agentic-qe 3.4.1 → 3.4.2

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 (496) hide show
  1. package/.claude/skills/.validation/README.md +111 -0
  2. package/.claude/skills/.validation/examples/chaos-engineering-output.example.json +530 -0
  3. package/.claude/skills/.validation/examples/performance-testing-output.example.json +252 -0
  4. package/.claude/skills/.validation/examples/security-testing-output.example.json +413 -0
  5. package/.claude/skills/.validation/examples/testability-scoring-output.example.json +350 -0
  6. package/.claude/skills/.validation/schemas/skill-eval.schema.json +452 -0
  7. package/.claude/skills/.validation/schemas/skill-frontmatter.schema.json +341 -0
  8. package/.claude/skills/.validation/schemas/skill-output-meta.schema.json +199 -0
  9. package/.claude/skills/.validation/schemas/skill-output.template.json +610 -0
  10. package/.claude/skills/.validation/skill-validation-mcp-integration.md +250 -0
  11. package/.claude/skills/.validation/templates/eval.template.yaml +366 -0
  12. package/.claude/skills/.validation/templates/schemas/output.json +145 -0
  13. package/.claude/skills/.validation/templates/security-testing-eval.template.yaml +725 -0
  14. package/.claude/skills/.validation/templates/skill-frontmatter.example.yaml +225 -0
  15. package/.claude/skills/.validation/templates/validate.template.sh +1060 -0
  16. package/.claude/skills/.validation/templates/validator-lib.sh +1031 -0
  17. package/.claude/skills/.validation/test-data/invalid-output.json +5 -0
  18. package/.claude/skills/.validation/test-data/minimal-output.json +9 -0
  19. package/.claude/skills/.validation/test-data/sample-output.json +73 -0
  20. package/.claude/skills/TRUST-TIERS.md +158 -0
  21. package/.claude/skills/a11y-ally/SKILL.md +1664 -1658
  22. package/.claude/skills/a11y-ally/evals/a11y-ally.yaml +376 -0
  23. package/.claude/skills/a11y-ally/schemas/output.json +549 -0
  24. package/.claude/skills/a11y-ally/scripts/validate.sh +690 -0
  25. package/.claude/skills/accessibility-testing/SKILL.md +8 -1
  26. package/.claude/skills/accessibility-testing/evals/accessibility-testing.yaml +719 -0
  27. package/.claude/skills/accessibility-testing/schemas/output.json +776 -0
  28. package/.claude/skills/accessibility-testing/scripts/validate.sh +943 -0
  29. package/.claude/skills/accessibility-testing/test-data/sample-output.json +191 -0
  30. package/.claude/skills/agentic-quality-engineering/SKILL.md +4 -0
  31. package/.claude/skills/agentic-quality-engineering/schemas/output.json +577 -0
  32. package/.claude/skills/api-testing-patterns/SKILL.md +5 -0
  33. package/.claude/skills/api-testing-patterns/evals/api-testing-patterns.yaml +696 -0
  34. package/.claude/skills/api-testing-patterns/schemas/output.json +845 -0
  35. package/.claude/skills/api-testing-patterns/scripts/validate.sh +931 -0
  36. package/.claude/skills/aqe-v2-v3-migration/schemas/output.json +513 -0
  37. package/.claude/skills/aqe-v2-v3-migration/skill.md +4 -0
  38. package/.claude/skills/brutal-honesty-review/SKILL.md +5 -0
  39. package/.claude/skills/brutal-honesty-review/schemas/output.json +291 -0
  40. package/.claude/skills/brutal-honesty-review/scripts/validate.sh +130 -0
  41. package/.claude/skills/bug-reporting-excellence/SKILL.md +5 -0
  42. package/.claude/skills/bug-reporting-excellence/schemas/output.json +288 -0
  43. package/.claude/skills/bug-reporting-excellence/scripts/validate.sh +108 -0
  44. package/.claude/skills/chaos-engineering-resilience/SKILL.md +5 -0
  45. package/.claude/skills/chaos-engineering-resilience/evals/chaos-engineering-resilience.yaml +761 -0
  46. package/.claude/skills/chaos-engineering-resilience/schemas/output.json +1205 -0
  47. package/.claude/skills/chaos-engineering-resilience/scripts/validate.sh +1107 -0
  48. package/.claude/skills/cicd-pipeline-qe-orchestrator/SKILL.md +6 -0
  49. package/.claude/skills/cicd-pipeline-qe-orchestrator/evals/cicd-pipeline-qe-orchestrator.yaml +157 -0
  50. package/.claude/skills/cicd-pipeline-qe-orchestrator/schemas/output.json +542 -0
  51. package/.claude/skills/cicd-pipeline-qe-orchestrator/scripts/validate.sh +310 -0
  52. package/.claude/skills/code-review-quality/SKILL.md +5 -0
  53. package/.claude/skills/code-review-quality/schemas/output.json +264 -0
  54. package/.claude/skills/code-review-quality/scripts/validate.sh +113 -0
  55. package/.claude/skills/compatibility-testing/evals/compatibility-testing.yaml +410 -0
  56. package/.claude/skills/compatibility-testing/schemas/output.json +551 -0
  57. package/.claude/skills/compatibility-testing/scripts/validate.sh +605 -0
  58. package/.claude/skills/compliance-testing/SKILL.md +7 -0
  59. package/.claude/skills/compliance-testing/evals/compliance-testing.yaml +1107 -0
  60. package/.claude/skills/compliance-testing/schemas/output.json +845 -0
  61. package/.claude/skills/compliance-testing/scripts/validate.sh +888 -0
  62. package/.claude/skills/consultancy-practices/SKILL.md +4 -0
  63. package/.claude/skills/consultancy-practices/schemas/output.json +282 -0
  64. package/.claude/skills/context-driven-testing/SKILL.md +3 -0
  65. package/.claude/skills/contract-testing/SKILL.md +5 -0
  66. package/.claude/skills/contract-testing/evals/contract-testing.yaml +748 -0
  67. package/.claude/skills/contract-testing/schemas/output.json +638 -0
  68. package/.claude/skills/contract-testing/scripts/validate.sh +1033 -0
  69. package/.claude/skills/database-testing/SKILL.md +5 -0
  70. package/.claude/skills/database-testing/evals/database-testing.yaml +968 -0
  71. package/.claude/skills/database-testing/schemas/output.json +1446 -0
  72. package/.claude/skills/database-testing/scripts/validate.sh +1099 -0
  73. package/.claude/skills/exploratory-testing-advanced/SKILL.md +3 -0
  74. package/.claude/skills/holistic-testing-pact/SKILL.md +3 -0
  75. package/.claude/skills/localization-testing/SKILL.md +6 -0
  76. package/.claude/skills/localization-testing/evals/localization-testing.yaml +544 -0
  77. package/.claude/skills/localization-testing/schemas/output.json +325 -0
  78. package/.claude/skills/localization-testing/scripts/validate.sh +131 -0
  79. package/.claude/skills/mobile-testing/SKILL.md +6 -0
  80. package/.claude/skills/mobile-testing/evals/mobile-testing.yaml +537 -0
  81. package/.claude/skills/mobile-testing/schemas/output.json +318 -0
  82. package/.claude/skills/mobile-testing/scripts/validate.sh +127 -0
  83. package/.claude/skills/mutation-testing/SKILL.md +8 -1
  84. package/.claude/skills/mutation-testing/evals/mutation-testing.yaml +652 -0
  85. package/.claude/skills/mutation-testing/schemas/output.json +707 -0
  86. package/.claude/skills/mutation-testing/scripts/validate.sh +992 -0
  87. package/.claude/skills/mutation-testing/test-data/sample-output.json +295 -0
  88. package/.claude/skills/n8n-expression-testing/SKILL.md +6 -0
  89. package/.claude/skills/n8n-expression-testing/evals/n8n-expression-testing.yaml +450 -0
  90. package/.claude/skills/n8n-expression-testing/schemas/output.json +369 -0
  91. package/.claude/skills/n8n-expression-testing/scripts/validate.sh +162 -0
  92. package/.claude/skills/n8n-integration-testing-patterns/SKILL.md +6 -0
  93. package/.claude/skills/n8n-integration-testing-patterns/evals/n8n-integration-testing-patterns.yaml +522 -0
  94. package/.claude/skills/n8n-integration-testing-patterns/schemas/output.json +291 -0
  95. package/.claude/skills/n8n-integration-testing-patterns/scripts/validate.sh +104 -0
  96. package/.claude/skills/n8n-security-testing/SKILL.md +6 -0
  97. package/.claude/skills/n8n-security-testing/evals/n8n-security-testing.yaml +493 -0
  98. package/.claude/skills/n8n-security-testing/schemas/output.json +293 -0
  99. package/.claude/skills/n8n-security-testing/scripts/validate.sh +120 -0
  100. package/.claude/skills/n8n-trigger-testing-strategies/SKILL.md +6 -0
  101. package/.claude/skills/n8n-trigger-testing-strategies/evals/n8n-trigger-testing-strategies.yaml +500 -0
  102. package/.claude/skills/n8n-trigger-testing-strategies/schemas/output.json +295 -0
  103. package/.claude/skills/n8n-trigger-testing-strategies/scripts/validate.sh +121 -0
  104. package/.claude/skills/n8n-workflow-testing-fundamentals/SKILL.md +6 -0
  105. package/.claude/skills/n8n-workflow-testing-fundamentals/evals/n8n-workflow-testing-fundamentals.yaml +497 -0
  106. package/.claude/skills/n8n-workflow-testing-fundamentals/schemas/output.json +254 -0
  107. package/.claude/skills/n8n-workflow-testing-fundamentals/scripts/validate.sh +126 -0
  108. package/.claude/skills/performance-analysis/SKILL.md +6 -0
  109. package/.claude/skills/performance-analysis/evals/performance-analysis.yaml +144 -0
  110. package/.claude/skills/performance-analysis/schemas/output.json +588 -0
  111. package/.claude/skills/performance-analysis/scripts/validate.sh +63 -0
  112. package/.claude/skills/performance-testing/SKILL.md +5 -0
  113. package/.claude/skills/performance-testing/evals/performance-testing.yaml +772 -0
  114. package/.claude/skills/performance-testing/schemas/output.json +1184 -0
  115. package/.claude/skills/performance-testing/scripts/validate.sh +1090 -0
  116. package/.claude/skills/qcsd-ideation-swarm/SKILL.md +1759 -1753
  117. package/.claude/skills/qcsd-ideation-swarm/evals/qcsd-ideation-swarm.yaml +138 -0
  118. package/.claude/skills/qcsd-ideation-swarm/schemas/output.json +568 -0
  119. package/.claude/skills/qcsd-ideation-swarm/scripts/validate.sh +56 -0
  120. package/.claude/skills/qe-chaos-resilience/SKILL.md +6 -0
  121. package/.claude/skills/qe-chaos-resilience/evals/qe-chaos-resilience.yaml +443 -0
  122. package/.claude/skills/qe-chaos-resilience/schemas/output.json +314 -0
  123. package/.claude/skills/qe-chaos-resilience/scripts/validate.sh +401 -0
  124. package/.claude/skills/qe-code-intelligence/SKILL.md +6 -0
  125. package/.claude/skills/qe-code-intelligence/evals/qe-code-intelligence.yaml +459 -0
  126. package/.claude/skills/qe-code-intelligence/schemas/output.json +315 -0
  127. package/.claude/skills/qe-code-intelligence/scripts/validate.sh +408 -0
  128. package/.claude/skills/qe-contract-testing/SKILL.md +6 -0
  129. package/.claude/skills/qe-contract-testing/evals/qe-contract-testing.yaml +513 -0
  130. package/.claude/skills/qe-contract-testing/schemas/output.json +295 -0
  131. package/.claude/skills/qe-contract-testing/scripts/validate.sh +421 -0
  132. package/.claude/skills/qe-coverage-analysis/SKILL.md +6 -0
  133. package/.claude/skills/qe-coverage-analysis/evals/qe-coverage-analysis.yaml +494 -0
  134. package/.claude/skills/qe-coverage-analysis/schemas/output.json +286 -0
  135. package/.claude/skills/qe-coverage-analysis/scripts/validate.sh +453 -0
  136. package/.claude/skills/qe-defect-intelligence/SKILL.md +6 -0
  137. package/.claude/skills/qe-defect-intelligence/evals/qe-defect-intelligence.yaml +511 -0
  138. package/.claude/skills/qe-defect-intelligence/schemas/output.json +283 -0
  139. package/.claude/skills/qe-defect-intelligence/scripts/validate.sh +466 -0
  140. package/.claude/skills/qe-iterative-loop/SKILL.md +445 -440
  141. package/.claude/skills/qe-iterative-loop/schemas/output.json +264 -0
  142. package/.claude/skills/qe-iterative-loop/scripts/validate.sh +474 -0
  143. package/.claude/skills/qe-learning-optimization/SKILL.md +6 -0
  144. package/.claude/skills/qe-learning-optimization/evals/qe-learning-optimization.yaml +144 -0
  145. package/.claude/skills/qe-learning-optimization/schemas/output.json +288 -0
  146. package/.claude/skills/qe-learning-optimization/scripts/validate.sh +56 -0
  147. package/.claude/skills/qe-quality-assessment/SKILL.md +6 -0
  148. package/.claude/skills/qe-quality-assessment/evals/qe-quality-assessment.yaml +506 -0
  149. package/.claude/skills/qe-quality-assessment/schemas/output.json +550 -0
  150. package/.claude/skills/qe-quality-assessment/scripts/validate.sh +352 -0
  151. package/.claude/skills/qe-requirements-validation/SKILL.md +6 -0
  152. package/.claude/skills/qe-requirements-validation/evals/qe-requirements-validation.yaml +598 -0
  153. package/.claude/skills/qe-requirements-validation/schemas/output.json +587 -0
  154. package/.claude/skills/qe-requirements-validation/scripts/validate.sh +275 -0
  155. package/.claude/skills/qe-security-compliance/SKILL.md +6 -0
  156. package/.claude/skills/qe-security-compliance/evals/qe-security-compliance.yaml +595 -0
  157. package/.claude/skills/qe-security-compliance/schemas/output.json +498 -0
  158. package/.claude/skills/qe-security-compliance/scripts/validate.sh +305 -0
  159. package/.claude/skills/qe-test-execution/SKILL.md +6 -0
  160. package/.claude/skills/qe-test-execution/evals/qe-test-execution.yaml +607 -0
  161. package/.claude/skills/qe-test-execution/schemas/output.json +529 -0
  162. package/.claude/skills/qe-test-execution/scripts/validate.sh +323 -0
  163. package/.claude/skills/qe-test-generation/SKILL.md +6 -0
  164. package/.claude/skills/qe-test-generation/evals/qe-test-generation.yaml +148 -0
  165. package/.claude/skills/qe-test-generation/schemas/output.json +439 -0
  166. package/.claude/skills/qe-test-generation/scripts/validate.sh +56 -0
  167. package/.claude/skills/qe-visual-accessibility/SKILL.md +6 -0
  168. package/.claude/skills/qe-visual-accessibility/evals/qe-visual-accessibility.yaml +142 -0
  169. package/.claude/skills/qe-visual-accessibility/schemas/output.json +491 -0
  170. package/.claude/skills/qe-visual-accessibility/scripts/validate.sh +56 -0
  171. package/.claude/skills/quality-metrics/SKILL.md +6 -0
  172. package/.claude/skills/quality-metrics/evals/quality-metrics.yaml +494 -0
  173. package/.claude/skills/quality-metrics/schemas/output.json +403 -0
  174. package/.claude/skills/quality-metrics/scripts/validate.sh +434 -0
  175. package/.claude/skills/refactoring-patterns/SKILL.md +5 -0
  176. package/.claude/skills/refactoring-patterns/schemas/output.json +475 -0
  177. package/.claude/skills/refactoring-patterns/scripts/validate.sh +241 -0
  178. package/.claude/skills/regression-testing/SKILL.md +6 -0
  179. package/.claude/skills/regression-testing/evals/regression-testing.yaml +504 -0
  180. package/.claude/skills/regression-testing/schemas/output.json +311 -0
  181. package/.claude/skills/regression-testing/scripts/validate.sh +130 -0
  182. package/.claude/skills/risk-based-testing/SKILL.md +6 -0
  183. package/.claude/skills/risk-based-testing/evals/risk-based-testing.yaml +141 -0
  184. package/.claude/skills/risk-based-testing/schemas/output.json +480 -0
  185. package/.claude/skills/risk-based-testing/scripts/validate.sh +56 -0
  186. package/.claude/skills/security-testing/SKILL.md +5 -0
  187. package/.claude/skills/security-testing/evals/security-testing.yaml +789 -0
  188. package/.claude/skills/security-testing/schemas/output.json +879 -0
  189. package/.claude/skills/security-testing/scripts/validate.sh +967 -0
  190. package/.claude/skills/security-visual-testing/SKILL.md +223 -217
  191. package/.claude/skills/security-visual-testing/evals/security-visual-testing.yaml +163 -0
  192. package/.claude/skills/security-visual-testing/schemas/output.json +486 -0
  193. package/.claude/skills/security-visual-testing/scripts/validate.sh +748 -0
  194. package/.claude/skills/sherlock-review/SKILL.md +5 -0
  195. package/.claude/skills/sherlock-review/schemas/output.json +297 -0
  196. package/.claude/skills/sherlock-review/scripts/validate.sh +115 -0
  197. package/.claude/skills/shift-left-testing/SKILL.md +6 -0
  198. package/.claude/skills/shift-left-testing/evals/shift-left-testing.yaml +145 -0
  199. package/.claude/skills/shift-left-testing/schemas/output.json +459 -0
  200. package/.claude/skills/shift-left-testing/scripts/validate.sh +56 -0
  201. package/.claude/skills/shift-right-testing/SKILL.md +6 -0
  202. package/.claude/skills/shift-right-testing/evals/shift-right-testing.yaml +147 -0
  203. package/.claude/skills/shift-right-testing/schemas/output.json +418 -0
  204. package/.claude/skills/shift-right-testing/scripts/validate.sh +56 -0
  205. package/.claude/skills/six-thinking-hats/SKILL.md +3 -0
  206. package/.claude/skills/tdd-london-chicago/SKILL.md +5 -0
  207. package/.claude/skills/tdd-london-chicago/schemas/output.json +444 -0
  208. package/.claude/skills/tdd-london-chicago/scripts/validate.sh +214 -0
  209. package/.claude/skills/technical-writing/SKILL.md +4 -0
  210. package/.claude/skills/technical-writing/schemas/output.json +268 -0
  211. package/.claude/skills/test-automation-strategy/SKILL.md +6 -0
  212. package/.claude/skills/test-automation-strategy/evals/test-automation-strategy.yaml +148 -0
  213. package/.claude/skills/test-automation-strategy/schemas/output.json +444 -0
  214. package/.claude/skills/test-automation-strategy/scripts/validate.sh +195 -0
  215. package/.claude/skills/test-data-management/SKILL.md +6 -0
  216. package/.claude/skills/test-data-management/evals/test-data-management.yaml +504 -0
  217. package/.claude/skills/test-data-management/schemas/output.json +284 -0
  218. package/.claude/skills/test-data-management/scripts/validate.sh +137 -0
  219. package/.claude/skills/test-design-techniques/SKILL.md +6 -0
  220. package/.claude/skills/test-design-techniques/evals/test-design-techniques.yaml +142 -0
  221. package/.claude/skills/test-design-techniques/schemas/output.json +295 -0
  222. package/.claude/skills/test-design-techniques/scripts/validate.sh +91 -0
  223. package/.claude/skills/test-environment-management/SKILL.md +4 -0
  224. package/.claude/skills/test-environment-management/schemas/output.json +310 -0
  225. package/.claude/skills/test-reporting-analytics/SKILL.md +6 -0
  226. package/.claude/skills/test-reporting-analytics/evals/test-reporting-analytics.yaml +155 -0
  227. package/.claude/skills/test-reporting-analytics/schemas/output.json +329 -0
  228. package/.claude/skills/test-reporting-analytics/scripts/validate.sh +77 -0
  229. package/.claude/skills/testability-scoring/SKILL.md +5 -0
  230. package/.claude/skills/testability-scoring/evals/testability-scoring.yaml +814 -0
  231. package/.claude/skills/testability-scoring/schemas/output.json +606 -0
  232. package/.claude/skills/testability-scoring/scripts/validate.sh +891 -0
  233. package/.claude/skills/trust-tier-manifest.json +2333 -0
  234. package/.claude/skills/verification-quality/SKILL.md +6 -0
  235. package/.claude/skills/verification-quality/evals/verification-quality.yaml +150 -0
  236. package/.claude/skills/verification-quality/schemas/output.json +432 -0
  237. package/.claude/skills/verification-quality/scripts/validate.sh +77 -0
  238. package/.claude/skills/visual-testing-advanced/SKILL.md +6 -0
  239. package/.claude/skills/visual-testing-advanced/evals/visual-testing-advanced.yaml +154 -0
  240. package/.claude/skills/visual-testing-advanced/schemas/output.json +294 -0
  241. package/.claude/skills/visual-testing-advanced/scripts/validate.sh +77 -0
  242. package/.claude/skills/xp-practices/SKILL.md +3 -0
  243. package/README.md +39 -2
  244. package/package.json +4 -1
  245. package/scripts/run-skill-eval.ts +1097 -0
  246. package/scripts/test-schema-validation.js +301 -0
  247. package/scripts/update-skill-manifest.ts +751 -0
  248. package/scripts/validate-skill-frontmatter.js +141 -0
  249. package/v3/CHANGELOG.md +21 -0
  250. package/v3/README.md +43 -3
  251. package/v3/assets/agents/v3/qe-test-idea-rewriter.md +375 -375
  252. package/v3/assets/skills/.validation/README.md +111 -0
  253. package/v3/assets/skills/.validation/examples/chaos-engineering-output.example.json +530 -0
  254. package/v3/assets/skills/.validation/examples/performance-testing-output.example.json +252 -0
  255. package/v3/assets/skills/.validation/examples/security-testing-output.example.json +413 -0
  256. package/v3/assets/skills/.validation/examples/testability-scoring-output.example.json +350 -0
  257. package/v3/assets/skills/.validation/schemas/skill-eval.schema.json +452 -0
  258. package/v3/assets/skills/.validation/schemas/skill-frontmatter.schema.json +341 -0
  259. package/v3/assets/skills/.validation/schemas/skill-output-meta.schema.json +199 -0
  260. package/v3/assets/skills/.validation/schemas/skill-output.template.json +610 -0
  261. package/v3/assets/skills/.validation/skill-validation-mcp-integration.md +250 -0
  262. package/v3/assets/skills/.validation/templates/eval.template.yaml +366 -0
  263. package/v3/assets/skills/.validation/templates/schemas/output.json +145 -0
  264. package/v3/assets/skills/.validation/templates/security-testing-eval.template.yaml +725 -0
  265. package/v3/assets/skills/.validation/templates/skill-frontmatter.example.yaml +225 -0
  266. package/v3/assets/skills/.validation/templates/validate.template.sh +1060 -0
  267. package/v3/assets/skills/.validation/templates/validator-lib.sh +1031 -0
  268. package/v3/assets/skills/.validation/test-data/invalid-output.json +5 -0
  269. package/v3/assets/skills/.validation/test-data/minimal-output.json +9 -0
  270. package/v3/assets/skills/.validation/test-data/sample-output.json +73 -0
  271. package/v3/assets/skills/accessibility-testing/SKILL.md +8 -1
  272. package/v3/assets/skills/accessibility-testing/evals/accessibility-testing.yaml +719 -0
  273. package/v3/assets/skills/accessibility-testing/schemas/output.json +776 -0
  274. package/v3/assets/skills/accessibility-testing/scripts/validate.sh +943 -0
  275. package/v3/assets/skills/accessibility-testing/test-data/sample-output.json +191 -0
  276. package/v3/assets/skills/agentic-quality-engineering/SKILL.md +4 -0
  277. package/v3/assets/skills/agentic-quality-engineering/schemas/output.json +577 -0
  278. package/v3/assets/skills/api-testing-patterns/SKILL.md +5 -0
  279. package/v3/assets/skills/api-testing-patterns/evals/api-testing-patterns.yaml +696 -0
  280. package/v3/assets/skills/api-testing-patterns/schemas/output.json +845 -0
  281. package/v3/assets/skills/api-testing-patterns/scripts/validate.sh +931 -0
  282. package/v3/assets/skills/aqe-v2-v3-migration/schemas/output.json +513 -0
  283. package/v3/assets/skills/aqe-v2-v3-migration/skill.md +20 -16
  284. package/v3/assets/skills/bug-reporting-excellence/SKILL.md +5 -0
  285. package/v3/assets/skills/bug-reporting-excellence/schemas/output.json +288 -0
  286. package/v3/assets/skills/bug-reporting-excellence/scripts/validate.sh +108 -0
  287. package/v3/assets/skills/chaos-engineering-resilience/SKILL.md +5 -0
  288. package/v3/assets/skills/chaos-engineering-resilience/evals/chaos-engineering-resilience.yaml +761 -0
  289. package/v3/assets/skills/chaos-engineering-resilience/schemas/output.json +1205 -0
  290. package/v3/assets/skills/chaos-engineering-resilience/scripts/validate.sh +1107 -0
  291. package/v3/assets/skills/code-review-quality/SKILL.md +5 -0
  292. package/v3/assets/skills/code-review-quality/schemas/output.json +264 -0
  293. package/v3/assets/skills/code-review-quality/scripts/validate.sh +113 -0
  294. package/v3/assets/skills/compatibility-testing/evals/compatibility-testing.yaml +410 -0
  295. package/v3/assets/skills/compatibility-testing/schemas/output.json +551 -0
  296. package/v3/assets/skills/compatibility-testing/scripts/validate.sh +605 -0
  297. package/v3/assets/skills/compliance-testing/SKILL.md +7 -0
  298. package/v3/assets/skills/compliance-testing/evals/compliance-testing.yaml +1107 -0
  299. package/v3/assets/skills/compliance-testing/schemas/output.json +845 -0
  300. package/v3/assets/skills/compliance-testing/scripts/validate.sh +888 -0
  301. package/v3/assets/skills/consultancy-practices/SKILL.md +4 -0
  302. package/v3/assets/skills/consultancy-practices/schemas/output.json +282 -0
  303. package/v3/assets/skills/context-driven-testing/SKILL.md +3 -0
  304. package/v3/assets/skills/contract-testing/SKILL.md +5 -0
  305. package/v3/assets/skills/contract-testing/evals/contract-testing.yaml +748 -0
  306. package/v3/assets/skills/contract-testing/schemas/output.json +638 -0
  307. package/v3/assets/skills/contract-testing/scripts/validate.sh +1033 -0
  308. package/v3/assets/skills/database-testing/SKILL.md +5 -0
  309. package/v3/assets/skills/database-testing/evals/database-testing.yaml +968 -0
  310. package/v3/assets/skills/database-testing/schemas/output.json +1446 -0
  311. package/v3/assets/skills/database-testing/scripts/validate.sh +1099 -0
  312. package/v3/assets/skills/exploratory-testing-advanced/SKILL.md +3 -0
  313. package/v3/assets/skills/holistic-testing-pact/SKILL.md +3 -0
  314. package/v3/assets/skills/localization-testing/SKILL.md +6 -0
  315. package/v3/assets/skills/localization-testing/evals/localization-testing.yaml +544 -0
  316. package/v3/assets/skills/localization-testing/schemas/output.json +325 -0
  317. package/v3/assets/skills/localization-testing/scripts/validate.sh +131 -0
  318. package/v3/assets/skills/mobile-testing/SKILL.md +6 -0
  319. package/v3/assets/skills/mobile-testing/evals/mobile-testing.yaml +537 -0
  320. package/v3/assets/skills/mobile-testing/schemas/output.json +318 -0
  321. package/v3/assets/skills/mobile-testing/scripts/validate.sh +127 -0
  322. package/v3/assets/skills/mutation-testing/SKILL.md +8 -1
  323. package/v3/assets/skills/mutation-testing/evals/mutation-testing.yaml +652 -0
  324. package/v3/assets/skills/mutation-testing/schemas/output.json +707 -0
  325. package/v3/assets/skills/mutation-testing/scripts/validate.sh +992 -0
  326. package/v3/assets/skills/mutation-testing/test-data/sample-output.json +295 -0
  327. package/v3/assets/skills/n8n-expression-testing/scripts/validate.sh +162 -0
  328. package/v3/assets/skills/n8n-integration-testing-patterns/scripts/validate.sh +104 -0
  329. package/v3/assets/skills/n8n-security-testing/scripts/validate.sh +120 -0
  330. package/v3/assets/skills/n8n-trigger-testing-strategies/scripts/validate.sh +121 -0
  331. package/v3/assets/skills/n8n-workflow-testing-fundamentals/scripts/validate.sh +126 -0
  332. package/v3/assets/skills/performance-testing/SKILL.md +5 -0
  333. package/v3/assets/skills/performance-testing/evals/performance-testing.yaml +772 -0
  334. package/v3/assets/skills/performance-testing/schemas/output.json +1184 -0
  335. package/v3/assets/skills/performance-testing/scripts/validate.sh +1090 -0
  336. package/v3/assets/skills/qe-chaos-resilience/SKILL.md +6 -0
  337. package/v3/assets/skills/qe-chaos-resilience/evals/qe-chaos-resilience.yaml +443 -0
  338. package/v3/assets/skills/qe-chaos-resilience/schemas/output.json +314 -0
  339. package/v3/assets/skills/qe-chaos-resilience/scripts/validate.sh +401 -0
  340. package/v3/assets/skills/qe-code-intelligence/SKILL.md +6 -0
  341. package/v3/assets/skills/qe-code-intelligence/evals/qe-code-intelligence.yaml +459 -0
  342. package/v3/assets/skills/qe-code-intelligence/schemas/output.json +315 -0
  343. package/v3/assets/skills/qe-code-intelligence/scripts/validate.sh +408 -0
  344. package/v3/assets/skills/qe-contract-testing/SKILL.md +6 -0
  345. package/v3/assets/skills/qe-contract-testing/evals/qe-contract-testing.yaml +513 -0
  346. package/v3/assets/skills/qe-contract-testing/schemas/output.json +295 -0
  347. package/v3/assets/skills/qe-contract-testing/scripts/validate.sh +421 -0
  348. package/v3/assets/skills/qe-coverage-analysis/SKILL.md +6 -0
  349. package/v3/assets/skills/qe-coverage-analysis/evals/qe-coverage-analysis.yaml +494 -0
  350. package/v3/assets/skills/qe-coverage-analysis/schemas/output.json +286 -0
  351. package/v3/assets/skills/qe-coverage-analysis/scripts/validate.sh +453 -0
  352. package/v3/assets/skills/qe-defect-intelligence/SKILL.md +6 -0
  353. package/v3/assets/skills/qe-defect-intelligence/evals/qe-defect-intelligence.yaml +511 -0
  354. package/v3/assets/skills/qe-defect-intelligence/schemas/output.json +283 -0
  355. package/v3/assets/skills/qe-defect-intelligence/scripts/validate.sh +466 -0
  356. package/v3/assets/skills/qe-iterative-loop/SKILL.md +445 -443
  357. package/v3/assets/skills/qe-iterative-loop/schemas/output.json +264 -0
  358. package/v3/assets/skills/qe-iterative-loop/scripts/validate.sh +474 -0
  359. package/v3/assets/skills/qe-learning-optimization/SKILL.md +6 -0
  360. package/v3/assets/skills/qe-learning-optimization/evals/qe-learning-optimization.yaml +144 -0
  361. package/v3/assets/skills/qe-learning-optimization/schemas/output.json +288 -0
  362. package/v3/assets/skills/qe-learning-optimization/scripts/validate.sh +56 -0
  363. package/v3/assets/skills/qe-quality-assessment/SKILL.md +6 -0
  364. package/v3/assets/skills/qe-quality-assessment/evals/qe-quality-assessment.yaml +506 -0
  365. package/v3/assets/skills/qe-quality-assessment/schemas/output.json +550 -0
  366. package/v3/assets/skills/qe-quality-assessment/scripts/validate.sh +352 -0
  367. package/v3/assets/skills/qe-requirements-validation/SKILL.md +6 -0
  368. package/v3/assets/skills/qe-requirements-validation/evals/qe-requirements-validation.yaml +598 -0
  369. package/v3/assets/skills/qe-requirements-validation/schemas/output.json +587 -0
  370. package/v3/assets/skills/qe-requirements-validation/scripts/validate.sh +275 -0
  371. package/v3/assets/skills/qe-security-compliance/SKILL.md +6 -0
  372. package/v3/assets/skills/qe-security-compliance/evals/qe-security-compliance.yaml +595 -0
  373. package/v3/assets/skills/qe-security-compliance/schemas/output.json +498 -0
  374. package/v3/assets/skills/qe-security-compliance/scripts/validate.sh +305 -0
  375. package/v3/assets/skills/qe-test-execution/SKILL.md +6 -0
  376. package/v3/assets/skills/qe-test-execution/evals/qe-test-execution.yaml +607 -0
  377. package/v3/assets/skills/qe-test-execution/schemas/output.json +529 -0
  378. package/v3/assets/skills/qe-test-execution/scripts/validate.sh +323 -0
  379. package/v3/assets/skills/qe-test-generation/SKILL.md +6 -0
  380. package/v3/assets/skills/qe-test-generation/evals/qe-test-generation.yaml +148 -0
  381. package/v3/assets/skills/qe-test-generation/schemas/output.json +439 -0
  382. package/v3/assets/skills/qe-test-generation/scripts/validate.sh +56 -0
  383. package/v3/assets/skills/qe-visual-accessibility/SKILL.md +6 -0
  384. package/v3/assets/skills/qe-visual-accessibility/evals/qe-visual-accessibility.yaml +142 -0
  385. package/v3/assets/skills/qe-visual-accessibility/schemas/output.json +491 -0
  386. package/v3/assets/skills/qe-visual-accessibility/scripts/validate.sh +56 -0
  387. package/v3/assets/skills/quality-metrics/SKILL.md +6 -0
  388. package/v3/assets/skills/quality-metrics/evals/quality-metrics.yaml +494 -0
  389. package/v3/assets/skills/quality-metrics/schemas/output.json +403 -0
  390. package/v3/assets/skills/quality-metrics/scripts/validate.sh +434 -0
  391. package/v3/assets/skills/refactoring-patterns/SKILL.md +5 -0
  392. package/v3/assets/skills/refactoring-patterns/schemas/output.json +475 -0
  393. package/v3/assets/skills/refactoring-patterns/scripts/validate.sh +241 -0
  394. package/v3/assets/skills/regression-testing/SKILL.md +6 -0
  395. package/v3/assets/skills/regression-testing/evals/regression-testing.yaml +504 -0
  396. package/v3/assets/skills/regression-testing/schemas/output.json +311 -0
  397. package/v3/assets/skills/regression-testing/scripts/validate.sh +130 -0
  398. package/v3/assets/skills/risk-based-testing/SKILL.md +6 -0
  399. package/v3/assets/skills/risk-based-testing/evals/risk-based-testing.yaml +141 -0
  400. package/v3/assets/skills/risk-based-testing/schemas/output.json +480 -0
  401. package/v3/assets/skills/risk-based-testing/scripts/validate.sh +56 -0
  402. package/v3/assets/skills/security-testing/SKILL.md +5 -0
  403. package/v3/assets/skills/security-testing/evals/security-testing.yaml +789 -0
  404. package/v3/assets/skills/security-testing/schemas/output.json +879 -0
  405. package/v3/assets/skills/security-testing/scripts/validate.sh +967 -0
  406. package/v3/assets/skills/shift-left-testing/SKILL.md +6 -0
  407. package/v3/assets/skills/shift-left-testing/evals/shift-left-testing.yaml +145 -0
  408. package/v3/assets/skills/shift-left-testing/schemas/output.json +459 -0
  409. package/v3/assets/skills/shift-left-testing/scripts/validate.sh +56 -0
  410. package/v3/assets/skills/shift-right-testing/SKILL.md +6 -0
  411. package/v3/assets/skills/shift-right-testing/evals/shift-right-testing.yaml +147 -0
  412. package/v3/assets/skills/shift-right-testing/schemas/output.json +418 -0
  413. package/v3/assets/skills/shift-right-testing/scripts/validate.sh +56 -0
  414. package/v3/assets/skills/six-thinking-hats/SKILL.md +3 -0
  415. package/v3/assets/skills/tdd-london-chicago/SKILL.md +5 -0
  416. package/v3/assets/skills/tdd-london-chicago/schemas/output.json +444 -0
  417. package/v3/assets/skills/tdd-london-chicago/scripts/validate.sh +214 -0
  418. package/v3/assets/skills/technical-writing/SKILL.md +4 -0
  419. package/v3/assets/skills/technical-writing/schemas/output.json +268 -0
  420. package/v3/assets/skills/test-automation-strategy/SKILL.md +6 -0
  421. package/v3/assets/skills/test-automation-strategy/evals/test-automation-strategy.yaml +148 -0
  422. package/v3/assets/skills/test-automation-strategy/schemas/output.json +444 -0
  423. package/v3/assets/skills/test-automation-strategy/scripts/validate.sh +195 -0
  424. package/v3/assets/skills/test-data-management/SKILL.md +6 -0
  425. package/v3/assets/skills/test-data-management/evals/test-data-management.yaml +504 -0
  426. package/v3/assets/skills/test-data-management/schemas/output.json +284 -0
  427. package/v3/assets/skills/test-data-management/scripts/validate.sh +137 -0
  428. package/v3/assets/skills/test-design-techniques/SKILL.md +6 -0
  429. package/v3/assets/skills/test-design-techniques/evals/test-design-techniques.yaml +142 -0
  430. package/v3/assets/skills/test-design-techniques/schemas/output.json +295 -0
  431. package/v3/assets/skills/test-design-techniques/scripts/validate.sh +91 -0
  432. package/v3/assets/skills/test-environment-management/SKILL.md +4 -0
  433. package/v3/assets/skills/test-environment-management/schemas/output.json +310 -0
  434. package/v3/assets/skills/test-reporting-analytics/SKILL.md +6 -0
  435. package/v3/assets/skills/test-reporting-analytics/evals/test-reporting-analytics.yaml +155 -0
  436. package/v3/assets/skills/test-reporting-analytics/schemas/output.json +329 -0
  437. package/v3/assets/skills/test-reporting-analytics/scripts/validate.sh +77 -0
  438. package/v3/assets/skills/verification-quality/SKILL.md +6 -0
  439. package/v3/assets/skills/verification-quality/evals/verification-quality.yaml +150 -0
  440. package/v3/assets/skills/verification-quality/schemas/output.json +432 -0
  441. package/v3/assets/skills/verification-quality/scripts/validate.sh +77 -0
  442. package/v3/assets/skills/visual-testing-advanced/SKILL.md +6 -0
  443. package/v3/assets/skills/visual-testing-advanced/evals/visual-testing-advanced.yaml +154 -0
  444. package/v3/assets/skills/visual-testing-advanced/schemas/output.json +294 -0
  445. package/v3/assets/skills/visual-testing-advanced/scripts/validate.sh +77 -0
  446. package/v3/assets/skills/xp-practices/SKILL.md +3 -0
  447. package/v3/assets/templates/validation-report.md.hbs +139 -0
  448. package/v3/assets/templates/validation-summary.json +56 -0
  449. package/v3/dist/cli/bundle.js +7368 -3418
  450. package/v3/dist/cli/commands/eval.d.ts +18 -0
  451. package/v3/dist/cli/commands/eval.d.ts.map +1 -0
  452. package/v3/dist/cli/commands/eval.js +505 -0
  453. package/v3/dist/cli/commands/eval.js.map +1 -0
  454. package/v3/dist/cli/commands/validate-swarm.d.ts +16 -0
  455. package/v3/dist/cli/commands/validate-swarm.d.ts.map +1 -0
  456. package/v3/dist/cli/commands/validate-swarm.js +251 -0
  457. package/v3/dist/cli/commands/validate-swarm.js.map +1 -0
  458. package/v3/dist/cli/commands/validate.d.ts +14 -0
  459. package/v3/dist/cli/commands/validate.d.ts.map +1 -0
  460. package/v3/dist/cli/commands/validate.js +408 -0
  461. package/v3/dist/cli/commands/validate.js.map +1 -0
  462. package/v3/dist/cli/index.js +6 -0
  463. package/v3/dist/cli/index.js.map +1 -1
  464. package/v3/dist/index.d.ts +2 -0
  465. package/v3/dist/index.d.ts.map +1 -1
  466. package/v3/dist/index.js +10 -0
  467. package/v3/dist/index.js.map +1 -1
  468. package/v3/dist/init/skills-installer.d.ts +6 -0
  469. package/v3/dist/init/skills-installer.d.ts.map +1 -1
  470. package/v3/dist/init/skills-installer.js +48 -0
  471. package/v3/dist/init/skills-installer.js.map +1 -1
  472. package/v3/dist/learning/index.d.ts +2 -0
  473. package/v3/dist/learning/index.d.ts.map +1 -1
  474. package/v3/dist/learning/index.js +4 -0
  475. package/v3/dist/learning/index.js.map +1 -1
  476. package/v3/dist/learning/skill-validation-learner.d.ts +264 -0
  477. package/v3/dist/learning/skill-validation-learner.d.ts.map +1 -0
  478. package/v3/dist/learning/skill-validation-learner.js +515 -0
  479. package/v3/dist/learning/skill-validation-learner.js.map +1 -0
  480. package/v3/dist/validation/index.d.ts +19 -0
  481. package/v3/dist/validation/index.d.ts.map +1 -0
  482. package/v3/dist/validation/index.js +31 -0
  483. package/v3/dist/validation/index.js.map +1 -0
  484. package/v3/dist/validation/parallel-eval-runner.d.ts +307 -0
  485. package/v3/dist/validation/parallel-eval-runner.d.ts.map +1 -0
  486. package/v3/dist/validation/parallel-eval-runner.js +566 -0
  487. package/v3/dist/validation/parallel-eval-runner.js.map +1 -0
  488. package/v3/dist/validation/swarm-skill-validator.d.ts +282 -0
  489. package/v3/dist/validation/swarm-skill-validator.d.ts.map +1 -0
  490. package/v3/dist/validation/swarm-skill-validator.js +460 -0
  491. package/v3/dist/validation/swarm-skill-validator.js.map +1 -0
  492. package/v3/dist/validation/validation-result-aggregator.d.ts +232 -0
  493. package/v3/dist/validation/validation-result-aggregator.d.ts.map +1 -0
  494. package/v3/dist/validation/validation-result-aggregator.js +630 -0
  495. package/v3/dist/validation/validation-result-aggregator.js.map +1 -0
  496. package/v3/package.json +1 -1
@@ -0,0 +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"