agentic-qe 3.7.9 → 3.7.11

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 (401) 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 -158
  46. package/.claude/skills/enterprise-integration-testing/schemas/output.json +74 -74
  47. package/.claude/skills/enterprise-integration-testing/scripts/validate-config.json +25 -25
  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 -153
  53. package/.claude/skills/middleware-testing-patterns/schemas/output.json +58 -58
  54. package/.claude/skills/middleware-testing-patterns/scripts/validate-config.json +25 -25
  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 -157
  72. package/.claude/skills/observability-testing-patterns/schemas/output.json +58 -58
  73. package/.claude/skills/observability-testing-patterns/scripts/validate-config.json +25 -25
  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 -211
  84. package/.claude/skills/qcsd-cicd-swarm/schemas/output.json +86 -86
  85. package/.claude/skills/qcsd-cicd-swarm/scripts/validate-config.json +30 -30
  86. package/.claude/skills/qcsd-development-swarm/SKILL.md +2154 -2154
  87. package/.claude/skills/qcsd-development-swarm/evals/qcsd-development-swarm.yaml +162 -162
  88. package/.claude/skills/qcsd-development-swarm/schemas/output.json +72 -72
  89. package/.claude/skills/qcsd-development-swarm/scripts/validate-config.json +25 -25
  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/verification-quality/evals/verification-quality.yaml +150 -150
  157. package/.claude/skills/verification-quality/schemas/output.json +432 -432
  158. package/.claude/skills/visual-testing-advanced/evals/visual-testing-advanced.yaml +154 -154
  159. package/.claude/skills/visual-testing-advanced/schemas/output.json +294 -294
  160. package/.claude/skills/wms-testing-patterns/evals/wms-testing-patterns.yaml +165 -165
  161. package/.claude/skills/wms-testing-patterns/schemas/output.json +150 -150
  162. package/.claude/skills/wms-testing-patterns/scripts/validate-config.json +51 -51
  163. package/CHANGELOG.md +36 -0
  164. package/README.md +171 -901
  165. package/assets/agents/v3/helpers/quality-criteria/evidence-classification.md +116 -116
  166. package/assets/agents/v3/helpers/quality-criteria/htsm-categories.md +139 -139
  167. package/assets/governance/constitution.md +202 -202
  168. package/assets/governance/shards/chaos-resilience.shard.md +221 -221
  169. package/assets/governance/shards/code-intelligence.shard.md +178 -178
  170. package/assets/governance/shards/contract-testing.shard.md +206 -206
  171. package/assets/governance/shards/coverage-analysis.shard.md +146 -146
  172. package/assets/governance/shards/defect-intelligence.shard.md +182 -182
  173. package/assets/governance/shards/learning-optimization.shard.md +248 -248
  174. package/assets/governance/shards/quality-assessment.shard.md +165 -165
  175. package/assets/governance/shards/requirements-validation.shard.md +177 -177
  176. package/assets/governance/shards/security-compliance.shard.md +196 -196
  177. package/assets/governance/shards/test-execution.shard.md +156 -156
  178. package/assets/governance/shards/test-generation.shard.md +128 -128
  179. package/assets/governance/shards/visual-accessibility.shard.md +209 -209
  180. package/assets/hooks/cross-phase-memory.yaml +253 -253
  181. package/assets/patterns/adr-051-booster-patterns.json +78 -78
  182. package/assets/patterns/adr-051-embedding-patterns.json +147 -147
  183. package/assets/patterns/adr-051-integration-summary.json +62 -62
  184. package/assets/patterns/adr-051-reasoning-patterns.json +166 -166
  185. package/assets/patterns/adr-051-router-patterns.json +113 -113
  186. package/assets/patterns/index.json +136 -136
  187. package/assets/skills/.validation/README.md +111 -111
  188. package/assets/skills/.validation/examples/chaos-engineering-output.example.json +530 -530
  189. package/assets/skills/.validation/examples/performance-testing-output.example.json +252 -252
  190. package/assets/skills/.validation/examples/security-testing-output.example.json +413 -413
  191. package/assets/skills/.validation/examples/testability-scoring-output.example.json +350 -350
  192. package/assets/skills/.validation/schemas/skill-eval.schema.json +462 -462
  193. package/assets/skills/.validation/schemas/skill-frontmatter.schema.json +341 -341
  194. package/assets/skills/.validation/schemas/skill-output-meta.schema.json +199 -199
  195. package/assets/skills/.validation/schemas/skill-output.template.json +610 -610
  196. package/assets/skills/.validation/skill-validation-mcp-integration.md +250 -250
  197. package/assets/skills/.validation/templates/eval.template.yaml +366 -366
  198. package/assets/skills/.validation/templates/schemas/output.json +145 -145
  199. package/assets/skills/.validation/templates/security-testing-eval.template.yaml +725 -725
  200. package/assets/skills/.validation/templates/skill-frontmatter.example.yaml +225 -225
  201. package/assets/skills/.validation/test-data/invalid-output.json +5 -5
  202. package/assets/skills/.validation/test-data/minimal-output.json +9 -9
  203. package/assets/skills/.validation/test-data/sample-output.json +73 -73
  204. package/assets/skills/a11y-ally/evals/a11y-ally.yaml +376 -376
  205. package/assets/skills/a11y-ally/schemas/output.json +549 -549
  206. package/assets/skills/accessibility-testing/evals/accessibility-testing.yaml +719 -719
  207. package/assets/skills/accessibility-testing/schemas/output.json +776 -776
  208. package/assets/skills/accessibility-testing/test-data/sample-output.json +191 -191
  209. package/assets/skills/agentic-quality-engineering/schemas/output.json +577 -577
  210. package/assets/skills/api-testing-patterns/evals/api-testing-patterns.yaml +696 -696
  211. package/assets/skills/api-testing-patterns/schemas/output.json +845 -845
  212. package/assets/skills/aqe-v2-v3-migration/schemas/output.json +513 -513
  213. package/assets/skills/brutal-honesty-review/schemas/output.json +291 -291
  214. package/assets/skills/bug-reporting-excellence/schemas/output.json +288 -288
  215. package/assets/skills/chaos-engineering-resilience/evals/chaos-engineering-resilience.yaml +761 -761
  216. package/assets/skills/chaos-engineering-resilience/schemas/output.json +1205 -1205
  217. package/assets/skills/cicd-pipeline-qe-orchestrator/evals/cicd-pipeline-qe-orchestrator.yaml +157 -157
  218. package/assets/skills/cicd-pipeline-qe-orchestrator/schemas/output.json +542 -542
  219. package/assets/skills/code-review-quality/schemas/output.json +264 -264
  220. package/assets/skills/compatibility-testing/evals/compatibility-testing.yaml +410 -410
  221. package/assets/skills/compatibility-testing/schemas/output.json +551 -551
  222. package/assets/skills/compliance-testing/evals/compliance-testing.yaml +1107 -1107
  223. package/assets/skills/compliance-testing/schemas/output.json +845 -845
  224. package/assets/skills/consultancy-practices/schemas/output.json +282 -282
  225. package/assets/skills/contract-testing/evals/contract-testing.yaml +748 -748
  226. package/assets/skills/contract-testing/schemas/output.json +638 -638
  227. package/assets/skills/database-testing/evals/database-testing.yaml +968 -968
  228. package/assets/skills/database-testing/schemas/output.json +1446 -1446
  229. package/assets/skills/debug-loop/SKILL.md +61 -61
  230. package/assets/skills/enterprise-integration-testing/SKILL.md +735 -735
  231. package/assets/skills/enterprise-integration-testing/evals/enterprise-integration-testing.yaml +158 -158
  232. package/assets/skills/enterprise-integration-testing/schemas/output.json +74 -74
  233. package/assets/skills/enterprise-integration-testing/scripts/validate-config.json +25 -25
  234. package/assets/skills/localization-testing/evals/localization-testing.yaml +544 -544
  235. package/assets/skills/localization-testing/schemas/output.json +325 -325
  236. package/assets/skills/middleware-testing-patterns/SKILL.md +798 -798
  237. package/assets/skills/middleware-testing-patterns/evals/middleware-testing-patterns.yaml +153 -153
  238. package/assets/skills/middleware-testing-patterns/schemas/output.json +58 -58
  239. package/assets/skills/middleware-testing-patterns/scripts/validate-config.json +25 -25
  240. package/assets/skills/mobile-testing/evals/mobile-testing.yaml +537 -537
  241. package/assets/skills/mobile-testing/schemas/output.json +318 -318
  242. package/assets/skills/mutation-testing/evals/mutation-testing.yaml +652 -652
  243. package/assets/skills/mutation-testing/schemas/output.json +707 -707
  244. package/assets/skills/mutation-testing/test-data/sample-output.json +295 -295
  245. package/assets/skills/n8n-expression-testing/evals/n8n-expression-testing.yaml +450 -450
  246. package/assets/skills/n8n-expression-testing/schemas/output.json +369 -369
  247. package/assets/skills/n8n-integration-testing-patterns/evals/n8n-integration-testing-patterns.yaml +522 -522
  248. package/assets/skills/n8n-integration-testing-patterns/schemas/output.json +291 -291
  249. package/assets/skills/n8n-security-testing/evals/n8n-security-testing.yaml +493 -493
  250. package/assets/skills/n8n-security-testing/schemas/output.json +293 -293
  251. package/assets/skills/n8n-trigger-testing-strategies/evals/n8n-trigger-testing-strategies.yaml +500 -500
  252. package/assets/skills/n8n-trigger-testing-strategies/schemas/output.json +295 -295
  253. package/assets/skills/n8n-workflow-testing-fundamentals/evals/n8n-workflow-testing-fundamentals.yaml +497 -497
  254. package/assets/skills/n8n-workflow-testing-fundamentals/schemas/output.json +254 -254
  255. package/assets/skills/observability-testing-patterns/SKILL.md +930 -930
  256. package/assets/skills/observability-testing-patterns/evals/observability-testing-patterns.yaml +157 -157
  257. package/assets/skills/observability-testing-patterns/schemas/output.json +58 -58
  258. package/assets/skills/observability-testing-patterns/scripts/validate-config.json +25 -25
  259. package/assets/skills/pentest-validation/SKILL.md +268 -268
  260. package/assets/skills/pentest-validation/evals/pentest-validation.yaml +708 -708
  261. package/assets/skills/pentest-validation/schemas/output.json +281 -281
  262. package/assets/skills/performance-testing/evals/performance-testing.yaml +772 -772
  263. package/assets/skills/performance-testing/schemas/output.json +1184 -1184
  264. package/assets/skills/pr-review/SKILL.md +61 -61
  265. package/assets/skills/qcsd-cicd-swarm/SKILL.md +2206 -2206
  266. package/assets/skills/qcsd-cicd-swarm/evals/qcsd-cicd-swarm.yaml +211 -211
  267. package/assets/skills/qcsd-cicd-swarm/schemas/output.json +86 -86
  268. package/assets/skills/qcsd-cicd-swarm/scripts/validate-config.json +30 -30
  269. package/assets/skills/qcsd-development-swarm/SKILL.md +2154 -2154
  270. package/assets/skills/qcsd-development-swarm/evals/qcsd-development-swarm.yaml +162 -162
  271. package/assets/skills/qcsd-development-swarm/schemas/output.json +72 -72
  272. package/assets/skills/qcsd-development-swarm/scripts/validate-config.json +25 -25
  273. package/assets/skills/qcsd-ideation-swarm/evals/qcsd-ideation-swarm.yaml +138 -138
  274. package/assets/skills/qcsd-ideation-swarm/schemas/output.json +568 -568
  275. package/assets/skills/qcsd-production-swarm/SKILL.md +2781 -2781
  276. package/assets/skills/qcsd-production-swarm/evals/qcsd-production-swarm.yaml +246 -246
  277. package/assets/skills/qcsd-production-swarm/schemas/output.json +505 -505
  278. package/assets/skills/qcsd-production-swarm/scripts/validate-config.json +25 -25
  279. package/assets/skills/qe-chaos-resilience/evals/qe-chaos-resilience.yaml +443 -443
  280. package/assets/skills/qe-chaos-resilience/schemas/output.json +314 -314
  281. package/assets/skills/qe-code-intelligence/evals/qe-code-intelligence.yaml +459 -459
  282. package/assets/skills/qe-code-intelligence/schemas/output.json +315 -315
  283. package/assets/skills/qe-contract-testing/evals/qe-contract-testing.yaml +513 -513
  284. package/assets/skills/qe-contract-testing/schemas/output.json +295 -295
  285. package/assets/skills/qe-coverage-analysis/evals/qe-coverage-analysis.yaml +494 -494
  286. package/assets/skills/qe-coverage-analysis/schemas/output.json +286 -286
  287. package/assets/skills/qe-defect-intelligence/evals/qe-defect-intelligence.yaml +511 -511
  288. package/assets/skills/qe-defect-intelligence/schemas/output.json +283 -283
  289. package/assets/skills/qe-iterative-loop/schemas/output.json +264 -264
  290. package/assets/skills/qe-learning-optimization/evals/qe-learning-optimization.yaml +144 -144
  291. package/assets/skills/qe-learning-optimization/schemas/output.json +288 -288
  292. package/assets/skills/qe-quality-assessment/evals/qe-quality-assessment.yaml +506 -506
  293. package/assets/skills/qe-quality-assessment/schemas/output.json +550 -550
  294. package/assets/skills/qe-requirements-validation/evals/qe-requirements-validation.yaml +598 -598
  295. package/assets/skills/qe-requirements-validation/schemas/output.json +587 -587
  296. package/assets/skills/qe-security-compliance/evals/qe-security-compliance.yaml +595 -595
  297. package/assets/skills/qe-security-compliance/schemas/output.json +498 -498
  298. package/assets/skills/qe-test-execution/evals/qe-test-execution.yaml +607 -607
  299. package/assets/skills/qe-test-execution/schemas/output.json +529 -529
  300. package/assets/skills/qe-test-generation/evals/qe-test-generation.yaml +148 -148
  301. package/assets/skills/qe-test-generation/schemas/output.json +439 -439
  302. package/assets/skills/qe-visual-accessibility/evals/qe-visual-accessibility.yaml +142 -142
  303. package/assets/skills/qe-visual-accessibility/schemas/output.json +491 -491
  304. package/assets/skills/quality-metrics/evals/quality-metrics.yaml +494 -494
  305. package/assets/skills/quality-metrics/schemas/output.json +403 -403
  306. package/assets/skills/refactoring-patterns/schemas/output.json +475 -475
  307. package/assets/skills/regression-testing/evals/regression-testing.yaml +504 -504
  308. package/assets/skills/regression-testing/schemas/output.json +311 -311
  309. package/assets/skills/risk-based-testing/evals/risk-based-testing.yaml +141 -141
  310. package/assets/skills/risk-based-testing/schemas/output.json +480 -480
  311. package/assets/skills/security-testing/evals/security-testing.yaml +789 -789
  312. package/assets/skills/security-testing/schemas/output.json +879 -879
  313. package/assets/skills/security-visual-testing/evals/security-visual-testing.yaml +163 -163
  314. package/assets/skills/security-visual-testing/schemas/output.json +486 -486
  315. package/assets/skills/sfdipot-product-factors/SKILL.md +239 -239
  316. package/assets/skills/sherlock-review/schemas/output.json +297 -297
  317. package/assets/skills/shift-left-testing/evals/shift-left-testing.yaml +145 -145
  318. package/assets/skills/shift-left-testing/schemas/output.json +459 -459
  319. package/assets/skills/shift-right-testing/evals/shift-right-testing.yaml +147 -147
  320. package/assets/skills/shift-right-testing/schemas/output.json +418 -418
  321. package/assets/skills/tdd-london-chicago/schemas/output.json +444 -444
  322. package/assets/skills/technical-writing/schemas/output.json +268 -268
  323. package/assets/skills/test-automation-strategy/evals/test-automation-strategy.yaml +148 -148
  324. package/assets/skills/test-automation-strategy/schemas/output.json +444 -444
  325. package/assets/skills/test-data-management/evals/test-data-management.yaml +504 -504
  326. package/assets/skills/test-data-management/schemas/output.json +284 -284
  327. package/assets/skills/test-design-techniques/evals/test-design-techniques.yaml +142 -142
  328. package/assets/skills/test-design-techniques/schemas/output.json +295 -295
  329. package/assets/skills/test-environment-management/schemas/output.json +310 -310
  330. package/assets/skills/test-idea-rewriting/SKILL.md +229 -229
  331. package/assets/skills/test-reporting-analytics/evals/test-reporting-analytics.yaml +155 -155
  332. package/assets/skills/test-reporting-analytics/schemas/output.json +329 -329
  333. package/assets/skills/testability-scoring/evals/testability-scoring.yaml +814 -814
  334. package/assets/skills/testability-scoring/resources/templates/config.template.js +84 -84
  335. package/assets/skills/testability-scoring/schemas/output.json +606 -606
  336. package/assets/skills/testability-scoring/scripts/generate-html-report.js +1007 -1007
  337. package/assets/skills/verification-quality/evals/verification-quality.yaml +150 -150
  338. package/assets/skills/verification-quality/schemas/output.json +432 -432
  339. package/assets/skills/visual-testing-advanced/evals/visual-testing-advanced.yaml +154 -154
  340. package/assets/skills/visual-testing-advanced/schemas/output.json +294 -294
  341. package/assets/skills/wms-testing-patterns/evals/wms-testing-patterns.yaml +165 -165
  342. package/assets/skills/wms-testing-patterns/schemas/output.json +150 -150
  343. package/assets/skills/wms-testing-patterns/scripts/validate-config.json +51 -51
  344. package/assets/templates/validation-summary.json +56 -56
  345. package/dist/agents/claim-verifier/verifiers/output-verifier.d.ts +1 -0
  346. package/dist/agents/claim-verifier/verifiers/output-verifier.d.ts.map +1 -1
  347. package/dist/agents/claim-verifier/verifiers/output-verifier.js +16 -3
  348. package/dist/agents/claim-verifier/verifiers/output-verifier.js.map +1 -1
  349. package/dist/cli/bundle.js +488 -75
  350. package/dist/cli/commands/mcp.d.ts.map +1 -1
  351. package/dist/cli/commands/mcp.js +11 -9
  352. package/dist/cli/commands/mcp.js.map +1 -1
  353. package/dist/governance/adversarial-defense-integration.d.ts +29 -0
  354. package/dist/governance/adversarial-defense-integration.d.ts.map +1 -1
  355. package/dist/governance/adversarial-defense-integration.js +85 -1
  356. package/dist/governance/adversarial-defense-integration.js.map +1 -1
  357. package/dist/governance/continue-gate-integration.d.ts +7 -5
  358. package/dist/governance/continue-gate-integration.d.ts.map +1 -1
  359. package/dist/governance/continue-gate-integration.js +72 -15
  360. package/dist/governance/continue-gate-integration.js.map +1 -1
  361. package/dist/governance/deterministic-gateway-integration.d.ts +5 -0
  362. package/dist/governance/deterministic-gateway-integration.d.ts.map +1 -1
  363. package/dist/governance/deterministic-gateway-integration.js +35 -1
  364. package/dist/governance/deterministic-gateway-integration.js.map +1 -1
  365. package/dist/governance/evolution-pipeline-integration.d.ts +5 -0
  366. package/dist/governance/evolution-pipeline-integration.d.ts.map +1 -1
  367. package/dist/governance/evolution-pipeline-integration.js +57 -1
  368. package/dist/governance/evolution-pipeline-integration.js.map +1 -1
  369. package/dist/governance/memory-write-gate-integration.d.ts +6 -3
  370. package/dist/governance/memory-write-gate-integration.d.ts.map +1 -1
  371. package/dist/governance/memory-write-gate-integration.js +48 -10
  372. package/dist/governance/memory-write-gate-integration.js.map +1 -1
  373. package/dist/governance/proof-envelope-integration.d.ts +1 -0
  374. package/dist/governance/proof-envelope-integration.d.ts.map +1 -1
  375. package/dist/governance/proof-envelope-integration.js +37 -0
  376. package/dist/governance/proof-envelope-integration.js.map +1 -1
  377. package/dist/governance/shard-retriever-integration.d.ts +10 -0
  378. package/dist/governance/shard-retriever-integration.d.ts.map +1 -1
  379. package/dist/governance/shard-retriever-integration.js +50 -1
  380. package/dist/governance/shard-retriever-integration.js.map +1 -1
  381. package/dist/governance/trust-accumulator-integration.d.ts +5 -0
  382. package/dist/governance/trust-accumulator-integration.d.ts.map +1 -1
  383. package/dist/governance/trust-accumulator-integration.js +35 -2
  384. package/dist/governance/trust-accumulator-integration.js.map +1 -1
  385. package/dist/init/phases/10-workers.js +2 -2
  386. package/dist/init/phases/10-workers.js.map +1 -1
  387. package/dist/mcp/bundle.js +478 -62
  388. package/dist/mcp/protocol-server.js +2 -2
  389. package/dist/mcp/tool-registry.d.ts.map +1 -1
  390. package/dist/mcp/tool-registry.js +1 -0
  391. package/dist/mcp/tool-registry.js.map +1 -1
  392. package/dist/shared/language-detector.js +1 -1
  393. package/dist/shared/language-detector.js.map +1 -1
  394. package/dist/shared/parsers/multi-language-parser.d.ts.map +1 -1
  395. package/dist/shared/parsers/multi-language-parser.js +55 -16
  396. package/dist/shared/parsers/multi-language-parser.js.map +1 -1
  397. package/dist/shared/sql-safety.d.ts.map +1 -1
  398. package/dist/shared/sql-safety.js +7 -1
  399. package/dist/shared/sql-safety.js.map +1 -1
  400. package/package.json +6 -2
  401. package/scripts/prepare-assets.sh +8 -0
@@ -1,652 +1,652 @@
1
- # =============================================================================
2
- # Mutation Testing Skill Evaluation Test Suite v1.0.0
3
- # Path: .claude/skills/mutation-testing/evals/mutation-testing.yaml
4
- # =============================================================================
5
- #
6
- # This evaluation suite validates mutation testing skill behavior through:
7
- # 1. Input/expected-output test cases for mutation operators
8
- # 2. Multi-model consistency testing
9
- # 3. Semantic validation of mutation analysis quality
10
- # 4. AQE MCP integration for shared learning
11
- #
12
- # Schema: .claude/skills/.validation/schemas/skill-eval.schema.json
13
- # =============================================================================
14
-
15
- skill: mutation-testing
16
- version: 1.0.0
17
- description: >
18
- Comprehensive evaluation test suite for the mutation-testing skill.
19
- Tests mutation score calculation, operator detection, surviving mutant
20
- analysis, and test improvement recommendations across multiple models
21
- to ensure consistent, high-quality mutation analysis output.
22
-
23
- # =============================================================================
24
- # Multi-Model Configuration
25
- # =============================================================================
26
-
27
- models_to_test:
28
- - claude-3.5-sonnet # Primary model (high accuracy expected)
29
- - claude-3-haiku # Fast model (ensure minimum quality)
30
- - gpt-4o # Cross-vendor validation
31
-
32
- # =============================================================================
33
- # MCP Integration Configuration
34
- # =============================================================================
35
-
36
- mcp_integration:
37
- enabled: true
38
- namespace: skill-validation/mutation-testing
39
-
40
- query_patterns: true
41
- track_outcomes: true
42
- store_patterns: true
43
- share_learning: true
44
- update_quality_gate: true
45
-
46
- target_agents:
47
- - qe-learning-coordinator
48
- - qe-queen-coordinator
49
- - qe-mutation-tester
50
-
51
- # =============================================================================
52
- # ReasoningBank Learning Configuration
53
- # =============================================================================
54
-
55
- learning:
56
- store_success_patterns: true
57
- store_failure_patterns: true
58
- pattern_ttl_days: 90
59
- min_confidence_to_store: 0.7
60
- cross_model_comparison: true
61
-
62
- # =============================================================================
63
- # Result Format Configuration
64
- # =============================================================================
65
-
66
- result_format:
67
- json_output: true
68
- markdown_report: true
69
- include_raw_output: false
70
- include_timing: true
71
- include_token_usage: true
72
-
73
- # =============================================================================
74
- # Environment Setup
75
- # =============================================================================
76
-
77
- setup:
78
- required_tools:
79
- - jq
80
- environment_variables:
81
- MUTATION_TIMEOUT_MS: "30000"
82
- fixtures:
83
- - name: simple_arithmetic_code
84
- content: |
85
- function calculateTotal(price, quantity) {
86
- return price * quantity;
87
- }
88
- - name: conditional_code
89
- content: |
90
- function isAdult(age) {
91
- return age >= 18;
92
- }
93
- - name: complex_code
94
- content: |
95
- function processOrder(order) {
96
- if (order.quantity <= 0) {
97
- throw new Error('Invalid quantity');
98
- }
99
- let discount = 0;
100
- if (order.quantity >= 10 && order.isPremium) {
101
- discount = 0.1;
102
- }
103
- return order.price * order.quantity * (1 - discount);
104
- }
105
-
106
- # =============================================================================
107
- # Test Cases
108
- # =============================================================================
109
-
110
- test_cases:
111
- # -------------------------------------------------------------------------
112
- # Basic Functionality Tests
113
- # -------------------------------------------------------------------------
114
-
115
- - id: tc001_basic_mutation_analysis
116
- description: "Skill analyzes simple code and identifies potential mutations"
117
- category: basic
118
- priority: critical
119
-
120
- input:
121
- code: |
122
- function add(a, b) {
123
- return a + b;
124
- }
125
- context:
126
- language: javascript
127
- prompt: |
128
- Analyze this code for mutation testing. Identify what mutations
129
- could be applied and what tests would be needed to kill them.
130
-
131
- expected_output:
132
- must_contain:
133
- - "mutation"
134
- - "arithmetic"
135
- - "+"
136
- must_not_contain:
137
- - "unable to analyze"
138
- - "error"
139
- finding_count:
140
- min: 1
141
- max: 10
142
-
143
- validation:
144
- schema_check: true
145
- keyword_match_threshold: 0.8
146
- reasoning_quality_min: 0.7
147
-
148
- - id: tc002_mutation_score_calculation
149
- description: "Skill correctly calculates mutation score from kill/survive data"
150
- category: basic
151
- priority: critical
152
-
153
- input:
154
- prompt: |
155
- Given these mutation testing results:
156
- - Total mutants: 100
157
- - Killed: 85
158
- - Survived: 12
159
- - Timeout: 2
160
- - No Coverage: 1
161
-
162
- Calculate the mutation score and assess the test suite quality.
163
-
164
- expected_output:
165
- must_contain:
166
- - "85"
167
- - "mutation score"
168
- - "quality"
169
- must_match_regex:
170
- - "8[0-9](\\.\\d+)?%" # Score around 85%
171
-
172
- validation:
173
- schema_check: true
174
- keyword_match_threshold: 0.9
175
-
176
- # -------------------------------------------------------------------------
177
- # Arithmetic Operator Tests (AOR)
178
- # -------------------------------------------------------------------------
179
-
180
- - id: tc003_arithmetic_operator_mutation
181
- description: "Skill identifies arithmetic operator mutations (+, -, *, /)"
182
- category: operators
183
- priority: high
184
-
185
- input:
186
- code: |
187
- function calculateTotal(price, quantity, tax) {
188
- const subtotal = price * quantity;
189
- const taxAmount = subtotal * tax;
190
- return subtotal + taxAmount;
191
- }
192
- context:
193
- language: javascript
194
- prompt: |
195
- Perform mutation analysis focusing on arithmetic operators.
196
- Identify all AOR (Arithmetic Operator Replacement) mutations.
197
-
198
- expected_output:
199
- must_contain:
200
- - "arithmetic"
201
- - "*"
202
- - "+"
203
- - "mutant"
204
- must_not_contain:
205
- - "no mutations"
206
-
207
- validation:
208
- schema_check: true
209
- keyword_match_threshold: 0.8
210
-
211
- # -------------------------------------------------------------------------
212
- # Relational Operator Tests (ROR)
213
- # -------------------------------------------------------------------------
214
-
215
- - id: tc004_relational_operator_mutation
216
- description: "Skill identifies relational operator mutations (>, <, >=, <=, ==, !=)"
217
- category: operators
218
- priority: high
219
-
220
- input:
221
- code: |
222
- function isEligible(age, income) {
223
- if (age >= 18 && income > 30000) {
224
- return true;
225
- }
226
- if (age < 65 && income <= 100000) {
227
- return true;
228
- }
229
- return false;
230
- }
231
- context:
232
- language: javascript
233
- prompt: |
234
- Analyze this code for relational operator mutations (ROR).
235
- Identify boundary conditions that need testing.
236
-
237
- expected_output:
238
- must_contain:
239
- - "relational"
240
- - ">="
241
- - "boundary"
242
- - "18"
243
- must_not_contain:
244
- - "unable"
245
-
246
- validation:
247
- schema_check: true
248
- keyword_match_threshold: 0.8
249
- reasoning_quality_min: 0.7
250
-
251
- - id: tc005_boundary_mutation_detection
252
- description: "Skill detects boundary value mutations (>= to >, etc.)"
253
- category: operators
254
- priority: critical
255
-
256
- input:
257
- code: |
258
- function getDiscount(quantity) {
259
- if (quantity >= 10) {
260
- return 0.1; // 10% discount
261
- }
262
- return 0;
263
- }
264
- context:
265
- language: javascript
266
- prompt: |
267
- This code has a boundary condition at quantity=10.
268
- What mutation would test if the boundary is correctly tested?
269
- What test case would kill that mutant?
270
-
271
- expected_output:
272
- must_contain:
273
- - "10"
274
- - "boundary"
275
- - ">="
276
- - ">"
277
- must_not_contain:
278
- - "no boundary"
279
-
280
- validation:
281
- schema_check: true
282
- reasoning_quality_min: 0.8
283
-
284
- # -------------------------------------------------------------------------
285
- # Logical Operator Tests (LCR/LOD)
286
- # -------------------------------------------------------------------------
287
-
288
- - id: tc006_logical_operator_mutation
289
- description: "Skill identifies logical operator mutations (&&, ||, !)"
290
- category: operators
291
- priority: high
292
-
293
- input:
294
- code: |
295
- function canAccess(user) {
296
- return user.isActive && (user.role === 'admin' || user.hasPermission);
297
- }
298
- context:
299
- language: javascript
300
- prompt: |
301
- Analyze this code for logical connector replacements (LCR).
302
- What happens if && is changed to || or vice versa?
303
-
304
- expected_output:
305
- must_contain:
306
- - "logical"
307
- - "&&"
308
- - "||"
309
- must_not_contain:
310
- - "no logical"
311
-
312
- validation:
313
- schema_check: true
314
- keyword_match_threshold: 0.8
315
-
316
- # -------------------------------------------------------------------------
317
- # Conditional Operator Tests (COR)
318
- # -------------------------------------------------------------------------
319
-
320
- - id: tc007_conditional_mutation
321
- description: "Skill identifies conditional/decision mutations"
322
- category: operators
323
- priority: high
324
-
325
- input:
326
- code: |
327
- function processPayment(payment) {
328
- if (payment.amount > 0) {
329
- if (payment.verified) {
330
- return 'approved';
331
- }
332
- return 'pending';
333
- }
334
- return 'rejected';
335
- }
336
- context:
337
- language: javascript
338
- prompt: |
339
- Analyze conditional mutations for this payment processing code.
340
- Consider mutations like replacing conditions with true/false.
341
-
342
- expected_output:
343
- must_contain:
344
- - "conditional"
345
- - "if"
346
- - "true"
347
- - "false"
348
-
349
- validation:
350
- schema_check: true
351
- keyword_match_threshold: 0.7
352
-
353
- # -------------------------------------------------------------------------
354
- # Return Value Tests (RVR)
355
- # -------------------------------------------------------------------------
356
-
357
- - id: tc008_return_value_mutation
358
- description: "Skill identifies return value mutations"
359
- category: operators
360
- priority: medium
361
-
362
- input:
363
- code: |
364
- function getStatus(code) {
365
- if (code === 200) return 'success';
366
- if (code === 404) return 'not found';
367
- if (code >= 500) return 'error';
368
- return 'unknown';
369
- }
370
- context:
371
- language: javascript
372
- prompt: |
373
- Analyze return value mutations for this status code handler.
374
- What mutations could be applied to the return statements?
375
-
376
- expected_output:
377
- must_contain:
378
- - "return"
379
- - "mutation"
380
- - "success"
381
- - "error"
382
-
383
- validation:
384
- schema_check: true
385
- keyword_match_threshold: 0.7
386
-
387
- # -------------------------------------------------------------------------
388
- # Surviving Mutant Analysis Tests
389
- # -------------------------------------------------------------------------
390
-
391
- - id: tc009_surviving_mutant_analysis
392
- description: "Skill analyzes surviving mutants and suggests test improvements"
393
- category: analysis
394
- priority: critical
395
-
396
- input:
397
- prompt: |
398
- The following mutant survived:
399
- - File: src/validator.ts
400
- - Line: 45
401
- - Original: if (age >= 18)
402
- - Mutated: if (age > 18)
403
- - Tests that cover this line: ['should validate adult', 'should validate minor']
404
-
405
- Why did this mutant survive and what test would kill it?
406
-
407
- expected_output:
408
- must_contain:
409
- - "boundary"
410
- - "18"
411
- - "test"
412
- - "exactly"
413
- must_not_contain:
414
- - "cannot determine"
415
-
416
- validation:
417
- schema_check: true
418
- reasoning_quality_min: 0.8
419
-
420
- - id: tc010_weak_test_identification
421
- description: "Skill identifies weak tests based on surviving mutants"
422
- category: analysis
423
- priority: high
424
-
425
- input:
426
- prompt: |
427
- Mutation testing results for auth.test.js:
428
- - 50 mutants generated in auth.js
429
- - 35 killed by auth.test.js
430
- - 15 survived
431
-
432
- Surviving mutant operators:
433
- - 8 relational (ROR)
434
- - 5 boundary (BOR)
435
- - 2 logical (LCR)
436
-
437
- Analyze what makes auth.test.js weak and how to improve it.
438
-
439
- expected_output:
440
- must_contain:
441
- - "weak"
442
- - "boundary"
443
- - "relational"
444
- - "improve"
445
- recommendation_count:
446
- min: 1
447
-
448
- validation:
449
- schema_check: true
450
- reasoning_quality_min: 0.7
451
-
452
- # -------------------------------------------------------------------------
453
- # Edge Cases
454
- # -------------------------------------------------------------------------
455
-
456
- - id: tc011_empty_code_handling
457
- description: "Skill handles empty or minimal code gracefully"
458
- category: edge_cases
459
- priority: medium
460
-
461
- input:
462
- code: |
463
- // Empty function
464
- function noop() {}
465
- context:
466
- language: javascript
467
- prompt: Analyze this code for mutation testing.
468
-
469
- expected_output:
470
- must_contain:
471
- - "no mutation"
472
- must_not_contain:
473
- - "error"
474
- - "crash"
475
-
476
- validation:
477
- schema_check: true
478
- allow_partial: true
479
-
480
- - id: tc012_complex_nested_conditions
481
- description: "Skill handles complex nested conditions"
482
- category: edge_cases
483
- priority: medium
484
-
485
- input:
486
- code: |
487
- function complexValidation(data) {
488
- if (data && data.type === 'A') {
489
- if (data.value > 0 && data.value <= 100) {
490
- if (data.status === 'active' || data.override) {
491
- return data.priority >= 1 && data.priority <= 5;
492
- }
493
- }
494
- }
495
- return false;
496
- }
497
- context:
498
- language: javascript
499
- prompt: |
500
- Analyze all possible mutations in this complex nested validation.
501
- Prioritize by impact.
502
-
503
- expected_output:
504
- must_contain:
505
- - "nested"
506
- - "condition"
507
- - "mutation"
508
- finding_count:
509
- min: 5
510
-
511
- validation:
512
- schema_check: true
513
- keyword_match_threshold: 0.7
514
-
515
- # -------------------------------------------------------------------------
516
- # Multi-Language Support
517
- # -------------------------------------------------------------------------
518
-
519
- - id: tc013_python_mutation_analysis
520
- description: "Skill correctly analyzes Python code mutations"
521
- category: language_support
522
- priority: medium
523
-
524
- input:
525
- code: |
526
- def calculate_price(base_price, discount_percent, tax_rate):
527
- discount = base_price * (discount_percent / 100)
528
- subtotal = base_price - discount
529
- tax = subtotal * tax_rate
530
- return subtotal + tax
531
- context:
532
- language: python
533
- prompt: Analyze this Python code for mutation testing.
534
-
535
- expected_output:
536
- must_contain:
537
- - "mutation"
538
- - "arithmetic"
539
- - "python"
540
-
541
- validation:
542
- schema_check: true
543
-
544
- - id: tc014_typescript_mutation_analysis
545
- description: "Skill correctly analyzes TypeScript code mutations"
546
- category: language_support
547
- priority: medium
548
-
549
- input:
550
- code: |
551
- interface Order {
552
- quantity: number;
553
- price: number;
554
- isPremium: boolean;
555
- }
556
-
557
- function calculateDiscount(order: Order): number {
558
- if (order.quantity >= 10 && order.isPremium) {
559
- return order.price * 0.15;
560
- }
561
- if (order.quantity >= 5) {
562
- return order.price * 0.05;
563
- }
564
- return 0;
565
- }
566
- context:
567
- language: typescript
568
- prompt: Analyze this TypeScript code for mutation testing.
569
-
570
- expected_output:
571
- must_contain:
572
- - "mutation"
573
- - "typescript"
574
- - "boundary"
575
-
576
- validation:
577
- schema_check: true
578
-
579
- # -------------------------------------------------------------------------
580
- # Integration with Coverage
581
- # -------------------------------------------------------------------------
582
-
583
- - id: tc015_coverage_mutation_correlation
584
- description: "Skill correlates coverage with mutation score"
585
- category: integration
586
- priority: high
587
-
588
- input:
589
- prompt: |
590
- Coverage report shows:
591
- - Line coverage: 95%
592
- - Branch coverage: 88%
593
-
594
- Mutation testing shows:
595
- - Mutation score: 65%
596
-
597
- Analyze the gap between coverage and mutation score.
598
- Why can high coverage coexist with low mutation score?
599
-
600
- expected_output:
601
- must_contain:
602
- - "coverage"
603
- - "mutation"
604
- - "assertion"
605
- - "quality"
606
- must_not_contain:
607
- - "coverage equals"
608
-
609
- validation:
610
- schema_check: true
611
- reasoning_quality_min: 0.8
612
- grading_rubric:
613
- completeness: 0.4
614
- accuracy: 0.4
615
- actionability: 0.2
616
-
617
- # =============================================================================
618
- # Success Criteria
619
- # =============================================================================
620
-
621
- success_criteria:
622
- # Minimum 90% of tests must pass
623
- pass_rate: 0.9
624
-
625
- # All critical tests must pass
626
- critical_pass_rate: 1.0
627
-
628
- # Minimum reasoning quality
629
- avg_reasoning_quality: 0.7
630
-
631
- # Maximum 5 minutes for full suite
632
- max_execution_time_ms: 300000
633
-
634
- # Maximum 15% variance between models
635
- cross_model_variance: 0.15
636
-
637
- # =============================================================================
638
- # Metadata
639
- # =============================================================================
640
-
641
- metadata:
642
- author: "@agentic-qe"
643
- created: "2026-02-02"
644
- last_updated: "2026-02-02"
645
- coverage_target: >
646
- Comprehensive mutation operator coverage (AOR, ROR, LCR, COR, RVR),
647
- surviving mutant analysis, weak test identification, multi-language
648
- support, and coverage correlation analysis.
649
- related_skills:
650
- - test-design-techniques
651
- - coverage-analysis
652
- - tdd-london-chicago
1
+ # =============================================================================
2
+ # Mutation Testing Skill Evaluation Test Suite v1.0.0
3
+ # Path: .claude/skills/mutation-testing/evals/mutation-testing.yaml
4
+ # =============================================================================
5
+ #
6
+ # This evaluation suite validates mutation testing skill behavior through:
7
+ # 1. Input/expected-output test cases for mutation operators
8
+ # 2. Multi-model consistency testing
9
+ # 3. Semantic validation of mutation analysis quality
10
+ # 4. AQE MCP integration for shared learning
11
+ #
12
+ # Schema: .claude/skills/.validation/schemas/skill-eval.schema.json
13
+ # =============================================================================
14
+
15
+ skill: mutation-testing
16
+ version: 1.0.0
17
+ description: >
18
+ Comprehensive evaluation test suite for the mutation-testing skill.
19
+ Tests mutation score calculation, operator detection, surviving mutant
20
+ analysis, and test improvement recommendations across multiple models
21
+ to ensure consistent, high-quality mutation analysis output.
22
+
23
+ # =============================================================================
24
+ # Multi-Model Configuration
25
+ # =============================================================================
26
+
27
+ models_to_test:
28
+ - claude-3.5-sonnet # Primary model (high accuracy expected)
29
+ - claude-3-haiku # Fast model (ensure minimum quality)
30
+ - gpt-4o # Cross-vendor validation
31
+
32
+ # =============================================================================
33
+ # MCP Integration Configuration
34
+ # =============================================================================
35
+
36
+ mcp_integration:
37
+ enabled: true
38
+ namespace: skill-validation/mutation-testing
39
+
40
+ query_patterns: true
41
+ track_outcomes: true
42
+ store_patterns: true
43
+ share_learning: true
44
+ update_quality_gate: true
45
+
46
+ target_agents:
47
+ - qe-learning-coordinator
48
+ - qe-queen-coordinator
49
+ - qe-mutation-tester
50
+
51
+ # =============================================================================
52
+ # ReasoningBank Learning Configuration
53
+ # =============================================================================
54
+
55
+ learning:
56
+ store_success_patterns: true
57
+ store_failure_patterns: true
58
+ pattern_ttl_days: 90
59
+ min_confidence_to_store: 0.7
60
+ cross_model_comparison: true
61
+
62
+ # =============================================================================
63
+ # Result Format Configuration
64
+ # =============================================================================
65
+
66
+ result_format:
67
+ json_output: true
68
+ markdown_report: true
69
+ include_raw_output: false
70
+ include_timing: true
71
+ include_token_usage: true
72
+
73
+ # =============================================================================
74
+ # Environment Setup
75
+ # =============================================================================
76
+
77
+ setup:
78
+ required_tools:
79
+ - jq
80
+ environment_variables:
81
+ MUTATION_TIMEOUT_MS: "30000"
82
+ fixtures:
83
+ - name: simple_arithmetic_code
84
+ content: |
85
+ function calculateTotal(price, quantity) {
86
+ return price * quantity;
87
+ }
88
+ - name: conditional_code
89
+ content: |
90
+ function isAdult(age) {
91
+ return age >= 18;
92
+ }
93
+ - name: complex_code
94
+ content: |
95
+ function processOrder(order) {
96
+ if (order.quantity <= 0) {
97
+ throw new Error('Invalid quantity');
98
+ }
99
+ let discount = 0;
100
+ if (order.quantity >= 10 && order.isPremium) {
101
+ discount = 0.1;
102
+ }
103
+ return order.price * order.quantity * (1 - discount);
104
+ }
105
+
106
+ # =============================================================================
107
+ # Test Cases
108
+ # =============================================================================
109
+
110
+ test_cases:
111
+ # -------------------------------------------------------------------------
112
+ # Basic Functionality Tests
113
+ # -------------------------------------------------------------------------
114
+
115
+ - id: tc001_basic_mutation_analysis
116
+ description: "Skill analyzes simple code and identifies potential mutations"
117
+ category: basic
118
+ priority: critical
119
+
120
+ input:
121
+ code: |
122
+ function add(a, b) {
123
+ return a + b;
124
+ }
125
+ context:
126
+ language: javascript
127
+ prompt: |
128
+ Analyze this code for mutation testing. Identify what mutations
129
+ could be applied and what tests would be needed to kill them.
130
+
131
+ expected_output:
132
+ must_contain:
133
+ - "mutation"
134
+ - "arithmetic"
135
+ - "+"
136
+ must_not_contain:
137
+ - "unable to analyze"
138
+ - "error"
139
+ finding_count:
140
+ min: 1
141
+ max: 10
142
+
143
+ validation:
144
+ schema_check: true
145
+ keyword_match_threshold: 0.8
146
+ reasoning_quality_min: 0.7
147
+
148
+ - id: tc002_mutation_score_calculation
149
+ description: "Skill correctly calculates mutation score from kill/survive data"
150
+ category: basic
151
+ priority: critical
152
+
153
+ input:
154
+ prompt: |
155
+ Given these mutation testing results:
156
+ - Total mutants: 100
157
+ - Killed: 85
158
+ - Survived: 12
159
+ - Timeout: 2
160
+ - No Coverage: 1
161
+
162
+ Calculate the mutation score and assess the test suite quality.
163
+
164
+ expected_output:
165
+ must_contain:
166
+ - "85"
167
+ - "mutation score"
168
+ - "quality"
169
+ must_match_regex:
170
+ - "8[0-9](\\.\\d+)?%" # Score around 85%
171
+
172
+ validation:
173
+ schema_check: true
174
+ keyword_match_threshold: 0.9
175
+
176
+ # -------------------------------------------------------------------------
177
+ # Arithmetic Operator Tests (AOR)
178
+ # -------------------------------------------------------------------------
179
+
180
+ - id: tc003_arithmetic_operator_mutation
181
+ description: "Skill identifies arithmetic operator mutations (+, -, *, /)"
182
+ category: operators
183
+ priority: high
184
+
185
+ input:
186
+ code: |
187
+ function calculateTotal(price, quantity, tax) {
188
+ const subtotal = price * quantity;
189
+ const taxAmount = subtotal * tax;
190
+ return subtotal + taxAmount;
191
+ }
192
+ context:
193
+ language: javascript
194
+ prompt: |
195
+ Perform mutation analysis focusing on arithmetic operators.
196
+ Identify all AOR (Arithmetic Operator Replacement) mutations.
197
+
198
+ expected_output:
199
+ must_contain:
200
+ - "arithmetic"
201
+ - "*"
202
+ - "+"
203
+ - "mutant"
204
+ must_not_contain:
205
+ - "no mutations"
206
+
207
+ validation:
208
+ schema_check: true
209
+ keyword_match_threshold: 0.8
210
+
211
+ # -------------------------------------------------------------------------
212
+ # Relational Operator Tests (ROR)
213
+ # -------------------------------------------------------------------------
214
+
215
+ - id: tc004_relational_operator_mutation
216
+ description: "Skill identifies relational operator mutations (>, <, >=, <=, ==, !=)"
217
+ category: operators
218
+ priority: high
219
+
220
+ input:
221
+ code: |
222
+ function isEligible(age, income) {
223
+ if (age >= 18 && income > 30000) {
224
+ return true;
225
+ }
226
+ if (age < 65 && income <= 100000) {
227
+ return true;
228
+ }
229
+ return false;
230
+ }
231
+ context:
232
+ language: javascript
233
+ prompt: |
234
+ Analyze this code for relational operator mutations (ROR).
235
+ Identify boundary conditions that need testing.
236
+
237
+ expected_output:
238
+ must_contain:
239
+ - "relational"
240
+ - ">="
241
+ - "boundary"
242
+ - "18"
243
+ must_not_contain:
244
+ - "unable"
245
+
246
+ validation:
247
+ schema_check: true
248
+ keyword_match_threshold: 0.8
249
+ reasoning_quality_min: 0.7
250
+
251
+ - id: tc005_boundary_mutation_detection
252
+ description: "Skill detects boundary value mutations (>= to >, etc.)"
253
+ category: operators
254
+ priority: critical
255
+
256
+ input:
257
+ code: |
258
+ function getDiscount(quantity) {
259
+ if (quantity >= 10) {
260
+ return 0.1; // 10% discount
261
+ }
262
+ return 0;
263
+ }
264
+ context:
265
+ language: javascript
266
+ prompt: |
267
+ This code has a boundary condition at quantity=10.
268
+ What mutation would test if the boundary is correctly tested?
269
+ What test case would kill that mutant?
270
+
271
+ expected_output:
272
+ must_contain:
273
+ - "10"
274
+ - "boundary"
275
+ - ">="
276
+ - ">"
277
+ must_not_contain:
278
+ - "no boundary"
279
+
280
+ validation:
281
+ schema_check: true
282
+ reasoning_quality_min: 0.8
283
+
284
+ # -------------------------------------------------------------------------
285
+ # Logical Operator Tests (LCR/LOD)
286
+ # -------------------------------------------------------------------------
287
+
288
+ - id: tc006_logical_operator_mutation
289
+ description: "Skill identifies logical operator mutations (&&, ||, !)"
290
+ category: operators
291
+ priority: high
292
+
293
+ input:
294
+ code: |
295
+ function canAccess(user) {
296
+ return user.isActive && (user.role === 'admin' || user.hasPermission);
297
+ }
298
+ context:
299
+ language: javascript
300
+ prompt: |
301
+ Analyze this code for logical connector replacements (LCR).
302
+ What happens if && is changed to || or vice versa?
303
+
304
+ expected_output:
305
+ must_contain:
306
+ - "logical"
307
+ - "&&"
308
+ - "||"
309
+ must_not_contain:
310
+ - "no logical"
311
+
312
+ validation:
313
+ schema_check: true
314
+ keyword_match_threshold: 0.8
315
+
316
+ # -------------------------------------------------------------------------
317
+ # Conditional Operator Tests (COR)
318
+ # -------------------------------------------------------------------------
319
+
320
+ - id: tc007_conditional_mutation
321
+ description: "Skill identifies conditional/decision mutations"
322
+ category: operators
323
+ priority: high
324
+
325
+ input:
326
+ code: |
327
+ function processPayment(payment) {
328
+ if (payment.amount > 0) {
329
+ if (payment.verified) {
330
+ return 'approved';
331
+ }
332
+ return 'pending';
333
+ }
334
+ return 'rejected';
335
+ }
336
+ context:
337
+ language: javascript
338
+ prompt: |
339
+ Analyze conditional mutations for this payment processing code.
340
+ Consider mutations like replacing conditions with true/false.
341
+
342
+ expected_output:
343
+ must_contain:
344
+ - "conditional"
345
+ - "if"
346
+ - "true"
347
+ - "false"
348
+
349
+ validation:
350
+ schema_check: true
351
+ keyword_match_threshold: 0.7
352
+
353
+ # -------------------------------------------------------------------------
354
+ # Return Value Tests (RVR)
355
+ # -------------------------------------------------------------------------
356
+
357
+ - id: tc008_return_value_mutation
358
+ description: "Skill identifies return value mutations"
359
+ category: operators
360
+ priority: medium
361
+
362
+ input:
363
+ code: |
364
+ function getStatus(code) {
365
+ if (code === 200) return 'success';
366
+ if (code === 404) return 'not found';
367
+ if (code >= 500) return 'error';
368
+ return 'unknown';
369
+ }
370
+ context:
371
+ language: javascript
372
+ prompt: |
373
+ Analyze return value mutations for this status code handler.
374
+ What mutations could be applied to the return statements?
375
+
376
+ expected_output:
377
+ must_contain:
378
+ - "return"
379
+ - "mutation"
380
+ - "success"
381
+ - "error"
382
+
383
+ validation:
384
+ schema_check: true
385
+ keyword_match_threshold: 0.7
386
+
387
+ # -------------------------------------------------------------------------
388
+ # Surviving Mutant Analysis Tests
389
+ # -------------------------------------------------------------------------
390
+
391
+ - id: tc009_surviving_mutant_analysis
392
+ description: "Skill analyzes surviving mutants and suggests test improvements"
393
+ category: analysis
394
+ priority: critical
395
+
396
+ input:
397
+ prompt: |
398
+ The following mutant survived:
399
+ - File: src/validator.ts
400
+ - Line: 45
401
+ - Original: if (age >= 18)
402
+ - Mutated: if (age > 18)
403
+ - Tests that cover this line: ['should validate adult', 'should validate minor']
404
+
405
+ Why did this mutant survive and what test would kill it?
406
+
407
+ expected_output:
408
+ must_contain:
409
+ - "boundary"
410
+ - "18"
411
+ - "test"
412
+ - "exactly"
413
+ must_not_contain:
414
+ - "cannot determine"
415
+
416
+ validation:
417
+ schema_check: true
418
+ reasoning_quality_min: 0.8
419
+
420
+ - id: tc010_weak_test_identification
421
+ description: "Skill identifies weak tests based on surviving mutants"
422
+ category: analysis
423
+ priority: high
424
+
425
+ input:
426
+ prompt: |
427
+ Mutation testing results for auth.test.js:
428
+ - 50 mutants generated in auth.js
429
+ - 35 killed by auth.test.js
430
+ - 15 survived
431
+
432
+ Surviving mutant operators:
433
+ - 8 relational (ROR)
434
+ - 5 boundary (BOR)
435
+ - 2 logical (LCR)
436
+
437
+ Analyze what makes auth.test.js weak and how to improve it.
438
+
439
+ expected_output:
440
+ must_contain:
441
+ - "weak"
442
+ - "boundary"
443
+ - "relational"
444
+ - "improve"
445
+ recommendation_count:
446
+ min: 1
447
+
448
+ validation:
449
+ schema_check: true
450
+ reasoning_quality_min: 0.7
451
+
452
+ # -------------------------------------------------------------------------
453
+ # Edge Cases
454
+ # -------------------------------------------------------------------------
455
+
456
+ - id: tc011_empty_code_handling
457
+ description: "Skill handles empty or minimal code gracefully"
458
+ category: edge_cases
459
+ priority: medium
460
+
461
+ input:
462
+ code: |
463
+ // Empty function
464
+ function noop() {}
465
+ context:
466
+ language: javascript
467
+ prompt: Analyze this code for mutation testing.
468
+
469
+ expected_output:
470
+ must_contain:
471
+ - "no mutation"
472
+ must_not_contain:
473
+ - "error"
474
+ - "crash"
475
+
476
+ validation:
477
+ schema_check: true
478
+ allow_partial: true
479
+
480
+ - id: tc012_complex_nested_conditions
481
+ description: "Skill handles complex nested conditions"
482
+ category: edge_cases
483
+ priority: medium
484
+
485
+ input:
486
+ code: |
487
+ function complexValidation(data) {
488
+ if (data && data.type === 'A') {
489
+ if (data.value > 0 && data.value <= 100) {
490
+ if (data.status === 'active' || data.override) {
491
+ return data.priority >= 1 && data.priority <= 5;
492
+ }
493
+ }
494
+ }
495
+ return false;
496
+ }
497
+ context:
498
+ language: javascript
499
+ prompt: |
500
+ Analyze all possible mutations in this complex nested validation.
501
+ Prioritize by impact.
502
+
503
+ expected_output:
504
+ must_contain:
505
+ - "nested"
506
+ - "condition"
507
+ - "mutation"
508
+ finding_count:
509
+ min: 5
510
+
511
+ validation:
512
+ schema_check: true
513
+ keyword_match_threshold: 0.7
514
+
515
+ # -------------------------------------------------------------------------
516
+ # Multi-Language Support
517
+ # -------------------------------------------------------------------------
518
+
519
+ - id: tc013_python_mutation_analysis
520
+ description: "Skill correctly analyzes Python code mutations"
521
+ category: language_support
522
+ priority: medium
523
+
524
+ input:
525
+ code: |
526
+ def calculate_price(base_price, discount_percent, tax_rate):
527
+ discount = base_price * (discount_percent / 100)
528
+ subtotal = base_price - discount
529
+ tax = subtotal * tax_rate
530
+ return subtotal + tax
531
+ context:
532
+ language: python
533
+ prompt: Analyze this Python code for mutation testing.
534
+
535
+ expected_output:
536
+ must_contain:
537
+ - "mutation"
538
+ - "arithmetic"
539
+ - "python"
540
+
541
+ validation:
542
+ schema_check: true
543
+
544
+ - id: tc014_typescript_mutation_analysis
545
+ description: "Skill correctly analyzes TypeScript code mutations"
546
+ category: language_support
547
+ priority: medium
548
+
549
+ input:
550
+ code: |
551
+ interface Order {
552
+ quantity: number;
553
+ price: number;
554
+ isPremium: boolean;
555
+ }
556
+
557
+ function calculateDiscount(order: Order): number {
558
+ if (order.quantity >= 10 && order.isPremium) {
559
+ return order.price * 0.15;
560
+ }
561
+ if (order.quantity >= 5) {
562
+ return order.price * 0.05;
563
+ }
564
+ return 0;
565
+ }
566
+ context:
567
+ language: typescript
568
+ prompt: Analyze this TypeScript code for mutation testing.
569
+
570
+ expected_output:
571
+ must_contain:
572
+ - "mutation"
573
+ - "typescript"
574
+ - "boundary"
575
+
576
+ validation:
577
+ schema_check: true
578
+
579
+ # -------------------------------------------------------------------------
580
+ # Integration with Coverage
581
+ # -------------------------------------------------------------------------
582
+
583
+ - id: tc015_coverage_mutation_correlation
584
+ description: "Skill correlates coverage with mutation score"
585
+ category: integration
586
+ priority: high
587
+
588
+ input:
589
+ prompt: |
590
+ Coverage report shows:
591
+ - Line coverage: 95%
592
+ - Branch coverage: 88%
593
+
594
+ Mutation testing shows:
595
+ - Mutation score: 65%
596
+
597
+ Analyze the gap between coverage and mutation score.
598
+ Why can high coverage coexist with low mutation score?
599
+
600
+ expected_output:
601
+ must_contain:
602
+ - "coverage"
603
+ - "mutation"
604
+ - "assertion"
605
+ - "quality"
606
+ must_not_contain:
607
+ - "coverage equals"
608
+
609
+ validation:
610
+ schema_check: true
611
+ reasoning_quality_min: 0.8
612
+ grading_rubric:
613
+ completeness: 0.4
614
+ accuracy: 0.4
615
+ actionability: 0.2
616
+
617
+ # =============================================================================
618
+ # Success Criteria
619
+ # =============================================================================
620
+
621
+ success_criteria:
622
+ # Minimum 90% of tests must pass
623
+ pass_rate: 0.9
624
+
625
+ # All critical tests must pass
626
+ critical_pass_rate: 1.0
627
+
628
+ # Minimum reasoning quality
629
+ avg_reasoning_quality: 0.7
630
+
631
+ # Maximum 5 minutes for full suite
632
+ max_execution_time_ms: 300000
633
+
634
+ # Maximum 15% variance between models
635
+ cross_model_variance: 0.15
636
+
637
+ # =============================================================================
638
+ # Metadata
639
+ # =============================================================================
640
+
641
+ metadata:
642
+ author: "@agentic-qe"
643
+ created: "2026-02-02"
644
+ last_updated: "2026-02-02"
645
+ coverage_target: >
646
+ Comprehensive mutation operator coverage (AOR, ROR, LCR, COR, RVR),
647
+ surviving mutant analysis, weak test identification, multi-language
648
+ support, and coverage correlation analysis.
649
+ related_skills:
650
+ - test-design-techniques
651
+ - coverage-analysis
652
+ - tdd-london-chicago