chaos-engineering-resilience.yaml +761 -761
  30. package/.claude/skills/chaos-engineering-resilience/schemas/output.json +1205 -1205
  31. package/.claude/skills/cicd-pipeline-qe-orchestrator/evals/cicd-pipeline-qe-orchestrator.yaml +157 -157
  32. package/.claude/skills/cicd-pipeline-qe-orchestrator/schemas/output.json +542 -542
  33. package/.claude/skills/code-review-quality/schemas/output.json +264 -264
  34. package/.claude/skills/compatibility-testing/evals/compatibility-testing.yaml +410 -410
  35. package/.claude/skills/compatibility-testing/schemas/output.json +551 -551
  36. package/.claude/skills/compliance-testing/evals/compliance-testing.yaml +1107 -1107
  37. package/.claude/skills/compliance-testing/schemas/output.json +845 -845
  38. package/.claude/skills/consultancy-practices/schemas/output.json +282 -282
  39. package/.claude/skills/contract-testing/evals/contract-testing.yaml +748 -748
  40. package/.claude/skills/contract-testing/schemas/output.json +638 -638
  41. package/.claude/skills/database-testing/evals/database-testing.yaml +968 -968
  42. package/.claude/skills/database-testing/schemas/output.json +1446 -1446
  43. package/.claude/skills/debug-loop/SKILL.md +61 -61
  44. package/.claude/skills/enterprise-integration-testing/SKILL.md +735 -735
  45. package/.claude/skills/enterprise-integration-testing/evals/enterprise-integration-testing.yaml +158 -0
  46. package/.claude/skills/enterprise-integration-testing/schemas/output.json +74 -0
  47. package/.claude/skills/enterprise-integration-testing/scripts/validate-config.json +25 -0
  48. package/.claude/skills/iterative-loop/SKILL.md +371 -371
  49. package/.claude/skills/localization-testing/evals/localization-testing.yaml +544 -544
  50. package/.claude/skills/localization-testing/schemas/output.json +325 -325
  51. package/.claude/skills/middleware-testing-patterns/SKILL.md +798 -798
  52. package/.claude/skills/middleware-testing-patterns/evals/middleware-testing-patterns.yaml +153 -0
  53. package/.claude/skills/middleware-testing-patterns/schemas/output.json +58 -0
  54. package/.claude/skills/middleware-testing-patterns/scripts/validate-config.json +25 -0
  55. package/.claude/skills/mobile-testing/evals/mobile-testing.yaml +537 -537
  56. package/.claude/skills/mobile-testing/schemas/output.json +318 -318
  57. package/.claude/skills/mutation-testing/evals/mutation-testing.yaml +652 -652
  58. package/.claude/skills/mutation-testing/schemas/output.json +707 -707
  59. package/.claude/skills/mutation-testing/test-data/sample-output.json +295 -295
  60. package/.claude/skills/n8n-expression-testing/evals/n8n-expression-testing.yaml +450 -450
  61. package/.claude/skills/n8n-expression-testing/schemas/output.json +369 -369
  62. package/.claude/skills/n8n-integration-testing-patterns/evals/n8n-integration-testing-patterns.yaml +522 -522
  63. package/.claude/skills/n8n-integration-testing-patterns/schemas/output.json +291 -291
  64. package/.claude/skills/n8n-security-testing/evals/n8n-security-testing.yaml +493 -493
  65. package/.claude/skills/n8n-security-testing/schemas/output.json +293 -293
  66. package/.claude/skills/n8n-trigger-testing-strategies/evals/n8n-trigger-testing-strategies.yaml +500 -500
  67. package/.claude/skills/n8n-trigger-testing-strategies/schemas/output.json +295 -295
  68. package/.claude/skills/n8n-workflow-testing-fundamentals/evals/n8n-workflow-testing-fundamentals.yaml +497 -497
  69. package/.claude/skills/n8n-workflow-testing-fundamentals/schemas/output.json +254 -254
  70. package/.claude/skills/observability-testing-patterns/SKILL.md +930 -930
  71. package/.claude/skills/observability-testing-patterns/evals/observability-testing-patterns.yaml +157 -0
  72. package/.claude/skills/observability-testing-patterns/schemas/output.json +58 -0
  73. package/.claude/skills/observability-testing-patterns/scripts/validate-config.json +25 -0
  74. package/.claude/skills/pentest-validation/SKILL.md +268 -268
  75. package/.claude/skills/pentest-validation/evals/pentest-validation.yaml +708 -708
  76. package/.claude/skills/pentest-validation/schemas/output.json +281 -281
  77. package/.claude/skills/performance-analysis/evals/performance-analysis.yaml +144 -144
  78. package/.claude/skills/performance-analysis/schemas/output.json +588 -588
  79. package/.claude/skills/performance-testing/evals/performance-testing.yaml +772 -772
  80. package/.claude/skills/performance-testing/schemas/output.json +1184 -1184
  81. package/.claude/skills/pr-review/SKILL.md +61 -61
  82. package/.claude/skills/qcsd-cicd-swarm/SKILL.md +2206 -2206
  83. package/.claude/skills/qcsd-cicd-swarm/evals/qcsd-cicd-swarm.yaml +211 -0
  84. package/.claude/skills/qcsd-cicd-swarm/schemas/output.json +86 -0
  85. package/.claude/skills/qcsd-cicd-swarm/scripts/validate-config.json +30 -0
  86. package/.claude/skills/qcsd-development-swarm/SKILL.md +2154 -2154
  87. package/.claude/skills/qcsd-development-swarm/evals/qcsd-development-swarm.yaml +162 -0
  88. package/.claude/skills/qcsd-development-swarm/schemas/output.json +72 -0
  89. package/.claude/skills/qcsd-development-swarm/scripts/validate-config.json +25 -0
  90. package/.claude/skills/qcsd-ideation-swarm/evals/qcsd-ideation-swarm.yaml +138 -138
  91. package/.claude/skills/qcsd-ideation-swarm/schemas/output.json +568 -568
  92. package/.claude/skills/qcsd-production-swarm/SKILL.md +2781 -2781
  93. package/.claude/skills/qcsd-production-swarm/evals/qcsd-production-swarm.yaml +246 -246
  94. package/.claude/skills/qcsd-production-swarm/schemas/output.json +505 -505
  95. package/.claude/skills/qcsd-production-swarm/scripts/validate-config.json +25 -25
  96. package/.claude/skills/qe-chaos-resilience/evals/qe-chaos-resilience.yaml +443 -443
  97. package/.claude/skills/qe-chaos-resilience/schemas/output.json +314 -314
  98. package/.claude/skills/qe-code-intelligence/evals/qe-code-intelligence.yaml +459 -459
  99. package/.claude/skills/qe-code-intelligence/schemas/output.json +315 -315
  100. package/.claude/skills/qe-contract-testing/evals/qe-contract-testing.yaml +513 -513
  101. package/.claude/skills/qe-contract-testing/schemas/output.json +295 -295
  102. package/.claude/skills/qe-coverage-analysis/evals/qe-coverage-analysis.yaml +494 -494
  103. package/.claude/skills/qe-coverage-analysis/schemas/output.json +286 -286
  104. package/.claude/skills/qe-defect-intelligence/evals/qe-defect-intelligence.yaml +511 -511
  105. package/.claude/skills/qe-defect-intelligence/schemas/output.json +283 -283
  106. package/.claude/skills/qe-iterative-loop/schemas/output.json +264 -264
  107. package/.claude/skills/qe-learning-optimization/evals/qe-learning-optimization.yaml +144 -144
  108. package/.claude/skills/qe-learning-optimization/schemas/output.json +288 -288
  109. package/.claude/skills/qe-quality-assessment/evals/qe-quality-assessment.yaml +506 -506
  110. package/.claude/skills/qe-quality-assessment/schemas/output.json +550 -550
  111. package/.claude/skills/qe-requirements-validation/evals/qe-requirements-validation.yaml +598 -598
  112. package/.claude/skills/qe-requirements-validation/schemas/output.json +587 -587
  113. package/.claude/skills/qe-security-compliance/evals/qe-security-compliance.yaml +595 -595
  114. package/.claude/skills/qe-security-compliance/schemas/output.json +498 -498
  115. package/.claude/skills/qe-test-execution/evals/qe-test-execution.yaml +607 -607
  116. package/.claude/skills/qe-test-execution/schemas/output.json +529 -529
  117. package/.claude/skills/qe-test-generation/evals/qe-test-generation.yaml +148 -148
  118. package/.claude/skills/qe-test-generation/schemas/output.json +439 -439
  119. package/.claude/skills/qe-visual-accessibility/evals/qe-visual-accessibility.yaml +142 -142
  120. package/.claude/skills/qe-visual-accessibility/schemas/output.json +491 -491
  121. package/.claude/skills/quality-metrics/evals/quality-metrics.yaml +494 -494
  122. package/.claude/skills/quality-metrics/schemas/output.json +403 -403
  123. package/.claude/skills/refactoring-patterns/schemas/output.json +475 -475
  124. package/.claude/skills/regression-testing/evals/regression-testing.yaml +504 -504
  125. package/.claude/skills/regression-testing/schemas/output.json +311 -311
  126. package/.claude/skills/release/SKILL.md +347 -347
  127. package/.claude/skills/risk-based-testing/evals/risk-based-testing.yaml +141 -141
  128. package/.claude/skills/risk-based-testing/schemas/output.json +480 -480
  129. package/.claude/skills/security-testing/evals/security-testing.yaml +789 -789
  130. package/.claude/skills/security-testing/schemas/output.json +879 -879
  131. package/.claude/skills/security-visual-testing/evals/security-visual-testing.yaml +163 -163
  132. package/.claude/skills/security-visual-testing/schemas/output.json +486 -486
  133. package/.claude/skills/sfdipot-product-factors/SKILL.md +239 -239
  134. package/.claude/skills/sherlock-review/schemas/output.json +297 -297
  135. package/.claude/skills/shift-left-testing/evals/shift-left-testing.yaml +145 -145
  136. package/.claude/skills/shift-left-testing/schemas/output.json +459 -459
  137. package/.claude/skills/shift-right-testing/evals/shift-right-testing.yaml +147 -147
  138. package/.claude/skills/shift-right-testing/schemas/output.json +418 -418
  139. package/.claude/skills/skills-manifest.json +1 -1
  140. package/.claude/skills/tdd-london-chicago/schemas/output.json +444 -444
  141. package/.claude/skills/technical-writing/schemas/output.json +268 -268
  142. package/.claude/skills/test-automation-strategy/evals/test-automation-strategy.yaml +148 -148
  143. package/.claude/skills/test-automation-strategy/schemas/output.json +444 -444
  144. package/.claude/skills/test-data-management/evals/test-data-management.yaml +504 -504
  145. package/.claude/skills/test-data-management/schemas/output.json +284 -284
  146. package/.claude/skills/test-design-techniques/evals/test-design-techniques.yaml +142 -142
  147. package/.claude/skills/test-design-techniques/schemas/output.json +295 -295
  148. package/.claude/skills/test-environment-management/schemas/output.json +310 -310
  149. package/.claude/skills/test-idea-rewriting/SKILL.md +229 -229
  150. package/.claude/skills/test-reporting-analytics/evals/test-reporting-analytics.yaml +155 -155
  151. package/.claude/skills/test-reporting-analytics/schemas/output.json +329 -329
  152. package/.claude/skills/testability-scoring/evals/testability-scoring.yaml +814 -814
  153. package/.claude/skills/testability-scoring/resources/templates/config.template.js +84 -84
  154. package/.claude/skills/testability-scoring/schemas/output.json +606 -606
  155. package/.claude/skills/testability-scoring/scripts/generate-html-report.js +1007 -1007
  156. package/.claude/skills/trust-tier-manifest.json +78 -7
  157. package/.claude/skills/verification-quality/evals/verification-quality.yaml +150 -150
  158. package/.claude/skills/verification-quality/schemas/output.json +432 -432
  159. package/.claude/skills/visual-testing-advanced/evals/visual-testing-advanced.yaml +154 -154
  160. package/.claude/skills/visual-testing-advanced/schemas/output.json +294 -294
  161. package/.claude/skills/wms-testing-patterns/evals/wms-testing-patterns.yaml +165 -165
  162. package/.claude/skills/wms-testing-patterns/schemas/output.json +150 -150
  163. package/.claude/skills/wms-testing-patterns/scripts/validate-config.json +51 -51
  164. package/CHANGELOG.md +34 -0
  165. package/README.md +169 -900
  166. package/assets/agents/v3/helpers/quality-criteria/evidence-classification.md +116 -116
  167. package/assets/agents/v3/helpers/quality-criteria/htsm-categories.md +139 -139
  168. package/assets/governance/constitution.md +202 -202
  169. package/assets/governance/shards/chaos-resilience.shard.md +221 -221
  170. package/assets/governance/shards/code-intelligence.shard.md +178 -178
  171. package/assets/governance/shards/contract-testing.shard.md +206 -206
  172. package/assets/governance/shards/coverage-analysis.shard.md +146 -146
  173. package/assets/governance/shards/defect-intelligence.shard.md +182 -182
  174. package/assets/governance/shards/learning-optimization.shard.md +248 -248
  175. package/assets/governance/shards/quality-assessment.shard.md +165 -165
  176. package/assets/governance/shards/requirements-validation.shard.md +177 -177
  177. package/assets/governance/shards/security-compliance.shard.md +196 -196
  178. package/assets/governance/shards/test-execution.shard.md +156 -156
  179. package/assets/governance/shards/test-generation.shard.md +128 -128
  180. package/assets/governance/shards/visual-accessibility.shard.md +209 -209
  181. package/assets/hooks/cross-phase-memory.yaml +253 -253
  182. package/assets/patterns/adr-051-booster-patterns.json +78 -78
  183. package/assets/patterns/adr-051-embedding-patterns.json +147 -147
  184. package/assets/patterns/adr-051-integration-summary.json +62 -62
  185. package/assets/patterns/adr-051-reasoning-patterns.json +166 -166
  186. package/assets/patterns/adr-051-router-patterns.json +113 -113
  187. package/assets/patterns/index.json +136 -136
  188. package/assets/skills/.validation/README.md +111 -111
  189. package/assets/skills/.validation/examples/chaos-engineering-output.example.json +530 -530
  190. package/assets/skills/.validation/examples/performance-testing-output.example.json +252 -252
  191. package/assets/skills/.validation/examples/security-testing-output.example.json +413 -413
  192. package/assets/skills/.validation/examples/testability-scoring-output.example.json +350 -350
  193. package/assets/skills/.validation/schemas/skill-eval.schema.json +462 -462
  194. package/assets/skills/.validation/schemas/skill-frontmatter.schema.json +341 -341
  195. package/assets/skills/.validation/schemas/skill-output-meta.schema.json +199 -199
  196. package/assets/skills/.validation/schemas/skill-output.template.json +610 -610
  197. package/assets/skills/.validation/skill-validation-mcp-integration.md +250 -250
  198. package/assets/skills/.validation/templates/eval.template.yaml +366 -366
  199. package/assets/skills/.validation/templates/schemas/output.json +145 -145
  200. package/assets/skills/.validation/templates/security-testing-eval.template.yaml +725 -725
  201. package/assets/skills/.validation/templates/skill-frontmatter.example.yaml +225 -225
  202. package/assets/skills/.validation/test-data/invalid-output.json +5 -5
  203. package/assets/skills/.validation/test-data/minimal-output.json +9 -9
  204. package/assets/skills/.validation/test-data/sample-output.json +73 -73
  205. package/assets/skills/a11y-ally/SKILL.md +1664 -1658
  206. package/assets/skills/a11y-ally/evals/a11y-ally.yaml +376 -0
  207. package/assets/skills/a11y-ally/schemas/output.json +549 -0
  208. package/assets/skills/a11y-ally/scripts/validate-config.json +42 -0
  209. package/assets/skills/accessibility-testing/evals/accessibility-testing.yaml +719 -719
  210. package/assets/skills/accessibility-testing/schemas/output.json +776 -776
  211. package/assets/skills/accessibility-testing/test-data/sample-output.json +191 -191
  212. package/assets/skills/agentic-quality-engineering/schemas/output.json +577 -577
  213. package/assets/skills/api-testing-patterns/evals/api-testing-patterns.yaml +696 -696
  214. package/assets/skills/api-testing-patterns/schemas/output.json +845 -845
  215. package/assets/skills/aqe-v2-v3-migration/schemas/output.json +513 -513
  216. package/assets/skills/brutal-honesty-review/SKILL.md +5 -0
  217. package/assets/skills/brutal-honesty-review/schemas/output.json +291 -0
  218. package/assets/skills/brutal-honesty-review/scripts/validate-config.json +34 -0
  219. package/assets/skills/bug-reporting-excellence/schemas/output.json +288 -288
  220. package/assets/skills/chaos-engineering-resilience/evals/chaos-engineering-resilience.yaml +761 -761
  221. package/assets/skills/chaos-engineering-resilience/schemas/output.json +1205 -1205
  222. package/assets/skills/cicd-pipeline-qe-orchestrator/README.md +1 -1
  223. package/assets/skills/cicd-pipeline-qe-orchestrator/SKILL.md +6 -0
  224. package/assets/skills/cicd-pipeline-qe-orchestrator/evals/cicd-pipeline-qe-orchestrator.yaml +157 -0
  225. package/assets/skills/cicd-pipeline-qe-orchestrator/schemas/output.json +542 -0
  226. package/assets/skills/cicd-pipeline-qe-orchestrator/scripts/validate-config.json +42 -0
  227. package/assets/skills/code-review-quality/schemas/output.json +264 -264
  228. package/assets/skills/compatibility-testing/evals/compatibility-testing.yaml +410 -410
  229. package/assets/skills/compatibility-testing/schemas/output.json +551 -551
  230. package/assets/skills/compliance-testing/evals/compliance-testing.yaml +1107 -1107
  231. package/assets/skills/compliance-testing/schemas/output.json +845 -845
  232. package/assets/skills/consultancy-practices/schemas/output.json +282 -282
  233. package/assets/skills/contract-testing/evals/contract-testing.yaml +748 -748
  234. package/assets/skills/contract-testing/schemas/output.json +638 -638
  235. package/assets/skills/database-testing/evals/database-testing.yaml +968 -968
  236. package/assets/skills/database-testing/schemas/output.json +1446 -1446
  237. package/assets/skills/debug-loop/SKILL.md +61 -61
  238. package/assets/skills/enterprise-integration-testing/SKILL.md +735 -735
  239. package/assets/skills/enterprise-integration-testing/evals/enterprise-integration-testing.yaml +158 -0
  240. package/assets/skills/enterprise-integration-testing/schemas/output.json +74 -0
  241. package/assets/skills/enterprise-integration-testing/scripts/validate-config.json +25 -0
  242. package/assets/skills/localization-testing/evals/localization-testing.yaml +544 -544
  243. package/assets/skills/localization-testing/schemas/output.json +325 -325
  244. package/assets/skills/middleware-testing-patterns/SKILL.md +798 -798
  245. package/assets/skills/middleware-testing-patterns/evals/middleware-testing-patterns.yaml +153 -0
  246. package/assets/skills/middleware-testing-patterns/schemas/output.json +58 -0
  247. package/assets/skills/middleware-testing-patterns/scripts/validate-config.json +25 -0
  248. package/assets/skills/mobile-testing/evals/mobile-testing.yaml +537 -537
  249. package/assets/skills/mobile-testing/schemas/output.json +318 -318
  250. package/assets/skills/mutation-testing/evals/mutation-testing.yaml +652 -652
  251. package/assets/skills/mutation-testing/schemas/output.json +707 -707
  252. package/assets/skills/mutation-testing/test-data/sample-output.json +295 -295
  253. package/assets/skills/n8n-expression-testing/SKILL.md +6 -0
  254. package/assets/skills/n8n-expression-testing/evals/n8n-expression-testing.yaml +450 -0
  255. package/assets/skills/n8n-expression-testing/schemas/output.json +369 -0
  256. package/assets/skills/n8n-expression-testing/scripts/validate-config.json +39 -0
  257. package/assets/skills/n8n-integration-testing-patterns/SKILL.md +6 -0
  258. package/assets/skills/n8n-integration-testing-patterns/evals/n8n-integration-testing-patterns.yaml +522 -0
  259. package/assets/skills/n8n-integration-testing-patterns/schemas/output.json +291 -0
  260. package/assets/skills/n8n-integration-testing-patterns/scripts/validate-config.json +34 -0
  261. package/assets/skills/n8n-security-testing/SKILL.md +6 -0
  262. package/assets/skills/n8n-security-testing/evals/n8n-security-testing.yaml +493 -0
  263. package/assets/skills/n8n-security-testing/schemas/output.json +293 -0
  264. package/assets/skills/n8n-security-testing/scripts/validate-config.json +34 -0
  265. package/assets/skills/n8n-trigger-testing-strategies/SKILL.md +6 -0
  266. package/assets/skills/n8n-trigger-testing-strategies/evals/n8n-trigger-testing-strategies.yaml +500 -0
  267. package/assets/skills/n8n-trigger-testing-strategies/schemas/output.json +295 -0
  268. package/assets/skills/n8n-trigger-testing-strategies/scripts/validate-config.json +34 -0
  269. package/assets/skills/n8n-workflow-testing-fundamentals/SKILL.md +6 -0
  270. package/assets/skills/n8n-workflow-testing-fundamentals/evals/n8n-workflow-testing-fundamentals.yaml +497 -0
  271. package/assets/skills/n8n-workflow-testing-fundamentals/schemas/output.json +254 -0
  272. package/assets/skills/n8n-workflow-testing-fundamentals/scripts/validate-config.json +35 -0
  273. package/assets/skills/observability-testing-patterns/SKILL.md +930 -930
  274. package/assets/skills/observability-testing-patterns/evals/observability-testing-patterns.yaml +157 -0
  275. package/assets/skills/observability-testing-patterns/schemas/output.json +58 -0
  276. package/assets/skills/observability-testing-patterns/scripts/validate-config.json +25 -0
  277. package/assets/skills/pentest-validation/SKILL.md +268 -268
  278. package/assets/skills/pentest-validation/evals/pentest-validation.yaml +708 -708
  279. package/assets/skills/pentest-validation/schemas/output.json +281 -281
  280. package/assets/skills/pentest-validation/scripts/validate-config.json +12 -0
  281. package/assets/skills/performance-testing/evals/performance-testing.yaml +772 -772
  282. package/assets/skills/performance-testing/schemas/output.json +1184 -1184
  283. package/assets/skills/pr-review/SKILL.md +61 -61
  284. package/assets/skills/qcsd-cicd-swarm/SKILL.md +2206 -2206
  285. package/assets/skills/qcsd-cicd-swarm/evals/qcsd-cicd-swarm.yaml +211 -0
  286. package/assets/skills/qcsd-cicd-swarm/schemas/output.json +86 -0
  287. package/assets/skills/qcsd-cicd-swarm/scripts/validate-config.json +30 -0
  288. package/assets/skills/qcsd-development-swarm/SKILL.md +2154 -2154
  289. package/assets/skills/qcsd-development-swarm/evals/qcsd-development-swarm.yaml +162 -0
  290. package/assets/skills/qcsd-development-swarm/schemas/output.json +72 -0
  291. package/assets/skills/qcsd-development-swarm/scripts/validate-config.json +25 -0
  292. package/assets/skills/qcsd-ideation-swarm/evals/qcsd-ideation-swarm.yaml +138 -0
  293. package/assets/skills/qcsd-ideation-swarm/schemas/output.json +568 -0
  294. package/assets/skills/qcsd-ideation-swarm/scripts/validate-config.json +25 -0
  295. package/assets/skills/qcsd-production-swarm/SKILL.md +2781 -0
  296. package/assets/skills/qcsd-production-swarm/evals/qcsd-production-swarm.yaml +246 -0
  297. package/assets/skills/qcsd-production-swarm/schemas/output.json +505 -0
  298. package/assets/skills/qcsd-production-swarm/scripts/validate-config.json +25 -0
  299. package/assets/skills/qcsd-refinement-swarm/evals/qcsd-refinement-swarm.yaml +139 -0
  300. package/assets/skills/qcsd-refinement-swarm/schemas/output.json +811 -0
  301. package/assets/skills/qcsd-refinement-swarm/scripts/validate-config.json +25 -0
  302. package/assets/skills/qe-chaos-resilience/evals/qe-chaos-resilience.yaml +443 -443
  303. package/assets/skills/qe-chaos-resilience/schemas/output.json +314 -314
  304. package/assets/skills/qe-code-intelligence/evals/qe-code-intelligence.yaml +459 -459
  305. package/assets/skills/qe-code-intelligence/schemas/output.json +315 -315
  306. package/assets/skills/qe-contract-testing/evals/qe-contract-testing.yaml +513 -513
  307. package/assets/skills/qe-contract-testing/schemas/output.json +295 -295
  308. package/assets/skills/qe-coverage-analysis/evals/qe-coverage-analysis.yaml +494 -494
  309. package/assets/skills/qe-coverage-analysis/schemas/output.json +286 -286
  310. package/assets/skills/qe-defect-intelligence/evals/qe-defect-intelligence.yaml +511 -511
  311. package/assets/skills/qe-defect-intelligence/schemas/output.json +283 -283
  312. package/assets/skills/qe-iterative-loop/schemas/output.json +264 -264
  313. package/assets/skills/qe-learning-optimization/evals/qe-learning-optimization.yaml +144 -144
  314. package/assets/skills/qe-learning-optimization/schemas/output.json +288 -288
  315. package/assets/skills/qe-quality-assessment/evals/qe-quality-assessment.yaml +506 -506
  316. package/assets/skills/qe-quality-assessment/schemas/output.json +550 -550
  317. package/assets/skills/qe-requirements-validation/evals/qe-requirements-validation.yaml +598 -598
  318. package/assets/skills/qe-requirements-validation/schemas/output.json +587 -587
  319. package/assets/skills/qe-security-compliance/evals/qe-security-compliance.yaml +595 -595
  320. package/assets/skills/qe-security-compliance/schemas/output.json +498 -498
  321. package/assets/skills/qe-test-execution/evals/qe-test-execution.yaml +607 -607
  322. package/assets/skills/qe-test-execution/schemas/output.json +529 -529
  323. package/assets/skills/qe-test-generation/evals/qe-test-generation.yaml +148 -148
  324. package/assets/skills/qe-test-generation/schemas/output.json +439 -439
  325. package/assets/skills/qe-visual-accessibility/evals/qe-visual-accessibility.yaml +142 -142
  326. package/assets/skills/qe-visual-accessibility/schemas/output.json +491 -491
  327. package/assets/skills/quality-metrics/evals/quality-metrics.yaml +494 -494
  328. package/assets/skills/quality-metrics/schemas/output.json +403 -403
  329. package/assets/skills/refactoring-patterns/schemas/output.json +475 -475
  330. package/assets/skills/regression-testing/evals/regression-testing.yaml +504 -504
  331. package/assets/skills/regression-testing/schemas/output.json +311 -311
  332. package/assets/skills/risk-based-testing/evals/risk-based-testing.yaml +141 -141
  333. package/assets/skills/risk-based-testing/schemas/output.json +480 -480
  334. package/assets/skills/security-testing/evals/security-testing.yaml +789 -789
  335. package/assets/skills/security-testing/schemas/output.json +879 -879
  336. package/assets/skills/security-visual-testing/evals/security-visual-testing.yaml +163 -163
  337. package/assets/skills/security-visual-testing/schemas/output.json +486 -486
  338. package/assets/skills/security-visual-testing/scripts/validate-config.json +45 -0
  339. package/assets/skills/sfdipot-product-factors/SKILL.md +239 -239
  340. package/assets/skills/sherlock-review/SKILL.md +5 -0
  341. package/assets/skills/sherlock-review/schemas/output.json +297 -0
  342. package/assets/skills/sherlock-review/scripts/validate-config.json +35 -0
  343. package/assets/skills/shift-left-testing/evals/shift-left-testing.yaml +145 -145
  344. package/assets/skills/shift-left-testing/schemas/output.json +459 -459
  345. package/assets/skills/shift-right-testing/evals/shift-right-testing.yaml +147 -147
  346. package/assets/skills/shift-right-testing/schemas/output.json +418 -418
  347. package/assets/skills/tdd-london-chicago/schemas/output.json +444 -444
  348. package/assets/skills/technical-writing/schemas/output.json +268 -268
  349. package/assets/skills/test-automation-strategy/evals/test-automation-strategy.yaml +148 -148
  350. package/assets/skills/test-automation-strategy/schemas/output.json +444 -444
  351. package/assets/skills/test-data-management/evals/test-data-management.yaml +504 -504
  352. package/assets/skills/test-data-management/schemas/output.json +284 -284
  353. package/assets/skills/test-design-techniques/evals/test-design-techniques.yaml +142 -142
  354. package/assets/skills/test-design-techniques/schemas/output.json +295 -295
  355. package/assets/skills/test-environment-management/schemas/output.json +310 -310
  356. package/assets/skills/test-idea-rewriting/SKILL.md +229 -229
  357. package/assets/skills/test-reporting-analytics/evals/test-reporting-analytics.yaml +155 -155
  358. package/assets/skills/test-reporting-analytics/schemas/output.json +329 -329
  359. package/assets/skills/testability-scoring/SKILL.md +5 -0
  360. package/assets/skills/testability-scoring/evals/testability-scoring.yaml +814 -0
  361. package/assets/skills/testability-scoring/resources/templates/config.template.js +84 -84
  362. package/assets/skills/testability-scoring/schemas/output.json +606 -0
  363. package/assets/skills/testability-scoring/scripts/generate-html-report.js +1007 -1007
  364. package/assets/skills/testability-scoring/scripts/validate-config.json +42 -0
  365. package/assets/skills/trust-tier-manifest.json +2404 -0
  366. package/assets/skills/verification-quality/evals/verification-quality.yaml +150 -150
  367. package/assets/skills/verification-quality/schemas/output.json +432 -432
  368. package/assets/skills/visual-testing-advanced/evals/visual-testing-advanced.yaml +154 -154
  369. package/assets/skills/visual-testing-advanced/schemas/output.json +294 -294
  370. package/assets/skills/wms-testing-patterns/evals/wms-testing-patterns.yaml +165 -0
  371. package/assets/skills/wms-testing-patterns/schemas/output.json +150 -0
  372. package/assets/skills/wms-testing-patterns/scripts/validate-config.json +51 -0
  373. package/assets/templates/validation-summary.json +56 -56
  374. package/dist/benchmarks/performance-benchmarks.js +1 -1
  375. package/dist/cli/bundle.js +9158 -2288
  376. package/dist/cli/commands/hooks.d.ts.map +1 -1
  377. package/dist/cli/commands/hooks.js +92 -0
  378. package/dist/cli/commands/hooks.js.map +1 -1
  379. package/dist/cli/commands/mcp.d.ts.map +1 -1
  380. package/dist/cli/commands/mcp.js +11 -9
  381. package/dist/cli/commands/mcp.js.map +1 -1
  382. package/dist/cli/commands/migrate.js +2 -2
  383. package/dist/coordination/constants.d.ts +1 -1
  384. package/dist/coordination/constants.js +1 -1
  385. package/dist/coordination/handlers/coverage-handlers.js +1 -1
  386. package/dist/coordination/handlers/coverage-handlers.js.map +1 -1
  387. package/dist/domains/code-intelligence/services/semantic-analyzer.d.ts +1 -1
  388. package/dist/domains/code-intelligence/services/semantic-analyzer.d.ts.map +1 -1
  389. package/dist/domains/code-intelligence/services/semantic-analyzer.js +1 -1
  390. package/dist/domains/code-intelligence/services/semantic-analyzer.js.map +1 -1
  391. package/dist/domains/coverage-analysis/coordinator.js +1 -1
  392. package/dist/domains/coverage-analysis/services/coverage-analyzer.js +1 -1
  393. package/dist/domains/coverage-analysis/services/coverage-embedder.d.ts +1 -1
  394. package/dist/domains/coverage-analysis/services/coverage-embedder.js +1 -1
  395. package/dist/domains/coverage-analysis/services/gap-detector.js +1 -1
  396. package/dist/domains/coverage-analysis/services/ghost-coverage-analyzer.js +1 -1
  397. package/dist/domains/coverage-analysis/services/hnsw-index.d.ts +2 -2
  398. package/dist/domains/coverage-analysis/services/hnsw-index.js +3 -3
  399. package/dist/domains/coverage-analysis/services/sublinear-analyzer.d.ts +1 -1
  400. package/dist/domains/coverage-analysis/services/sublinear-analyzer.js +1 -1
  401. package/dist/domains/test-execution/services/test-prioritizer.js +1 -1
  402. package/dist/domains/test-generation/context/rust-context-builder.d.ts +31 -0
  403. package/dist/domains/test-generation/context/rust-context-builder.d.ts.map +1 -0
  404. package/dist/domains/test-generation/context/rust-context-builder.js +27 -0
  405. package/dist/domains/test-generation/context/rust-context-builder.js.map +1 -0
  406. package/dist/domains/test-generation/coordinator.js +3 -3
  407. package/dist/domains/test-generation/coordinator.js.map +1 -1
  408. package/dist/domains/test-generation/detectors/mobile-detector.d.ts +41 -0
  409. package/dist/domains/test-generation/detectors/mobile-detector.d.ts.map +1 -0
  410. package/dist/domains/test-generation/detectors/mobile-detector.js +111 -0
  411. package/dist/domains/test-generation/detectors/mobile-detector.js.map +1 -0
  412. package/dist/domains/test-generation/detectors/spring-detector.d.ts +22 -0
  413. package/dist/domains/test-generation/detectors/spring-detector.d.ts.map +1 -0
  414. package/dist/domains/test-generation/detectors/spring-detector.js +37 -0
  415. package/dist/domains/test-generation/detectors/spring-detector.js.map +1 -0
  416. package/dist/domains/test-generation/factories/test-generator-factory.d.ts +2 -1
  417. package/dist/domains/test-generation/factories/test-generator-factory.d.ts.map +1 -1
  418. package/dist/domains/test-generation/factories/test-generator-factory.js +33 -13
  419. package/dist/domains/test-generation/factories/test-generator-factory.js.map +1 -1
  420. package/dist/domains/test-generation/generators/flutter-test-generator.d.ts +107 -0
  421. package/dist/domains/test-generation/generators/flutter-test-generator.d.ts.map +1 -0
  422. package/dist/domains/test-generation/generators/flutter-test-generator.js +590 -0
  423. package/dist/domains/test-generation/generators/flutter-test-generator.js.map +1 -0
  424. package/dist/domains/test-generation/generators/go-test-generator.d.ts +139 -0
  425. package/dist/domains/test-generation/generators/go-test-generator.d.ts.map +1 -0
  426. package/dist/domains/test-generation/generators/go-test-generator.js +654 -0
  427. package/dist/domains/test-generation/generators/go-test-generator.js.map +1 -0
  428. package/dist/domains/test-generation/generators/index.d.ts +8 -0
  429. package/dist/domains/test-generation/generators/index.d.ts.map +1 -1
  430. package/dist/domains/test-generation/generators/index.js +8 -0
  431. package/dist/domains/test-generation/generators/index.js.map +1 -1
  432. package/dist/domains/test-generation/generators/jest-rn-generator.d.ts +95 -0
  433. package/dist/domains/test-generation/generators/jest-rn-generator.d.ts.map +1 -0
  434. package/dist/domains/test-generation/generators/jest-rn-generator.js +591 -0
  435. package/dist/domains/test-generation/generators/jest-rn-generator.js.map +1 -0
  436. package/dist/domains/test-generation/generators/junit5-generator.d.ts +107 -0
  437. package/dist/domains/test-generation/generators/junit5-generator.d.ts.map +1 -0
  438. package/dist/domains/test-generation/generators/junit5-generator.js +588 -0
  439. package/dist/domains/test-generation/generators/junit5-generator.js.map +1 -0
  440. package/dist/domains/test-generation/generators/kotlin-junit-generator.d.ts +109 -0
  441. package/dist/domains/test-generation/generators/kotlin-junit-generator.d.ts.map +1 -0
  442. package/dist/domains/test-generation/generators/kotlin-junit-generator.js +588 -0
  443. package/dist/domains/test-generation/generators/kotlin-junit-generator.js.map +1 -0
  444. package/dist/domains/test-generation/generators/pytest-generator.d.ts +8 -1
  445. package/dist/domains/test-generation/generators/pytest-generator.d.ts.map +1 -1
  446. package/dist/domains/test-generation/generators/pytest-generator.js +57 -0
  447. package/dist/domains/test-generation/generators/pytest-generator.js.map +1 -1
  448. package/dist/domains/test-generation/generators/rust-test-generator.d.ts +80 -0
  449. package/dist/domains/test-generation/generators/rust-test-generator.d.ts.map +1 -0
  450. package/dist/domains/test-generation/generators/rust-test-generator.js +442 -0
  451. package/dist/domains/test-generation/generators/rust-test-generator.js.map +1 -0
  452. package/dist/domains/test-generation/generators/swift-testing-generator.d.ts +97 -0
  453. package/dist/domains/test-generation/generators/swift-testing-generator.d.ts.map +1 -0
  454. package/dist/domains/test-generation/generators/swift-testing-generator.js +482 -0
  455. package/dist/domains/test-generation/generators/swift-testing-generator.js.map +1 -0
  456. package/dist/domains/test-generation/generators/xunit-generator.d.ts +110 -0
  457. package/dist/domains/test-generation/generators/xunit-generator.d.ts.map +1 -0
  458. package/dist/domains/test-generation/generators/xunit-generator.js +611 -0
  459. package/dist/domains/test-generation/generators/xunit-generator.js.map +1 -0
  460. package/dist/domains/test-generation/interfaces.d.ts +11 -2
  461. package/dist/domains/test-generation/interfaces.d.ts.map +1 -1
  462. package/dist/domains/test-generation/prompts/language-prompts.d.ts +29 -0
  463. package/dist/domains/test-generation/prompts/language-prompts.d.ts.map +1 -0
  464. package/dist/domains/test-generation/prompts/language-prompts.js +135 -0
  465. package/dist/domains/test-generation/prompts/language-prompts.js.map +1 -0
  466. package/dist/domains/test-generation/services/compilation-validator.d.ts +43 -0
  467. package/dist/domains/test-generation/services/compilation-validator.d.ts.map +1 -0
  468. package/dist/domains/test-generation/services/compilation-validator.js +134 -0
  469. package/dist/domains/test-generation/services/compilation-validator.js.map +1 -0
  470. package/dist/domains/test-generation/services/index.d.ts +2 -1
  471. package/dist/domains/test-generation/services/index.d.ts.map +1 -1
  472. package/dist/domains/test-generation/services/index.js +3 -1
  473. package/dist/domains/test-generation/services/index.js.map +1 -1
  474. package/dist/domains/test-generation/services/test-file-resolver.d.ts +32 -0
  475. package/dist/domains/test-generation/services/test-file-resolver.d.ts.map +1 -0
  476. package/dist/domains/test-generation/services/test-file-resolver.js +159 -0
  477. package/dist/domains/test-generation/services/test-file-resolver.js.map +1 -0
  478. package/dist/domains/test-generation/services/test-generator.d.ts +10 -0
  479. package/dist/domains/test-generation/services/test-generator.d.ts.map +1 -1
  480. package/dist/domains/test-generation/services/test-generator.js +87 -10
  481. package/dist/domains/test-generation/services/test-generator.js.map +1 -1
  482. package/dist/governance/feature-flags.js +2 -2
  483. package/dist/governance/feature-flags.js.map +1 -1
  484. package/dist/governance/shard-embeddings.js +1 -1
  485. package/dist/init/init-wizard-hooks.d.ts.map +1 -1
  486. package/dist/init/init-wizard-hooks.js +0 -1
  487. package/dist/init/init-wizard-hooks.js.map +1 -1
  488. package/dist/init/phases/07-hooks.d.ts.map +1 -1
  489. package/dist/init/phases/07-hooks.js +0 -2
  490. package/dist/init/phases/07-hooks.js.map +1 -1
  491. package/dist/init/phases/08-mcp.d.ts +8 -4
  492. package/dist/init/phases/08-mcp.d.ts.map +1 -1
  493. package/dist/init/phases/08-mcp.js +13 -31
  494. package/dist/init/phases/08-mcp.js.map +1 -1
  495. package/dist/init/phases/10-workers.js +4 -4
  496. package/dist/init/phases/10-workers.js.map +1 -1
  497. package/dist/init/settings-merge.d.ts.map +1 -1
  498. package/dist/init/settings-merge.js +0 -2
  499. package/dist/init/settings-merge.js.map +1 -1
  500. package/dist/init/token-bootstrap.js +1 -1
  501. package/dist/init/token-bootstrap.js.map +1 -1
  502. package/dist/integrations/rl-suite/algorithms/decision-transformer.js +1 -1
  503. package/dist/kernel/constants.d.ts +2 -2
  504. package/dist/kernel/constants.js +2 -2
  505. package/dist/kernel/hnsw-adapter.js +1 -1
  506. package/dist/kernel/progressive-hnsw-backend.d.ts +2 -2
  507. package/dist/kernel/progressive-hnsw-backend.js +2 -2
  508. package/dist/learning/dream/concept-graph.d.ts +1 -1
  509. package/dist/learning/dream/concept-graph.js +1 -1
  510. package/dist/learning/dream/dream-engine.d.ts +1 -1
  511. package/dist/learning/dream/dream-engine.js +1 -1
  512. package/dist/learning/dream/index.d.ts +1 -1
  513. package/dist/learning/dream/index.js +1 -1
  514. package/dist/learning/dream/types.d.ts +1 -1
  515. package/dist/learning/dream/types.d.ts.map +1 -1
  516. package/dist/learning/dream/types.js +1 -1
  517. package/dist/learning/dream/types.js.map +1 -1
  518. package/dist/learning/token-tracker.js +1 -1
  519. package/dist/learning/token-tracker.js.map +1 -1
  520. package/dist/mcp/bundle.js +7538 -893
  521. package/dist/routing/qe-agent-registry.js +4 -4
  522. package/dist/routing/qe-agent-registry.js.map +1 -1
  523. package/dist/routing/types.d.ts +5 -8
  524. package/dist/routing/types.d.ts.map +1 -1
  525. package/dist/routing/types.js.map +1 -1
  526. package/dist/shared/embeddings/embedding-cache.js +2 -2
  527. package/dist/shared/embeddings/index.d.ts +2 -2
  528. package/dist/shared/embeddings/index.js +2 -2
  529. package/dist/shared/embeddings/nomic-embedder.d.ts +4 -4
  530. package/dist/shared/embeddings/nomic-embedder.js +2 -2
  531. package/dist/shared/embeddings/ollama-client.d.ts +1 -1
  532. package/dist/shared/embeddings/ollama-client.js +2 -2
  533. package/dist/shared/embeddings/ollama-client.js.map +1 -1
  534. package/dist/shared/embeddings/types.d.ts +2 -2
  535. package/dist/shared/embeddings/types.js +2 -2
  536. package/dist/shared/language-detector.d.ts +46 -0
  537. package/dist/shared/language-detector.d.ts.map +1 -0
  538. package/dist/shared/language-detector.js +183 -0
  539. package/dist/shared/language-detector.js.map +1 -0
  540. package/dist/shared/llm/providers/ollama.js +1 -1
  541. package/dist/shared/metrics/code-metrics.d.ts.map +1 -1
  542. package/dist/shared/metrics/code-metrics.js +24 -1
  543. package/dist/shared/metrics/code-metrics.js.map +1 -1
  544. package/dist/shared/parsers/index.d.ts +2 -0
  545. package/dist/shared/parsers/index.d.ts.map +1 -1
  546. package/dist/shared/parsers/index.js +2 -0
  547. package/dist/shared/parsers/index.js.map +1 -1
  548. package/dist/shared/parsers/interfaces.d.ts +81 -0
  549. package/dist/shared/parsers/interfaces.d.ts.map +1 -0
  550. package/dist/shared/parsers/interfaces.js +6 -0
  551. package/dist/shared/parsers/interfaces.js.map +1 -0
  552. package/dist/shared/parsers/multi-language-parser.d.ts +144 -0
  553. package/dist/shared/parsers/multi-language-parser.d.ts.map +1 -0
  554. package/dist/shared/parsers/multi-language-parser.js +1271 -0
  555. package/dist/shared/parsers/multi-language-parser.js.map +1 -0
  556. package/dist/shared/parsers/rust-ownership-analyzer.d.ts +45 -0
  557. package/dist/shared/parsers/rust-ownership-analyzer.d.ts.map +1 -0
  558. package/dist/shared/parsers/rust-ownership-analyzer.js +52 -0
  559. package/dist/shared/parsers/rust-ownership-analyzer.js.map +1 -0
  560. package/dist/shared/parsers/typescript-parser.d.ts +16 -0
  561. package/dist/shared/parsers/typescript-parser.d.ts.map +1 -1
  562. package/dist/shared/parsers/typescript-parser.js +85 -0
  563. package/dist/shared/parsers/typescript-parser.js.map +1 -1
  564. package/dist/shared/types/test-frameworks.d.ts +25 -0
  565. package/dist/shared/types/test-frameworks.d.ts.map +1 -0
  566. package/dist/shared/types/test-frameworks.js +111 -0
  567. package/dist/shared/types/test-frameworks.js.map +1 -0
  568. package/package.json +1 -1
  569. package/scripts/prepare-assets.sh +16 -2
@@ -1,719 +1,719 @@
1
- # =============================================================================
2
- # AQE Accessibility Testing Skill Evaluation Suite v1.0.0
3
- # WCAG 2.2 compliance testing evaluation with POUR principle coverage
4
- # =============================================================================
5
- #
6
- # This evaluation suite validates accessibility testing skill behavior through:
7
- # 1. POUR principle coverage (Perceivable, Operable, Understandable, Robust)
8
- # 2. WCAG 2.2 Level A, AA, AAA conformance testing
9
- # 3. Multi-model consistency across Claude and GPT models
10
- # 4. Severity classification validation
11
- # 5. Remediation quality assessment
12
- #
13
- # Schema: .validation/schemas/skill-eval.schema.json
14
- # Runner: scripts/run-skill-eval.ts
15
- # =============================================================================
16
-
17
- skill: accessibility-testing
18
- version: 1.0.0
19
- description: >
20
- Comprehensive evaluation suite for WCAG 2.2 accessibility testing skill.
21
- Tests POUR principles (Perceivable, Operable, Understandable, Robust),
22
- conformance levels, finding detection, and remediation quality across
23
- multiple LLM models.
24
-
25
- # =============================================================================
26
- # Multi-Model Configuration
27
- # =============================================================================
28
-
29
- models_to_test:
30
- - claude-3.5-sonnet # Primary model (high accuracy expected)
31
- - claude-3-haiku # Fast model (ensure minimum quality)
32
- - gpt-4o # Cross-vendor validation
33
-
34
- # =============================================================================
35
- # MCP Integration Configuration
36
- # =============================================================================
37
-
38
- mcp_integration:
39
- enabled: true
40
- namespace: skill-validation
41
-
42
- # Query existing accessibility patterns before running evals
43
- query_patterns: true
44
-
45
- # Track each test outcome for learning feedback
46
- track_outcomes: true
47
-
48
- # Store successful patterns (WCAG violations, remediation approaches)
49
- store_patterns: true
50
-
51
- # Share learning with fleet coordinator agents
52
- share_learning: true
53
-
54
- # Update quality gate with accessibility metrics
55
- update_quality_gate: true
56
-
57
- # Agents to share learning with
58
- target_agents:
59
- - qe-learning-coordinator
60
- - qe-queen-coordinator
61
- - qe-accessibility-auditor
62
-
63
- # =============================================================================
64
- # ReasoningBank Learning Configuration
65
- # =============================================================================
66
-
67
- learning:
68
- store_success_patterns: true
69
- store_failure_patterns: true
70
- pattern_ttl_days: 90
71
- min_confidence_to_store: 0.7
72
- cross_model_comparison: true
73
-
74
- # =============================================================================
75
- # Result Format Configuration
76
- # =============================================================================
77
-
78
- result_format:
79
- json_output: true
80
- markdown_report: true
81
- include_raw_output: false
82
- include_timing: true
83
- include_token_usage: true
84
-
85
- # =============================================================================
86
- # Environment Setup
87
- # =============================================================================
88
-
89
- setup:
90
- required_tools:
91
- - jq
92
- environment_variables:
93
- WCAG_VERSION: "2.2"
94
- TARGET_LEVEL: "AA"
95
- fixtures:
96
- - name: accessible_page
97
- content: |
98
- <!DOCTYPE html>
99
- <html lang="en">
100
- <head><title>Accessible Page</title></head>
101
- <body>
102
- <header><nav aria-label="Main"><a href="/">Home</a></nav></header>
103
- <main>
104
- <h1>Welcome</h1>
105
- <img src="hero.jpg" alt="Person using laptop">
106
- <form>
107
- <label for="email">Email:</label>
108
- <input type="email" id="email" name="email" required>
109
- <button type="submit">Subscribe</button>
110
- </form>
111
- </main>
112
- </body>
113
- </html>
114
- - name: inaccessible_page
115
- content: |
116
- <!DOCTYPE html>
117
- <html>
118
- <head><title></title></head>
119
- <body>
120
- <div onclick="navigate()">Menu</div>
121
- <img src="logo.png">
122
- <input type="text" placeholder="Enter email">
123
- <span style="color: #999; background: #fff;">Light gray text</span>
124
- </body>
125
- </html>
126
-
127
- # =============================================================================
128
- # Test Cases - POUR Principles Coverage
129
- # =============================================================================
130
-
131
- test_cases:
132
- # -------------------------------------------------------------------------
133
- # PERCEIVABLE (WCAG 1.x) - Content can be perceived
134
- # -------------------------------------------------------------------------
135
-
136
- - id: tc001_perceivable_alt_text
137
- description: "Detect missing alt text on images (WCAG 1.1.1)"
138
- category: perceivable
139
- priority: critical
140
-
141
- input:
142
- code: |
143
- <img src="product.jpg">
144
- <img src="banner.png" alt="">
145
- <img src="hero.jpg" alt="Team collaboration in modern office">
146
- context:
147
- language: html
148
- wcagLevel: AA
149
-
150
- expected_output:
151
- must_contain:
152
- - "alt"
153
- - "1.1.1"
154
- - "perceivable"
155
- must_not_contain:
156
- - "no issues"
157
- finding_count:
158
- min: 1
159
- max: 2
160
- severity_classification: serious
161
-
162
- validation:
163
- schema_check: true
164
- keyword_match_threshold: 0.9
165
- reasoning_quality_min: 0.7
166
-
167
- - id: tc002_perceivable_color_contrast
168
- description: "Detect insufficient color contrast (WCAG 1.4.3)"
169
- category: perceivable
170
- priority: critical
171
-
172
- input:
173
- code: |
174
- <p style="color: #777; background-color: #fff;">Gray text on white</p>
175
- <p style="color: #333; background-color: #fff;">Dark text on white</p>
176
- <h1 style="color: #aaa; background-color: #eee;">Low contrast heading</h1>
177
- context:
178
- language: html
179
- wcagLevel: AA
180
-
181
- expected_output:
182
- must_contain:
183
- - "contrast"
184
- - "1.4.3"
185
- - "4.5:1"
186
- finding_count:
187
- min: 1
188
- max: 3
189
-
190
- validation:
191
- schema_check: true
192
- keyword_match_threshold: 0.8
193
-
194
- - id: tc003_perceivable_video_captions
195
- description: "Detect videos without captions (WCAG 1.2.2)"
196
- category: perceivable
197
- priority: critical
198
-
199
- input:
200
- code: |
201
- <video src="product-demo.mp4" controls>
202
- <source src="product-demo.mp4" type="video/mp4">
203
- </video>
204
- <video controls>
205
- <source src="interview.mp4" type="video/mp4">
206
- <track kind="captions" src="captions.vtt" srclang="en">
207
- </video>
208
- context:
209
- language: html
210
- wcagLevel: AA
211
-
212
- expected_output:
213
- must_contain:
214
- - "caption"
215
- - "1.2.2"
216
- - "track"
217
- finding_count:
218
- min: 1
219
- max: 2
220
-
221
- validation:
222
- schema_check: true
223
- keyword_match_threshold: 0.8
224
-
225
- # -------------------------------------------------------------------------
226
- # OPERABLE (WCAG 2.x) - Interface is operable
227
- # -------------------------------------------------------------------------
228
-
229
- - id: tc004_operable_keyboard_access
230
- description: "Detect elements not keyboard accessible (WCAG 2.1.1)"
231
- category: operable
232
- priority: critical
233
-
234
- input:
235
- code: |
236
- <div onclick="handleClick()">Click me</div>
237
- <span class="button" onclick="submit()">Submit</span>
238
- <button onclick="save()">Save</button>
239
- <a href="/next">Next Page</a>
240
- context:
241
- language: html
242
- wcagLevel: A
243
-
244
- expected_output:
245
- must_contain:
246
- - "keyboard"
247
- - "2.1.1"
248
- - "operable"
249
- - "button"
250
- must_not_contain:
251
- - "all elements accessible"
252
- finding_count:
253
- min: 2
254
- max: 3
255
- severity_classification: critical
256
-
257
- validation:
258
- schema_check: true
259
- keyword_match_threshold: 0.9
260
- reasoning_quality_min: 0.8
261
-
262
- - id: tc005_operable_focus_visible
263
- description: "Detect missing focus indicators (WCAG 2.4.7)"
264
- category: operable
265
- priority: high
266
-
267
- input:
268
- code: |
269
- <style>
270
- button:focus { outline: none; }
271
- a:focus { outline: 0; }
272
- input:focus { outline: none; border-color: blue; }
273
- </style>
274
- <button>Submit</button>
275
- <a href="/">Home</a>
276
- <input type="text" placeholder="Search">
277
- context:
278
- language: html
279
- wcagLevel: AA
280
-
281
- expected_output:
282
- must_contain:
283
- - "focus"
284
- - "2.4.7"
285
- - "outline"
286
- finding_count:
287
- min: 2
288
- max: 3
289
-
290
- validation:
291
- schema_check: true
292
- keyword_match_threshold: 0.8
293
-
294
- - id: tc006_operable_keyboard_trap
295
- description: "Detect keyboard traps (WCAG 2.1.2)"
296
- category: operable
297
- priority: critical
298
-
299
- input:
300
- code: |
301
- <div id="modal" tabindex="0" onkeydown="if(event.key==='Tab'){event.preventDefault();}">
302
- <h2>Modal Dialog</h2>
303
- <input type="text" placeholder="Enter name">
304
- <button>Close</button>
305
- </div>
306
- context:
307
- language: html
308
- wcagLevel: A
309
- description: "Modal with keyboard trap"
310
-
311
- expected_output:
312
- must_contain:
313
- - "keyboard trap"
314
- - "2.1.2"
315
- - "Tab"
316
- severity_classification: critical
317
-
318
- validation:
319
- schema_check: true
320
-
321
- # -------------------------------------------------------------------------
322
- # UNDERSTANDABLE (WCAG 3.x) - Content is understandable
323
- # -------------------------------------------------------------------------
324
-
325
- - id: tc007_understandable_form_labels
326
- description: "Detect form inputs without labels (WCAG 3.3.2)"
327
- category: understandable
328
- priority: high
329
-
330
- input:
331
- code: |
332
- <form>
333
- <input type="text" placeholder="Name">
334
- <input type="email" placeholder="Email">
335
- <label for="phone">Phone:</label>
336
- <input type="tel" id="phone">
337
- <button>Submit</button>
338
- </form>
339
- context:
340
- language: html
341
- wcagLevel: A
342
-
343
- expected_output:
344
- must_contain:
345
- - "label"
346
- - "3.3.2"
347
- - "understandable"
348
- finding_count:
349
- min: 2
350
- max: 3
351
-
352
- validation:
353
- schema_check: true
354
- keyword_match_threshold: 0.8
355
-
356
- - id: tc008_understandable_error_messages
357
- description: "Detect missing error identification (WCAG 3.3.1)"
358
- category: understandable
359
- priority: high
360
-
361
- input:
362
- code: |
363
- <form>
364
- <input type="email" required aria-invalid="true">
365
- <span style="color: red;">*</span>
366
- <input type="password" required aria-describedby="pwd-error">
367
- <span id="pwd-error" role="alert">Password must be 8+ characters</span>
368
- </form>
369
- context:
370
- language: html
371
- wcagLevel: A
372
-
373
- expected_output:
374
- must_contain:
375
- - "error"
376
- - "3.3.1"
377
- finding_count:
378
- min: 1
379
- max: 2
380
-
381
- validation:
382
- schema_check: true
383
-
384
- - id: tc009_understandable_language
385
- description: "Detect missing page language (WCAG 3.1.1)"
386
- category: understandable
387
- priority: high
388
-
389
- input:
390
- code: |
391
- <!DOCTYPE html>
392
- <html>
393
- <head><title>My Page</title></head>
394
- <body><h1>Welcome</h1></body>
395
- </html>
396
- context:
397
- language: html
398
- wcagLevel: A
399
-
400
- expected_output:
401
- must_contain:
402
- - "lang"
403
- - "3.1.1"
404
- - "language"
405
- finding_count:
406
- min: 1
407
- max: 1
408
- severity_classification: serious
409
-
410
- validation:
411
- schema_check: true
412
- keyword_match_threshold: 0.9
413
-
414
- # -------------------------------------------------------------------------
415
- # ROBUST (WCAG 4.x) - Compatible with assistive technologies
416
- # -------------------------------------------------------------------------
417
-
418
- - id: tc010_robust_aria_valid
419
- description: "Detect invalid ARIA attributes (WCAG 4.1.2)"
420
- category: robust
421
- priority: high
422
-
423
- input:
424
- code: |
425
- <button aria-label="">Submit</button>
426
- <div role="button" aria-pressed="maybe">Toggle</div>
427
- <input type="checkbox" aria-checked="true">
428
- <nav aria-labelledby="nonexistent">Navigation</nav>
429
- context:
430
- language: html
431
- wcagLevel: A
432
-
433
- expected_output:
434
- must_contain:
435
- - "ARIA"
436
- - "4.1.2"
437
- - "robust"
438
- finding_count:
439
- min: 2
440
- max: 4
441
-
442
- validation:
443
- schema_check: true
444
- keyword_match_threshold: 0.8
445
-
446
- - id: tc011_robust_html_parsing
447
- description: "Detect HTML parsing errors (WCAG 4.1.1)"
448
- category: robust
449
- priority: medium
450
-
451
- input:
452
- code: |
453
- <html>
454
- <head><title>Page</head>
455
- <body>
456
- <div id="main">
457
- <p>Unclosed paragraph
458
- <div id="main">Duplicate ID</div>
459
- </div>
460
- </body>
461
- </html>
462
- context:
463
- language: html
464
- wcagLevel: A
465
-
466
- expected_output:
467
- must_contain:
468
- - "4.1.1"
469
- - "parsing"
470
- finding_count:
471
- min: 1
472
- max: 4
473
-
474
- validation:
475
- schema_check: true
476
-
477
- # -------------------------------------------------------------------------
478
- # Negative Tests (Should NOT find issues)
479
- # -------------------------------------------------------------------------
480
-
481
- - id: tc012_no_false_positives_accessible
482
- description: "Fully accessible page should not flag critical issues"
483
- category: negative
484
- priority: critical
485
-
486
- input:
487
- code: |
488
- <!DOCTYPE html>
489
- <html lang="en">
490
- <head>
491
- <title>Accessible Website</title>
492
- <meta charset="UTF-8">
493
- </head>
494
- <body>
495
- <a href="#main" class="skip-link">Skip to main content</a>
496
- <header>
497
- <nav aria-label="Main navigation">
498
- <ul>
499
- <li><a href="/">Home</a></li>
500
- <li><a href="/about">About</a></li>
501
- </ul>
502
- </nav>
503
- </header>
504
- <main id="main">
505
- <h1>Welcome to Our Site</h1>
506
- <img src="hero.jpg" alt="Happy customers using our product">
507
- <form>
508
- <label for="email">Email address:</label>
509
- <input type="email" id="email" name="email" required aria-describedby="email-hint">
510
- <span id="email-hint">We'll never share your email.</span>
511
- <button type="submit">Subscribe</button>
512
- </form>
513
- </main>
514
- <footer>
515
- <p>&copy; 2026 Accessible Company</p>
516
- </footer>
517
- </body>
518
- </html>
519
- context:
520
- language: html
521
- wcagLevel: AA
522
-
523
- expected_output:
524
- must_contain:
525
- - "accessible"
526
- must_not_contain:
527
- - "critical"
528
- - "serious"
529
- finding_count:
530
- max: 2 # Allow minor/informational findings only
531
-
532
- validation:
533
- schema_check: true
534
- keyword_match_threshold: 0.7
535
-
536
- # -------------------------------------------------------------------------
537
- # Edge Cases
538
- # -------------------------------------------------------------------------
539
-
540
- - id: tc013_dynamic_content_aria_live
541
- description: "Detect missing aria-live for dynamic content"
542
- category: edge_cases
543
- priority: medium
544
-
545
- input:
546
- code: |
547
- <div id="notifications">
548
- <!-- JavaScript updates this -->
549
- </div>
550
- <div id="status" aria-live="polite" role="status">
551
- Loading...
552
- </div>
553
- <div id="alerts" role="alert">
554
- Error occurred!
555
- </div>
556
- context:
557
- language: html
558
- wcagLevel: AA
559
- description: "Dynamic content regions"
560
-
561
- expected_output:
562
- must_contain:
563
- - "aria-live"
564
- - "dynamic"
565
-
566
- validation:
567
- schema_check: true
568
-
569
- - id: tc014_heading_hierarchy
570
- description: "Detect broken heading hierarchy (WCAG 1.3.1)"
571
- category: edge_cases
572
- priority: medium
573
-
574
- input:
575
- code: |
576
- <h1>Main Title</h1>
577
- <h3>Skipped h2!</h3>
578
- <h4>Another section</h4>
579
- <h2>Back to h2</h2>
580
- <h6>Way out of order</h6>
581
- context:
582
- language: html
583
- wcagLevel: A
584
-
585
- expected_output:
586
- must_contain:
587
- - "heading"
588
- - "hierarchy"
589
- - "1.3.1"
590
- finding_count:
591
- min: 1
592
- max: 3
593
-
594
- validation:
595
- schema_check: true
596
-
597
- # -------------------------------------------------------------------------
598
- # Remediation Quality Tests
599
- # -------------------------------------------------------------------------
600
-
601
- - id: tc015_remediation_code_quality
602
- description: "Verify remediation includes actionable code examples"
603
- category: remediation
604
- priority: high
605
-
606
- input:
607
- code: |
608
- <img src="product.jpg">
609
- <div onclick="buy()">Buy Now</div>
610
- context:
611
- language: html
612
- wcagLevel: AA
613
- options:
614
- includeRemediation: true
615
-
616
- expected_output:
617
- must_contain:
618
- - "alt="
619
- - "button"
620
- - "role"
621
- must_match_regex:
622
- - "<img.*alt=\".*\".*>"
623
- - "<button.*>.*</button>"
624
-
625
- validation:
626
- schema_check: true
627
- grading_rubric:
628
- completeness: 0.3
629
- accuracy: 0.4
630
- actionability: 0.3
631
-
632
- # -------------------------------------------------------------------------
633
- # Multi-page / Complex Scenarios
634
- # -------------------------------------------------------------------------
635
-
636
- - id: tc016_complex_form_validation
637
- description: "Complex form with multiple accessibility requirements"
638
- category: integration
639
- priority: high
640
-
641
- input:
642
- code: |
643
- <form id="checkout">
644
- <fieldset>
645
- <legend>Shipping Address</legend>
646
- <input type="text" name="street" placeholder="Street">
647
- <input type="text" name="city" placeholder="City">
648
- <select name="state">
649
- <option value="">Select State</option>
650
- </select>
651
- </fieldset>
652
- <fieldset>
653
- <legend>Payment</legend>
654
- <input type="text" name="card" maxlength="16">
655
- <input type="text" name="cvv" maxlength="3">
656
- </fieldset>
657
- <div class="error" style="display:none;"></div>
658
- <button type="submit">Place Order</button>
659
- </form>
660
- context:
661
- language: html
662
- wcagLevel: AA
663
- environment: production
664
-
665
- expected_output:
666
- must_contain:
667
- - "label"
668
- - "form"
669
- - "3.3"
670
- finding_count:
671
- min: 4
672
- max: 10
673
-
674
- validation:
675
- schema_check: true
676
- keyword_match_threshold: 0.8
677
-
678
- # =============================================================================
679
- # Success Criteria
680
- # =============================================================================
681
-
682
- success_criteria:
683
- # Minimum percentage of tests that must pass
684
- pass_rate: 0.90
685
-
686
- # Critical tests (POUR principle detection) must have 100% pass rate
687
- critical_pass_rate: 1.0
688
-
689
- # Average reasoning quality across all tests
690
- avg_reasoning_quality: 0.75
691
-
692
- # Maximum time for entire suite (5 minutes)
693
- max_execution_time_ms: 300000
694
-
695
- # Maximum variance between different models (15%)
696
- cross_model_variance: 0.15
697
-
698
- # =============================================================================
699
- # Metadata
700
- # =============================================================================
701
-
702
- metadata:
703
- author: "@aqe-team"
704
- created: "2026-02-02"
705
- last_updated: "2026-02-02"
706
- coverage_target: "POUR principles, WCAG 2.2 A/AA criteria, remediation quality"
707
- wcag_criteria_covered:
708
- - "1.1.1 Non-text Content"
709
- - "1.2.2 Captions (Prerecorded)"
710
- - "1.3.1 Info and Relationships"
711
- - "1.4.3 Contrast (Minimum)"
712
- - "2.1.1 Keyboard"
713
- - "2.1.2 No Keyboard Trap"
714
- - "2.4.7 Focus Visible"
715
- - "3.1.1 Language of Page"
716
- - "3.3.1 Error Identification"
717
- - "3.3.2 Labels or Instructions"
718
- - "4.1.1 Parsing"
719
- - "4.1.2 Name, Role, Value"
1
+ # =============================================================================
2
+ # AQE Accessibility Testing Skill Evaluation Suite v1.0.0
3
+ # WCAG 2.2 compliance testing evaluation with POUR principle coverage
4
+ # =============================================================================
5
+ #
6
+ # This evaluation suite validates accessibility testing skill behavior through:
7
+ # 1. POUR principle coverage (Perceivable, Operable, Understandable, Robust)
8
+ # 2. WCAG 2.2 Level A, AA, AAA conformance testing
9
+ # 3. Multi-model consistency across Claude and GPT models
10
+ # 4. Severity classification validation
11
+ # 5. Remediation quality assessment
12
+ #
13
+ # Schema: .validation/schemas/skill-eval.schema.json
14
+ # Runner: scripts/run-skill-eval.ts
15
+ # =============================================================================
16
+
17
+ skill: accessibility-testing
18
+ version: 1.0.0
19
+ description: >
20
+ Comprehensive evaluation suite for WCAG 2.2 accessibility testing skill.
21
+ Tests POUR principles (Perceivable, Operable, Understandable, Robust),
22
+ conformance levels, finding detection, and remediation quality across
23
+ multiple LLM models.
24
+
25
+ # =============================================================================
26
+ # Multi-Model Configuration
27
+ # =============================================================================
28
+
29
+ models_to_test:
30
+ - claude-3.5-sonnet # Primary model (high accuracy expected)
31
+ - claude-3-haiku # Fast model (ensure minimum quality)
32
+ - gpt-4o # Cross-vendor validation
33
+
34
+ # =============================================================================
35
+ # MCP Integration Configuration
36
+ # =============================================================================
37
+
38
+ mcp_integration:
39
+ enabled: true
40
+ namespace: skill-validation
41
+
42
+ # Query existing accessibility patterns before running evals
43
+ query_patterns: true
44
+
45
+ # Track each test outcome for learning feedback
46
+ track_outcomes: true
47
+
48
+ # Store successful patterns (WCAG violations, remediation approaches)
49
+ store_patterns: true
50
+
51
+ # Share learning with fleet coordinator agents
52
+ share_learning: true
53
+
54
+ # Update quality gate with accessibility metrics
55
+ update_quality_gate: true
56
+
57
+ # Agents to share learning with
58
+ target_agents:
59
+ - qe-learning-coordinator
60
+ - qe-queen-coordinator
61
+ - qe-accessibility-auditor
62
+
63
+ # =============================================================================
64
+ # ReasoningBank Learning Configuration
65
+ # =============================================================================
66
+
67
+ learning:
68
+ store_success_patterns: true
69
+ store_failure_patterns: true
70
+ pattern_ttl_days: 90
71
+ min_confidence_to_store: 0.7
72
+ cross_model_comparison: true
73
+
74
+ # =============================================================================
75
+ # Result Format Configuration
76
+ # =============================================================================
77
+
78
+ result_format:
79
+ json_output: true
80
+ markdown_report: true
81
+ include_raw_output: false
82
+ include_timing: true
83
+ include_token_usage: true
84
+
85
+ # =============================================================================
86
+ # Environment Setup
87
+ # =============================================================================
88
+
89
+ setup:
90
+ required_tools:
91
+ - jq
92
+ environment_variables:
93
+ WCAG_VERSION: "2.2"
94
+ TARGET_LEVEL: "AA"
95
+ fixtures:
96
+ - name: accessible_page
97
+ content: |
98
+ <!DOCTYPE html>
99
+ <html lang="en">
100
+ <head><title>Accessible Page</title></head>
101
+ <body>
102
+ <header><nav aria-label="Main"><a href="/">Home</a></nav></header>
103
+ <main>
104
+ <h1>Welcome</h1>
105
+ <img src="hero.jpg" alt="Person using laptop">
106
+ <form>
107
+ <label for="email">Email:</label>
108
+ <input type="email" id="email" name="email" required>
109
+ <button type="submit">Subscribe</button>
110
+ </form>
111
+ </main>
112
+ </body>
113
+ </html>
114
+ - name: inaccessible_page
115
+ content: |
116
+ <!DOCTYPE html>
117
+ <html>
118
+ <head><title></title></head>
119
+ <body>
120
+ <div onclick="navigate()">Menu</div>
121
+ <img src="logo.png">
122
+ <input type="text" placeholder="Enter email">
123
+ <span style="color: #999; background: #fff;">Light gray text</span>
124
+ </body>
125
+ </html>
126
+
127
+ # =============================================================================
128
+ # Test Cases - POUR Principles Coverage
129
+ # =============================================================================
130
+
131
+ test_cases:
132
+ # -------------------------------------------------------------------------
133
+ # PERCEIVABLE (WCAG 1.x) - Content can be perceived
134
+ # -------------------------------------------------------------------------
135
+
136
+ - id: tc001_perceivable_alt_text
137
+ description: "Detect missing alt text on images (WCAG 1.1.1)"
138
+ category: perceivable
139
+ priority: critical
140
+
141
+ input:
142
+ code: |
143
+ <img src="product.jpg">
144
+ <img src="banner.png" alt="">
145
+ <img src="hero.jpg" alt="Team collaboration in modern office">
146
+ context:
147
+ language: html
148
+ wcagLevel: AA
149
+
150
+ expected_output:
151
+ must_contain:
152
+ - "alt"
153
+ - "1.1.1"
154
+ - "perceivable"
155
+ must_not_contain:
156
+ - "no issues"
157
+ finding_count:
158
+ min: 1
159
+ max: 2
160
+ severity_classification: serious
161
+
162
+ validation:
163
+ schema_check: true
164
+ keyword_match_threshold: 0.9
165
+ reasoning_quality_min: 0.7
166
+
167
+ - id: tc002_perceivable_color_contrast
168
+ description: "Detect insufficient color contrast (WCAG 1.4.3)"
169
+ category: perceivable
170
+ priority: critical
171
+
172
+ input:
173
+ code: |
174
+ <p style="color: #777; background-color: #fff;">Gray text on white</p>
175
+ <p style="color: #333; background-color: #fff;">Dark text on white</p>
176
+ <h1 style="color: #aaa; background-color: #eee;">Low contrast heading</h1>
177
+ context:
178
+ language: html
179
+ wcagLevel: AA
180
+
181
+ expected_output:
182
+ must_contain:
183
+ - "contrast"
184
+ - "1.4.3"
185
+ - "4.5:1"
186
+ finding_count:
187
+ min: 1
188
+ max: 3
189
+
190
+ validation:
191
+ schema_check: true
192
+ keyword_match_threshold: 0.8
193
+
194
+ - id: tc003_perceivable_video_captions
195
+ description: "Detect videos without captions (WCAG 1.2.2)"
196
+ category: perceivable
197
+ priority: critical
198
+
199
+ input:
200
+ code: |
201
+ <video src="product-demo.mp4" controls>
202
+ <source src="product-demo.mp4" type="video/mp4">
203
+ </video>
204
+ <video controls>
205
+ <source src="interview.mp4" type="video/mp4">
206
+ <track kind="captions" src="captions.vtt" srclang="en">
207
+ </video>
208
+ context:
209
+ language: html
210
+ wcagLevel: AA
211
+
212
+ expected_output:
213
+ must_contain:
214
+ - "caption"
215
+ - "1.2.2"
216
+ - "track"
217
+ finding_count:
218
+ min: 1
219
+ max: 2
220
+
221
+ validation:
222
+ schema_check: true
223
+ keyword_match_threshold: 0.8
224
+
225
+ # -------------------------------------------------------------------------
226
+ # OPERABLE (WCAG 2.x) - Interface is operable
227
+ # -------------------------------------------------------------------------
228
+
229
+ - id: tc004_operable_keyboard_access
230
+ description: "Detect elements not keyboard accessible (WCAG 2.1.1)"
231
+ category: operable
232
+ priority: critical
233
+
234
+ input:
235
+ code: |
236
+ <div onclick="handleClick()">Click me</div>
237
+ <span class="button" onclick="submit()">Submit</span>
238
+ <button onclick="save()">Save</button>
239
+ <a href="/next">Next Page</a>
240
+ context:
241
+ language: html
242
+ wcagLevel: A
243
+
244
+ expected_output:
245
+ must_contain:
246
+ - "keyboard"
247
+ - "2.1.1"
248
+ - "operable"
249
+ - "button"
250
+ must_not_contain:
251
+ - "all elements accessible"
252
+ finding_count:
253
+ min: 2
254
+ max: 3
255
+ severity_classification: critical
256
+
257
+ validation:
258
+ schema_check: true
259
+ keyword_match_threshold: 0.9
260
+ reasoning_quality_min: 0.8
261
+
262
+ - id: tc005_operable_focus_visible
263
+ description: "Detect missing focus indicators (WCAG 2.4.7)"
264
+ category: operable
265
+ priority: high
266
+
267
+ input:
268
+ code: |
269
+ <style>
270
+ button:focus { outline: none; }
271
+ a:focus { outline: 0; }
272
+ input:focus { outline: none; border-color: blue; }
273
+ </style>
274
+ <button>Submit</button>
275
+ <a href="/">Home</a>
276
+ <input type="text" placeholder="Search">
277
+ context:
278
+ language: html
279
+ wcagLevel: AA
280
+
281
+ expected_output:
282
+ must_contain:
283
+ - "focus"
284
+ - "2.4.7"
285
+ - "outline"
286
+ finding_count:
287
+ min: 2
288
+ max: 3
289
+
290
+ validation:
291
+ schema_check: true
292
+ keyword_match_threshold: 0.8
293
+
294
+ - id: tc006_operable_keyboard_trap
295
+ description: "Detect keyboard traps (WCAG 2.1.2)"
296
+ category: operable
297
+ priority: critical
298
+
299
+ input:
300
+ code: |
301
+ <div id="modal" tabindex="0" onkeydown="if(event.key==='Tab'){event.preventDefault();}">
302
+ <h2>Modal Dialog</h2>
303
+ <input type="text" placeholder="Enter name">
304
+ <button>Close</button>
305
+ </div>
306
+ context:
307
+ language: html
308
+ wcagLevel: A
309
+ description: "Modal with keyboard trap"
310
+
311
+ expected_output:
312
+ must_contain:
313
+ - "keyboard trap"
314
+ - "2.1.2"
315
+ - "Tab"
316
+ severity_classification: critical
317
+
318
+ validation:
319
+ schema_check: true
320
+
321
+ # -------------------------------------------------------------------------
322
+ # UNDERSTANDABLE (WCAG 3.x) - Content is understandable
323
+ # -------------------------------------------------------------------------
324
+
325
+ - id: tc007_understandable_form_labels
326
+ description: "Detect form inputs without labels (WCAG 3.3.2)"
327
+ category: understandable
328
+ priority: high
329
+
330
+ input:
331
+ code: |
332
+ <form>
333
+ <input type="text" placeholder="Name">
334
+ <input type="email" placeholder="Email">
335
+ <label for="phone">Phone:</label>
336
+ <input type="tel" id="phone">
337
+ <button>Submit</button>
338
+ </form>
339
+ context:
340
+ language: html
341
+ wcagLevel: A
342
+
343
+ expected_output:
344
+ must_contain:
345
+ - "label"
346
+ - "3.3.2"
347
+ - "understandable"
348
+ finding_count:
349
+ min: 2
350
+ max: 3
351
+
352
+ validation:
353
+ schema_check: true
354
+ keyword_match_threshold: 0.8
355
+
356
+ - id: tc008_understandable_error_messages
357
+ description: "Detect missing error identification (WCAG 3.3.1)"
358
+ category: understandable
359
+ priority: high
360
+
361
+ input:
362
+ code: |
363
+ <form>
364
+ <input type="email" required aria-invalid="true">
365
+ <span style="color: red;">*</span>
366
+ <input type="password" required aria-describedby="pwd-error">
367
+ <span id="pwd-error" role="alert">Password must be 8+ characters</span>
368
+ </form>
369
+ context:
370
+ language: html
371
+ wcagLevel: A
372
+
373
+ expected_output:
374
+ must_contain:
375
+ - "error"
376
+ - "3.3.1"
377
+ finding_count:
378
+ min: 1
379
+ max: 2
380
+
381
+ validation:
382
+ schema_check: true
383
+
384
+ - id: tc009_understandable_language
385
+ description: "Detect missing page language (WCAG 3.1.1)"
386
+ category: understandable
387
+ priority: high
388
+
389
+ input:
390
+ code: |
391
+ <!DOCTYPE html>
392
+ <html>
393
+ <head><title>My Page</title></head>
394
+ <body><h1>Welcome</h1></body>
395
+ </html>
396
+ context:
397
+ language: html
398
+ wcagLevel: A
399
+
400
+ expected_output:
401
+ must_contain:
402
+ - "lang"
403
+ - "3.1.1"
404
+ - "language"
405
+ finding_count:
406
+ min: 1
407
+ max: 1
408
+ severity_classification: serious
409
+
410
+ validation:
411
+ schema_check: true
412
+ keyword_match_threshold: 0.9
413
+
414
+ # -------------------------------------------------------------------------
415
+ # ROBUST (WCAG 4.x) - Compatible with assistive technologies
416
+ # -------------------------------------------------------------------------
417
+
418
+ - id: tc010_robust_aria_valid
419
+ description: "Detect invalid ARIA attributes (WCAG 4.1.2)"
420
+ category: robust
421
+ priority: high
422
+
423
+ input:
424
+ code: |
425
+ <button aria-label="">Submit</button>
426
+ <div role="button" aria-pressed="maybe">Toggle</div>
427
+ <input type="checkbox" aria-checked="true">
428
+ <nav aria-labelledby="nonexistent">Navigation</nav>
429
+ context:
430
+ language: html
431
+ wcagLevel: A
432
+
433
+ expected_output:
434
+ must_contain:
435
+ - "ARIA"
436
+ - "4.1.2"
437
+ - "robust"
438
+ finding_count:
439
+ min: 2
440
+ max: 4
441
+
442
+ validation:
443
+ schema_check: true
444
+ keyword_match_threshold: 0.8
445
+
446
+ - id: tc011_robust_html_parsing
447
+ description: "Detect HTML parsing errors (WCAG 4.1.1)"
448
+ category: robust
449
+ priority: medium
450
+
451
+ input:
452
+ code: |
453
+ <html>
454
+ <head><title>Page</head>
455
+ <body>
456
+ <div id="main">
457
+ <p>Unclosed paragraph
458
+ <div id="main">Duplicate ID</div>
459
+ </div>
460
+ </body>
461
+ </html>
462
+ context:
463
+ language: html
464
+ wcagLevel: A
465
+
466
+ expected_output:
467
+ must_contain:
468
+ - "4.1.1"
469
+ - "parsing"
470
+ finding_count:
471
+ min: 1
472
+ max: 4
473
+
474
+ validation:
475
+ schema_check: true
476
+
477
+ # -------------------------------------------------------------------------
478
+ # Negative Tests (Should NOT find issues)
479
+ # -------------------------------------------------------------------------
480
+
481
+ - id: tc012_no_false_positives_accessible
482
+ description: "Fully accessible page should not flag critical issues"
483
+ category: negative
484
+ priority: critical
485
+
486
+ input:
487
+ code: |
488
+ <!DOCTYPE html>
489
+ <html lang="en">
490
+ <head>
491
+ <title>Accessible Website</title>
492
+ <meta charset="UTF-8">
493
+ </head>
494
+ <body>
495
+ <a href="#main" class="skip-link">Skip to main content</a>
496
+ <header>
497
+ <nav aria-label="Main navigation">
498
+ <ul>
499
+ <li><a href="/">Home</a></li>
500
+ <li><a href="/about">About</a></li>
501
+ </ul>
502
+ </nav>
503
+ </header>
504
+ <main id="main">
505
+ <h1>Welcome to Our Site</h1>
506
+ <img src="hero.jpg" alt="Happy customers using our product">
507
+ <form>
508
+ <label for="email">Email address:</label>
509
+ <input type="email" id="email" name="email" required aria-describedby="email-hint">
510
+ <span id="email-hint">We'll never share your email.</span>
511
+ <button type="submit">Subscribe</button>
512
+ </form>
513
+ </main>
514
+ <footer>
515
+ <p>&copy; 2026 Accessible Company</p>
516
+ </footer>
517
+ </body>
518
+ </html>
519
+ context:
520
+ language: html
521
+ wcagLevel: AA
522
+
523
+ expected_output:
524
+ must_contain:
525
+ - "accessible"
526
+ must_not_contain:
527
+ - "critical"
528
+ - "serious"
529
+ finding_count:
530
+ max: 2 # Allow minor/informational findings only
531
+
532
+ validation:
533
+ schema_check: true
534
+ keyword_match_threshold: 0.7
535
+
536
+ # -------------------------------------------------------------------------
537
+ # Edge Cases
538
+ # -------------------------------------------------------------------------
539
+
540
+ - id: tc013_dynamic_content_aria_live
541
+ description: "Detect missing aria-live for dynamic content"
542
+ category: edge_cases
543
+ priority: medium
544
+
545
+ input:
546
+ code: |
547
+ <div id="notifications">
548
+ <!-- JavaScript updates this -->
549
+ </div>
550
+ <div id="status" aria-live="polite" role="status">
551
+ Loading...
552
+ </div>
553
+ <div id="alerts" role="alert">
554
+ Error occurred!
555
+ </div>
556
+ context:
557
+ language: html
558
+ wcagLevel: AA
559
+ description: "Dynamic content regions"
560
+
561
+ expected_output:
562
+ must_contain:
563
+ - "aria-live"
564
+ - "dynamic"
565
+
566
+ validation:
567
+ schema_check: true
568
+
569
+ - id: tc014_heading_hierarchy
570
+ description: "Detect broken heading hierarchy (WCAG 1.3.1)"
571
+ category: edge_cases
572
+ priority: medium
573
+
574
+ input:
575
+ code: |
576
+ <h1>Main Title</h1>
577
+ <h3>Skipped h2!</h3>
578
+ <h4>Another section</h4>
579
+ <h2>Back to h2</h2>
580
+ <h6>Way out of order</h6>
581
+ context:
582
+ language: html
583
+ wcagLevel: A
584
+
585
+ expected_output:
586
+ must_contain:
587
+ - "heading"
588
+ - "hierarchy"
589
+ - "1.3.1"
590
+ finding_count:
591
+ min: 1
592
+ max: 3
593
+
594
+ validation:
595
+ schema_check: true
596
+
597
+ # -------------------------------------------------------------------------
598
+ # Remediation Quality Tests
599
+ # -------------------------------------------------------------------------
600
+
601
+ - id: tc015_remediation_code_quality
602
+ description: "Verify remediation includes actionable code examples"
603
+ category: remediation
604
+ priority: high
605
+
606
+ input:
607
+ code: |
608
+ <img src="product.jpg">
609
+ <div onclick="buy()">Buy Now</div>
610
+ context:
611
+ language: html
612
+ wcagLevel: AA
613
+ options:
614
+ includeRemediation: true
615
+
616
+ expected_output:
617
+ must_contain:
618
+ - "alt="
619
+ - "button"
620
+ - "role"
621
+ must_match_regex:
622
+ - "<img.*alt=\".*\".*>"
623
+ - "<button.*>.*</button>"
624
+
625
+ validation:
626
+ schema_check: true
627
+ grading_rubric:
628
+ completeness: 0.3
629
+ accuracy: 0.4
630
+ actionability: 0.3
631
+
632
+ # -------------------------------------------------------------------------
633
+ # Multi-page / Complex Scenarios
634
+ # -------------------------------------------------------------------------
635
+
636
+ - id: tc016_complex_form_validation
637
+ description: "Complex form with multiple accessibility requirements"
638
+ category: integration
639
+ priority: high
640
+
641
+ input:
642
+ code: |
643
+ <form id="checkout">
644
+ <fieldset>
645
+ <legend>Shipping Address</legend>
646
+ <input type="text" name="street" placeholder="Street">
647
+ <input type="text" name="city" placeholder="City">
648
+ <select name="state">
649
+ <option value="">Select State</option>
650
+ </select>
651
+ </fieldset>
652
+ <fieldset>
653
+ <legend>Payment</legend>
654
+ <input type="text" name="card" maxlength="16">
655
+ <input type="text" name="cvv" maxlength="3">
656
+ </fieldset>
657
+ <div class="error" style="display:none;"></div>
658
+ <button type="submit">Place Order</button>
659
+ </form>
660
+ context:
661
+ language: html
662
+ wcagLevel: AA
663
+ environment: production
664
+
665
+ expected_output:
666
+ must_contain:
667
+ - "label"
668
+ - "form"
669
+ - "3.3"
670
+ finding_count:
671
+ min: 4
672
+ max: 10
673
+
674
+ validation:
675
+ schema_check: true
676
+ keyword_match_threshold: 0.8
677
+
678
+ # =============================================================================
679
+ # Success Criteria
680
+ # =============================================================================
681
+
682
+ success_criteria:
683
+ # Minimum percentage of tests that must pass
684
+ pass_rate: 0.90
685
+
686
+ # Critical tests (POUR principle detection) must have 100% pass rate
687
+ critical_pass_rate: 1.0
688
+
689
+ # Average reasoning quality across all tests
690
+ avg_reasoning_quality: 0.75
691
+
692
+ # Maximum time for entire suite (5 minutes)
693
+ max_execution_time_ms: 300000
694
+
695
+ # Maximum variance between different models (15%)
696
+ cross_model_variance: 0.15
697
+
698
+ # =============================================================================
699
+ # Metadata
700
+ # =============================================================================
701
+
702
+ metadata:
703
+ author: "@aqe-team"
704
+ created: "2026-02-02"
705
+ last_updated: "2026-02-02"
706
+ coverage_target: "POUR principles, WCAG 2.2 A/AA criteria, remediation quality"
707
+ wcag_criteria_covered:
708
+ - "1.1.1 Non-text Content"
709
+ - "1.2.2 Captions (Prerecorded)"
710
+ - "1.3.1 Info and Relationships"
711
+ - "1.4.3 Contrast (Minimum)"
712
+ - "2.1.1 Keyboard"
713
+ - "2.1.2 No Keyboard Trap"
714
+ - "2.4.7 Focus Visible"
715
+ - "3.1.1 Language of Page"
716
+ - "3.3.1 Error Identification"
717
+ - "3.3.2 Labels or Instructions"
718
+ - "4.1.1 Parsing"
719
+ - "4.1.2 Name, Role, Value"