@ngocsangairvds/vsaf 3.0.0

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 (282) hide show
  1. package/.claude/skills/bmad-advanced-elicitation/SKILL.md +136 -0
  2. package/.claude/skills/bmad-advanced-elicitation/methods.csv +51 -0
  3. package/.claude/skills/bmad-agent-analyst/SKILL.md +59 -0
  4. package/.claude/skills/bmad-agent-analyst/bmad-skill-manifest.yaml +11 -0
  5. package/.claude/skills/bmad-agent-architect/SKILL.md +54 -0
  6. package/.claude/skills/bmad-agent-architect/bmad-skill-manifest.yaml +11 -0
  7. package/.claude/skills/bmad-agent-dev/SKILL.md +69 -0
  8. package/.claude/skills/bmad-agent-dev/bmad-skill-manifest.yaml +11 -0
  9. package/.claude/skills/bmad-agent-pm/SKILL.md +59 -0
  10. package/.claude/skills/bmad-agent-pm/bmad-skill-manifest.yaml +11 -0
  11. package/.claude/skills/bmad-agent-tech-writer/SKILL.md +57 -0
  12. package/.claude/skills/bmad-agent-tech-writer/bmad-skill-manifest.yaml +11 -0
  13. package/.claude/skills/bmad-agent-tech-writer/explain-concept.md +20 -0
  14. package/.claude/skills/bmad-agent-tech-writer/mermaid-gen.md +20 -0
  15. package/.claude/skills/bmad-agent-tech-writer/validate-doc.md +19 -0
  16. package/.claude/skills/bmad-agent-tech-writer/write-document.md +20 -0
  17. package/.claude/skills/bmad-agent-ux-designer/SKILL.md +55 -0
  18. package/.claude/skills/bmad-agent-ux-designer/bmad-skill-manifest.yaml +11 -0
  19. package/.claude/skills/bmad-brainstorming/SKILL.md +6 -0
  20. package/.claude/skills/bmad-brainstorming/brain-methods.csv +62 -0
  21. package/.claude/skills/bmad-brainstorming/steps/step-01-session-setup.md +214 -0
  22. package/.claude/skills/bmad-brainstorming/steps/step-01b-continue.md +124 -0
  23. package/.claude/skills/bmad-brainstorming/steps/step-02a-user-selected.md +229 -0
  24. package/.claude/skills/bmad-brainstorming/steps/step-02b-ai-recommended.md +239 -0
  25. package/.claude/skills/bmad-brainstorming/steps/step-02c-random-selection.md +211 -0
  26. package/.claude/skills/bmad-brainstorming/steps/step-02d-progressive-flow.md +266 -0
  27. package/.claude/skills/bmad-brainstorming/steps/step-03-technique-execution.md +401 -0
  28. package/.claude/skills/bmad-brainstorming/steps/step-04-idea-organization.md +305 -0
  29. package/.claude/skills/bmad-brainstorming/template.md +15 -0
  30. package/.claude/skills/bmad-brainstorming/workflow.md +53 -0
  31. package/.claude/skills/bmad-check-implementation-readiness/SKILL.md +6 -0
  32. package/.claude/skills/bmad-check-implementation-readiness/steps/step-01-document-discovery.md +179 -0
  33. package/.claude/skills/bmad-check-implementation-readiness/steps/step-02-prd-analysis.md +168 -0
  34. package/.claude/skills/bmad-check-implementation-readiness/steps/step-03-epic-coverage-validation.md +169 -0
  35. package/.claude/skills/bmad-check-implementation-readiness/steps/step-04-ux-alignment.md +129 -0
  36. package/.claude/skills/bmad-check-implementation-readiness/steps/step-05-epic-quality-review.md +241 -0
  37. package/.claude/skills/bmad-check-implementation-readiness/steps/step-06-final-assessment.md +126 -0
  38. package/.claude/skills/bmad-check-implementation-readiness/templates/readiness-report-template.md +4 -0
  39. package/.claude/skills/bmad-check-implementation-readiness/workflow.md +47 -0
  40. package/.claude/skills/bmad-checkpoint-preview/SKILL.md +29 -0
  41. package/.claude/skills/bmad-checkpoint-preview/generate-trail.md +38 -0
  42. package/.claude/skills/bmad-checkpoint-preview/step-01-orientation.md +105 -0
  43. package/.claude/skills/bmad-checkpoint-preview/step-02-walkthrough.md +89 -0
  44. package/.claude/skills/bmad-checkpoint-preview/step-03-detail-pass.md +106 -0
  45. package/.claude/skills/bmad-checkpoint-preview/step-04-testing.md +74 -0
  46. package/.claude/skills/bmad-checkpoint-preview/step-05-wrapup.md +24 -0
  47. package/.claude/skills/bmad-code-review/SKILL.md +6 -0
  48. package/.claude/skills/bmad-code-review/steps/step-01-gather-context.md +85 -0
  49. package/.claude/skills/bmad-code-review/steps/step-02-review.md +34 -0
  50. package/.claude/skills/bmad-code-review/steps/step-03-triage.md +49 -0
  51. package/.claude/skills/bmad-code-review/steps/step-04-present.md +129 -0
  52. package/.claude/skills/bmad-code-review/workflow.md +55 -0
  53. package/.claude/skills/bmad-correct-course/SKILL.md +6 -0
  54. package/.claude/skills/bmad-correct-course/checklist.md +288 -0
  55. package/.claude/skills/bmad-correct-course/workflow.md +267 -0
  56. package/.claude/skills/bmad-create-architecture/SKILL.md +6 -0
  57. package/.claude/skills/bmad-create-architecture/architecture-decision-template.md +12 -0
  58. package/.claude/skills/bmad-create-architecture/data/domain-complexity.csv +13 -0
  59. package/.claude/skills/bmad-create-architecture/data/project-types.csv +7 -0
  60. package/.claude/skills/bmad-create-architecture/steps/step-01-init.md +153 -0
  61. package/.claude/skills/bmad-create-architecture/steps/step-01b-continue.md +173 -0
  62. package/.claude/skills/bmad-create-architecture/steps/step-02-context.md +224 -0
  63. package/.claude/skills/bmad-create-architecture/steps/step-03-starter.md +329 -0
  64. package/.claude/skills/bmad-create-architecture/steps/step-04-decisions.md +318 -0
  65. package/.claude/skills/bmad-create-architecture/steps/step-05-patterns.md +359 -0
  66. package/.claude/skills/bmad-create-architecture/steps/step-06-structure.md +379 -0
  67. package/.claude/skills/bmad-create-architecture/steps/step-07-validation.md +359 -0
  68. package/.claude/skills/bmad-create-architecture/steps/step-08-complete.md +76 -0
  69. package/.claude/skills/bmad-create-architecture/workflow.md +32 -0
  70. package/.claude/skills/bmad-create-epics-and-stories/SKILL.md +6 -0
  71. package/.claude/skills/bmad-create-epics-and-stories/steps/step-01-validate-prerequisites.md +255 -0
  72. package/.claude/skills/bmad-create-epics-and-stories/steps/step-02-design-epics.md +212 -0
  73. package/.claude/skills/bmad-create-epics-and-stories/steps/step-03-create-stories.md +255 -0
  74. package/.claude/skills/bmad-create-epics-and-stories/steps/step-04-final-validation.md +131 -0
  75. package/.claude/skills/bmad-create-epics-and-stories/templates/epics-template.md +61 -0
  76. package/.claude/skills/bmad-create-epics-and-stories/workflow.md +51 -0
  77. package/.claude/skills/bmad-create-prd/SKILL.md +6 -0
  78. package/.claude/skills/bmad-create-prd/data/domain-complexity.csv +15 -0
  79. package/.claude/skills/bmad-create-prd/data/prd-purpose.md +197 -0
  80. package/.claude/skills/bmad-create-prd/data/project-types.csv +11 -0
  81. package/.claude/skills/bmad-create-prd/steps-c/step-01-init.md +178 -0
  82. package/.claude/skills/bmad-create-prd/steps-c/step-01b-continue.md +161 -0
  83. package/.claude/skills/bmad-create-prd/steps-c/step-02-discovery.md +208 -0
  84. package/.claude/skills/bmad-create-prd/steps-c/step-02b-vision.md +142 -0
  85. package/.claude/skills/bmad-create-prd/steps-c/step-02c-executive-summary.md +158 -0
  86. package/.claude/skills/bmad-create-prd/steps-c/step-03-success.md +214 -0
  87. package/.claude/skills/bmad-create-prd/steps-c/step-04-journeys.md +201 -0
  88. package/.claude/skills/bmad-create-prd/steps-c/step-05-domain.md +194 -0
  89. package/.claude/skills/bmad-create-prd/steps-c/step-06-innovation.md +211 -0
  90. package/.claude/skills/bmad-create-prd/steps-c/step-07-project-type.md +222 -0
  91. package/.claude/skills/bmad-create-prd/steps-c/step-08-scoping.md +216 -0
  92. package/.claude/skills/bmad-create-prd/steps-c/step-09-functional.md +219 -0
  93. package/.claude/skills/bmad-create-prd/steps-c/step-10-nonfunctional.md +230 -0
  94. package/.claude/skills/bmad-create-prd/steps-c/step-11-polish.md +221 -0
  95. package/.claude/skills/bmad-create-prd/steps-c/step-12-complete.md +115 -0
  96. package/.claude/skills/bmad-create-prd/templates/prd-template.md +10 -0
  97. package/.claude/skills/bmad-create-prd/workflow.md +61 -0
  98. package/.claude/skills/bmad-create-story/SKILL.md +6 -0
  99. package/.claude/skills/bmad-create-story/checklist.md +357 -0
  100. package/.claude/skills/bmad-create-story/discover-inputs.md +88 -0
  101. package/.claude/skills/bmad-create-story/template.md +49 -0
  102. package/.claude/skills/bmad-create-story/workflow.md +380 -0
  103. package/.claude/skills/bmad-create-ux-design/SKILL.md +6 -0
  104. package/.claude/skills/bmad-create-ux-design/steps/step-01-init.md +135 -0
  105. package/.claude/skills/bmad-create-ux-design/steps/step-01b-continue.md +127 -0
  106. package/.claude/skills/bmad-create-ux-design/steps/step-02-discovery.md +190 -0
  107. package/.claude/skills/bmad-create-ux-design/steps/step-03-core-experience.md +217 -0
  108. package/.claude/skills/bmad-create-ux-design/steps/step-04-emotional-response.md +220 -0
  109. package/.claude/skills/bmad-create-ux-design/steps/step-05-inspiration.md +235 -0
  110. package/.claude/skills/bmad-create-ux-design/steps/step-06-design-system.md +253 -0
  111. package/.claude/skills/bmad-create-ux-design/steps/step-07-defining-experience.md +255 -0
  112. package/.claude/skills/bmad-create-ux-design/steps/step-08-visual-foundation.md +225 -0
  113. package/.claude/skills/bmad-create-ux-design/steps/step-09-design-directions.md +225 -0
  114. package/.claude/skills/bmad-create-ux-design/steps/step-10-user-journeys.md +242 -0
  115. package/.claude/skills/bmad-create-ux-design/steps/step-11-component-strategy.md +249 -0
  116. package/.claude/skills/bmad-create-ux-design/steps/step-12-ux-patterns.md +238 -0
  117. package/.claude/skills/bmad-create-ux-design/steps/step-13-responsive-accessibility.md +265 -0
  118. package/.claude/skills/bmad-create-ux-design/steps/step-14-complete.md +171 -0
  119. package/.claude/skills/bmad-create-ux-design/ux-design-template.md +13 -0
  120. package/.claude/skills/bmad-create-ux-design/workflow.md +35 -0
  121. package/.claude/skills/bmad-dev-story/SKILL.md +6 -0
  122. package/.claude/skills/bmad-dev-story/checklist.md +80 -0
  123. package/.claude/skills/bmad-dev-story/workflow.md +450 -0
  124. package/.claude/skills/bmad-distillator/SKILL.md +177 -0
  125. package/.claude/skills/bmad-distillator/agents/distillate-compressor.md +116 -0
  126. package/.claude/skills/bmad-distillator/agents/round-trip-reconstructor.md +68 -0
  127. package/.claude/skills/bmad-distillator/resources/compression-rules.md +51 -0
  128. package/.claude/skills/bmad-distillator/resources/distillate-format-reference.md +227 -0
  129. package/.claude/skills/bmad-distillator/resources/splitting-strategy.md +78 -0
  130. package/.claude/skills/bmad-distillator/scripts/analyze_sources.py +300 -0
  131. package/.claude/skills/bmad-distillator/scripts/tests/test_analyze_sources.py +204 -0
  132. package/.claude/skills/bmad-document-project/SKILL.md +6 -0
  133. package/.claude/skills/bmad-document-project/checklist.md +245 -0
  134. package/.claude/skills/bmad-document-project/documentation-requirements.csv +12 -0
  135. package/.claude/skills/bmad-document-project/instructions.md +128 -0
  136. package/.claude/skills/bmad-document-project/templates/deep-dive-template.md +345 -0
  137. package/.claude/skills/bmad-document-project/templates/index-template.md +169 -0
  138. package/.claude/skills/bmad-document-project/templates/project-overview-template.md +103 -0
  139. package/.claude/skills/bmad-document-project/templates/project-scan-report-schema.json +160 -0
  140. package/.claude/skills/bmad-document-project/templates/source-tree-template.md +135 -0
  141. package/.claude/skills/bmad-document-project/workflow.md +25 -0
  142. package/.claude/skills/bmad-document-project/workflows/deep-dive-instructions.md +299 -0
  143. package/.claude/skills/bmad-document-project/workflows/deep-dive-workflow.md +34 -0
  144. package/.claude/skills/bmad-document-project/workflows/full-scan-instructions.md +1107 -0
  145. package/.claude/skills/bmad-document-project/workflows/full-scan-workflow.md +34 -0
  146. package/.claude/skills/bmad-domain-research/SKILL.md +6 -0
  147. package/.claude/skills/bmad-domain-research/domain-steps/step-01-init.md +137 -0
  148. package/.claude/skills/bmad-domain-research/domain-steps/step-02-domain-analysis.md +229 -0
  149. package/.claude/skills/bmad-domain-research/domain-steps/step-03-competitive-landscape.md +238 -0
  150. package/.claude/skills/bmad-domain-research/domain-steps/step-04-regulatory-focus.md +206 -0
  151. package/.claude/skills/bmad-domain-research/domain-steps/step-05-technical-trends.md +234 -0
  152. package/.claude/skills/bmad-domain-research/domain-steps/step-06-research-synthesis.md +444 -0
  153. package/.claude/skills/bmad-domain-research/research.template.md +29 -0
  154. package/.claude/skills/bmad-domain-research/workflow.md +51 -0
  155. package/.claude/skills/bmad-edit-prd/SKILL.md +6 -0
  156. package/.claude/skills/bmad-edit-prd/data/prd-purpose.md +197 -0
  157. package/.claude/skills/bmad-edit-prd/steps-e/step-e-01-discovery.md +242 -0
  158. package/.claude/skills/bmad-edit-prd/steps-e/step-e-01b-legacy-conversion.md +204 -0
  159. package/.claude/skills/bmad-edit-prd/steps-e/step-e-02-review.md +245 -0
  160. package/.claude/skills/bmad-edit-prd/steps-e/step-e-03-edit.md +250 -0
  161. package/.claude/skills/bmad-edit-prd/steps-e/step-e-04-complete.md +163 -0
  162. package/.claude/skills/bmad-edit-prd/workflow.md +62 -0
  163. package/.claude/skills/bmad-editorial-review-prose/SKILL.md +86 -0
  164. package/.claude/skills/bmad-editorial-review-structure/SKILL.md +179 -0
  165. package/.claude/skills/bmad-generate-project-context/SKILL.md +6 -0
  166. package/.claude/skills/bmad-generate-project-context/project-context-template.md +21 -0
  167. package/.claude/skills/bmad-generate-project-context/steps/step-01-discover.md +186 -0
  168. package/.claude/skills/bmad-generate-project-context/steps/step-02-generate.md +321 -0
  169. package/.claude/skills/bmad-generate-project-context/steps/step-03-complete.md +278 -0
  170. package/.claude/skills/bmad-generate-project-context/workflow.md +39 -0
  171. package/.claude/skills/bmad-help/SKILL.md +75 -0
  172. package/.claude/skills/bmad-index-docs/SKILL.md +66 -0
  173. package/.claude/skills/bmad-market-research/SKILL.md +6 -0
  174. package/.claude/skills/bmad-market-research/research.template.md +29 -0
  175. package/.claude/skills/bmad-market-research/steps/step-01-init.md +184 -0
  176. package/.claude/skills/bmad-market-research/steps/step-02-customer-behavior.md +239 -0
  177. package/.claude/skills/bmad-market-research/steps/step-03-customer-pain-points.md +251 -0
  178. package/.claude/skills/bmad-market-research/steps/step-04-customer-decisions.md +261 -0
  179. package/.claude/skills/bmad-market-research/steps/step-05-competitive-analysis.md +173 -0
  180. package/.claude/skills/bmad-market-research/steps/step-06-research-completion.md +478 -0
  181. package/.claude/skills/bmad-market-research/workflow.md +51 -0
  182. package/.claude/skills/bmad-party-mode/SKILL.md +125 -0
  183. package/.claude/skills/bmad-prfaq/SKILL.md +96 -0
  184. package/.claude/skills/bmad-prfaq/agents/artifact-analyzer.md +60 -0
  185. package/.claude/skills/bmad-prfaq/agents/web-researcher.md +49 -0
  186. package/.claude/skills/bmad-prfaq/assets/prfaq-template.md +62 -0
  187. package/.claude/skills/bmad-prfaq/bmad-manifest.json +16 -0
  188. package/.claude/skills/bmad-prfaq/references/customer-faq.md +55 -0
  189. package/.claude/skills/bmad-prfaq/references/internal-faq.md +51 -0
  190. package/.claude/skills/bmad-prfaq/references/press-release.md +60 -0
  191. package/.claude/skills/bmad-prfaq/references/verdict.md +79 -0
  192. package/.claude/skills/bmad-product-brief/SKILL.md +82 -0
  193. package/.claude/skills/bmad-product-brief/agents/artifact-analyzer.md +60 -0
  194. package/.claude/skills/bmad-product-brief/agents/opportunity-reviewer.md +44 -0
  195. package/.claude/skills/bmad-product-brief/agents/skeptic-reviewer.md +44 -0
  196. package/.claude/skills/bmad-product-brief/agents/web-researcher.md +49 -0
  197. package/.claude/skills/bmad-product-brief/bmad-manifest.json +17 -0
  198. package/.claude/skills/bmad-product-brief/prompts/contextual-discovery.md +57 -0
  199. package/.claude/skills/bmad-product-brief/prompts/draft-and-review.md +86 -0
  200. package/.claude/skills/bmad-product-brief/prompts/finalize.md +75 -0
  201. package/.claude/skills/bmad-product-brief/prompts/guided-elicitation.md +70 -0
  202. package/.claude/skills/bmad-product-brief/resources/brief-template.md +60 -0
  203. package/.claude/skills/bmad-qa-generate-e2e-tests/SKILL.md +6 -0
  204. package/.claude/skills/bmad-qa-generate-e2e-tests/checklist.md +33 -0
  205. package/.claude/skills/bmad-qa-generate-e2e-tests/workflow.md +136 -0
  206. package/.claude/skills/bmad-quick-dev/SKILL.md +6 -0
  207. package/.claude/skills/bmad-quick-dev/compile-epic-context.md +62 -0
  208. package/.claude/skills/bmad-quick-dev/spec-template.md +88 -0
  209. package/.claude/skills/bmad-quick-dev/step-01-clarify-and-route.md +91 -0
  210. package/.claude/skills/bmad-quick-dev/step-02-plan.md +47 -0
  211. package/.claude/skills/bmad-quick-dev/step-03-implement.md +39 -0
  212. package/.claude/skills/bmad-quick-dev/step-04-review.md +49 -0
  213. package/.claude/skills/bmad-quick-dev/step-05-present.md +63 -0
  214. package/.claude/skills/bmad-quick-dev/step-oneshot.md +61 -0
  215. package/.claude/skills/bmad-quick-dev/workflow.md +75 -0
  216. package/.claude/skills/bmad-retrospective/SKILL.md +6 -0
  217. package/.claude/skills/bmad-retrospective/workflow.md +1479 -0
  218. package/.claude/skills/bmad-review-adversarial-general/SKILL.md +37 -0
  219. package/.claude/skills/bmad-review-edge-case-hunter/SKILL.md +67 -0
  220. package/.claude/skills/bmad-shard-doc/SKILL.md +105 -0
  221. package/.claude/skills/bmad-sprint-planning/SKILL.md +6 -0
  222. package/.claude/skills/bmad-sprint-planning/checklist.md +33 -0
  223. package/.claude/skills/bmad-sprint-planning/sprint-status-template.yaml +56 -0
  224. package/.claude/skills/bmad-sprint-planning/workflow.md +263 -0
  225. package/.claude/skills/bmad-sprint-status/SKILL.md +6 -0
  226. package/.claude/skills/bmad-sprint-status/workflow.md +261 -0
  227. package/.claude/skills/bmad-technical-research/SKILL.md +6 -0
  228. package/.claude/skills/bmad-technical-research/research.template.md +29 -0
  229. package/.claude/skills/bmad-technical-research/technical-steps/step-01-init.md +137 -0
  230. package/.claude/skills/bmad-technical-research/technical-steps/step-02-technical-overview.md +239 -0
  231. package/.claude/skills/bmad-technical-research/technical-steps/step-03-integration-patterns.md +248 -0
  232. package/.claude/skills/bmad-technical-research/technical-steps/step-04-architectural-patterns.md +202 -0
  233. package/.claude/skills/bmad-technical-research/technical-steps/step-05-implementation-research.md +233 -0
  234. package/.claude/skills/bmad-technical-research/technical-steps/step-06-research-synthesis.md +487 -0
  235. package/.claude/skills/bmad-technical-research/workflow.md +52 -0
  236. package/.claude/skills/bmad-validate-prd/SKILL.md +6 -0
  237. package/.claude/skills/bmad-validate-prd/data/domain-complexity.csv +15 -0
  238. package/.claude/skills/bmad-validate-prd/data/prd-purpose.md +197 -0
  239. package/.claude/skills/bmad-validate-prd/data/project-types.csv +11 -0
  240. package/.claude/skills/bmad-validate-prd/steps-v/step-v-01-discovery.md +221 -0
  241. package/.claude/skills/bmad-validate-prd/steps-v/step-v-02-format-detection.md +188 -0
  242. package/.claude/skills/bmad-validate-prd/steps-v/step-v-02b-parity-check.md +206 -0
  243. package/.claude/skills/bmad-validate-prd/steps-v/step-v-03-density-validation.md +171 -0
  244. package/.claude/skills/bmad-validate-prd/steps-v/step-v-04-brief-coverage-validation.md +211 -0
  245. package/.claude/skills/bmad-validate-prd/steps-v/step-v-05-measurability-validation.md +225 -0
  246. package/.claude/skills/bmad-validate-prd/steps-v/step-v-06-traceability-validation.md +214 -0
  247. package/.claude/skills/bmad-validate-prd/steps-v/step-v-07-implementation-leakage-validation.md +202 -0
  248. package/.claude/skills/bmad-validate-prd/steps-v/step-v-08-domain-compliance-validation.md +240 -0
  249. package/.claude/skills/bmad-validate-prd/steps-v/step-v-09-project-type-validation.md +260 -0
  250. package/.claude/skills/bmad-validate-prd/steps-v/step-v-10-smart-validation.md +206 -0
  251. package/.claude/skills/bmad-validate-prd/steps-v/step-v-11-holistic-quality-validation.md +261 -0
  252. package/.claude/skills/bmad-validate-prd/steps-v/step-v-12-completeness-validation.md +239 -0
  253. package/.claude/skills/bmad-validate-prd/steps-v/step-v-13-report-complete.md +229 -0
  254. package/.claude/skills/bmad-validate-prd/workflow.md +61 -0
  255. package/.claude/skills/gitnexus/gitnexus-cli/SKILL.md +82 -0
  256. package/.claude/skills/gitnexus/gitnexus-debugging/SKILL.md +89 -0
  257. package/.claude/skills/gitnexus/gitnexus-exploring/SKILL.md +78 -0
  258. package/.claude/skills/gitnexus/gitnexus-guide/SKILL.md +64 -0
  259. package/.claude/skills/gitnexus/gitnexus-impact-analysis/SKILL.md +97 -0
  260. package/.claude/skills/gitnexus/gitnexus-refactoring/SKILL.md +121 -0
  261. package/.claude/skills/openspec-apply-change/SKILL.md +156 -0
  262. package/.claude/skills/openspec-archive-change/SKILL.md +114 -0
  263. package/.claude/skills/openspec-explore/SKILL.md +288 -0
  264. package/.claude/skills/openspec-propose/SKILL.md +110 -0
  265. package/.claude/skills/vsaf-build/SKILL.md +52 -0
  266. package/.claude/skills/vsaf-doc/SKILL.md +66 -0
  267. package/.claude/skills/vsaf-memory-protocol.md +51 -0
  268. package/.claude/skills/vsaf-onboard/SKILL.md +55 -0
  269. package/.claude/skills/vsaf-plan/SKILL.md +68 -0
  270. package/.claude/skills/vsaf-ship/SKILL.md +76 -0
  271. package/.claude/skills/vsaf-test/SKILL.md +70 -0
  272. package/README.md +124 -0
  273. package/assets/templates/.claude/settings.json +82 -0
  274. package/assets/templates/CLAUDE.md +248 -0
  275. package/assets/templates/Makefile +77 -0
  276. package/assets/templates/scripts/session-end-check.sh +28 -0
  277. package/bin/vsaf.js +68 -0
  278. package/package.json +22 -0
  279. package/src/global.js +98 -0
  280. package/src/project.js +94 -0
  281. package/src/status.js +51 -0
  282. package/src/utils.js +42 -0
@@ -0,0 +1,288 @@
1
+ ---
2
+ name: openspec-explore
3
+ description: Enter explore mode - a thinking partner for exploring ideas, investigating problems, and clarifying requirements. Use when the user wants to think through something before or during a change.
4
+ license: MIT
5
+ compatibility: Requires openspec CLI.
6
+ metadata:
7
+ author: openspec
8
+ version: "1.0"
9
+ generatedBy: "1.3.0"
10
+ ---
11
+
12
+ Enter explore mode. Think deeply. Visualize freely. Follow the conversation wherever it goes.
13
+
14
+ **IMPORTANT: Explore mode is for thinking, not implementing.** You may read files, search code, and investigate the codebase, but you must NEVER write code or implement features. If the user asks you to implement something, remind them to exit explore mode first and create a change proposal. You MAY create OpenSpec artifacts (proposals, designs, specs) if the user asks—that's capturing thinking, not implementing.
15
+
16
+ **This is a stance, not a workflow.** There are no fixed steps, no required sequence, no mandatory outputs. You're a thinking partner helping the user explore.
17
+
18
+ ---
19
+
20
+ ## The Stance
21
+
22
+ - **Curious, not prescriptive** - Ask questions that emerge naturally, don't follow a script
23
+ - **Open threads, not interrogations** - Surface multiple interesting directions and let the user follow what resonates. Don't funnel them through a single path of questions.
24
+ - **Visual** - Use ASCII diagrams liberally when they'd help clarify thinking
25
+ - **Adaptive** - Follow interesting threads, pivot when new information emerges
26
+ - **Patient** - Don't rush to conclusions, let the shape of the problem emerge
27
+ - **Grounded** - Explore the actual codebase when relevant, don't just theorize
28
+
29
+ ---
30
+
31
+ ## What You Might Do
32
+
33
+ Depending on what the user brings, you might:
34
+
35
+ **Explore the problem space**
36
+ - Ask clarifying questions that emerge from what they said
37
+ - Challenge assumptions
38
+ - Reframe the problem
39
+ - Find analogies
40
+
41
+ **Investigate the codebase**
42
+ - Map existing architecture relevant to the discussion
43
+ - Find integration points
44
+ - Identify patterns already in use
45
+ - Surface hidden complexity
46
+
47
+ **Compare options**
48
+ - Brainstorm multiple approaches
49
+ - Build comparison tables
50
+ - Sketch tradeoffs
51
+ - Recommend a path (if asked)
52
+
53
+ **Visualize**
54
+ ```
55
+ ┌─────────────────────────────────────────┐
56
+ │ Use ASCII diagrams liberally │
57
+ ├─────────────────────────────────────────┤
58
+ │ │
59
+ │ ┌────────┐ ┌────────┐ │
60
+ │ │ State │────────▶│ State │ │
61
+ │ │ A │ │ B │ │
62
+ │ └────────┘ └────────┘ │
63
+ │ │
64
+ │ System diagrams, state machines, │
65
+ │ data flows, architecture sketches, │
66
+ │ dependency graphs, comparison tables │
67
+ │ │
68
+ └─────────────────────────────────────────┘
69
+ ```
70
+
71
+ **Surface risks and unknowns**
72
+ - Identify what could go wrong
73
+ - Find gaps in understanding
74
+ - Suggest spikes or investigations
75
+
76
+ ---
77
+
78
+ ## OpenSpec Awareness
79
+
80
+ You have full context of the OpenSpec system. Use it naturally, don't force it.
81
+
82
+ ### Check for context
83
+
84
+ At the start, quickly check what exists:
85
+ ```bash
86
+ openspec list --json
87
+ ```
88
+
89
+ This tells you:
90
+ - If there are active changes
91
+ - Their names, schemas, and status
92
+ - What the user might be working on
93
+
94
+ ### When no change exists
95
+
96
+ Think freely. When insights crystallize, you might offer:
97
+
98
+ - "This feels solid enough to start a change. Want me to create a proposal?"
99
+ - Or keep exploring - no pressure to formalize
100
+
101
+ ### When a change exists
102
+
103
+ If the user mentions a change or you detect one is relevant:
104
+
105
+ 1. **Read existing artifacts for context**
106
+ - `openspec/changes/<name>/proposal.md`
107
+ - `openspec/changes/<name>/design.md`
108
+ - `openspec/changes/<name>/tasks.md`
109
+ - etc.
110
+
111
+ 2. **Reference them naturally in conversation**
112
+ - "Your design mentions using Redis, but we just realized SQLite fits better..."
113
+ - "The proposal scopes this to premium users, but we're now thinking everyone..."
114
+
115
+ 3. **Offer to capture when decisions are made**
116
+
117
+ | Insight Type | Where to Capture |
118
+ |----------------------------|--------------------------------|
119
+ | New requirement discovered | `specs/<capability>/spec.md` |
120
+ | Requirement changed | `specs/<capability>/spec.md` |
121
+ | Design decision made | `design.md` |
122
+ | Scope changed | `proposal.md` |
123
+ | New work identified | `tasks.md` |
124
+ | Assumption invalidated | Relevant artifact |
125
+
126
+ Example offers:
127
+ - "That's a design decision. Capture it in design.md?"
128
+ - "This is a new requirement. Add it to specs?"
129
+ - "This changes scope. Update the proposal?"
130
+
131
+ 4. **The user decides** - Offer and move on. Don't pressure. Don't auto-capture.
132
+
133
+ ---
134
+
135
+ ## What You Don't Have To Do
136
+
137
+ - Follow a script
138
+ - Ask the same questions every time
139
+ - Produce a specific artifact
140
+ - Reach a conclusion
141
+ - Stay on topic if a tangent is valuable
142
+ - Be brief (this is thinking time)
143
+
144
+ ---
145
+
146
+ ## Handling Different Entry Points
147
+
148
+ **User brings a vague idea:**
149
+ ```
150
+ User: I'm thinking about adding real-time collaboration
151
+
152
+ You: Real-time collab is a big space. Let me think about this...
153
+
154
+ COLLABORATION SPECTRUM
155
+ ════════════════════════════════════════════
156
+
157
+ Awareness Coordination Sync
158
+ │ │ │
159
+ ▼ ▼ ▼
160
+ ┌────────┐ ┌────────┐ ┌────────┐
161
+ │Presence│ │Cursors │ │ CRDT │
162
+ │ "3 │ │ Multi │ │Conflict│
163
+ │online" │ │ select │ │ free │
164
+ └────────┘ └────────┘ └────────┘
165
+ │ │ │
166
+ trivial moderate complex
167
+
168
+ Where's your head at?
169
+ ```
170
+
171
+ **User brings a specific problem:**
172
+ ```
173
+ User: The auth system is a mess
174
+
175
+ You: [reads codebase]
176
+
177
+ ┌─────────────────────────────────────────────┐
178
+ │ CURRENT AUTH FLOW │
179
+ └─────────────────────────────────────────────┘
180
+
181
+ ┌─────────────┼─────────────┐
182
+ ▼ ▼ ▼
183
+ ┌─────────┐ ┌─────────┐ ┌─────────┐
184
+ │ Google │ │ GitHub │ │ Email │
185
+ │ OAuth │ │ OAuth │ │ Magic │
186
+ └────┬────┘ └────┬────┘ └────┬────┘
187
+ │ │ │
188
+ └─────────────┼─────────────┘
189
+
190
+ ┌───────────┐
191
+ │ Session │
192
+ └─────┬─────┘
193
+
194
+
195
+ ┌───────────┐
196
+ │ Perms │
197
+ └───────────┘
198
+
199
+ I see three tangles. Which one's burning?
200
+ ```
201
+
202
+ **User is stuck mid-implementation:**
203
+ ```
204
+ User: /opsx:explore add-auth-system
205
+ The OAuth integration is more complex than expected
206
+
207
+ You: [reads change artifacts]
208
+
209
+ You're on task 4: "Implement OAuth flow"
210
+
211
+ Let me trace what's involved...
212
+
213
+ [draws diagram, explores options, suggests paths]
214
+
215
+ Want to update the design to reflect this?
216
+ Or add a spike task to investigate?
217
+ ```
218
+
219
+ **User wants to compare options:**
220
+ ```
221
+ User: Should we use Postgres or SQLite?
222
+
223
+ You: Generic answer is boring. What's the context?
224
+
225
+ User: A CLI tool that tracks local dev environments
226
+
227
+ You: That changes everything.
228
+
229
+ ┌─────────────────────────────────────────────────┐
230
+ │ CLI TOOL DATA STORAGE │
231
+ └─────────────────────────────────────────────────┘
232
+
233
+ Key constraints:
234
+ • No daemon running
235
+ • Must work offline
236
+ • Single user
237
+
238
+ SQLite Postgres
239
+ Deployment embedded ✓ needs server ✗
240
+ Offline yes ✓ no ✗
241
+ Single file yes ✓ no ✗
242
+
243
+ SQLite. Not even close.
244
+
245
+ Unless... is there a sync component?
246
+ ```
247
+
248
+ ---
249
+
250
+ ## Ending Discovery
251
+
252
+ There's no required ending. Discovery might:
253
+
254
+ - **Flow into a proposal**: "Ready to start? I can create a change proposal."
255
+ - **Result in artifact updates**: "Updated design.md with these decisions"
256
+ - **Just provide clarity**: User has what they need, moves on
257
+ - **Continue later**: "We can pick this up anytime"
258
+
259
+ When it feels like things are crystallizing, you might summarize:
260
+
261
+ ```
262
+ ## What We Figured Out
263
+
264
+ **The problem**: [crystallized understanding]
265
+
266
+ **The approach**: [if one emerged]
267
+
268
+ **Open questions**: [if any remain]
269
+
270
+ **Next steps** (if ready):
271
+ - Create a change proposal
272
+ - Keep exploring: just keep talking
273
+ ```
274
+
275
+ But this summary is optional. Sometimes the thinking IS the value.
276
+
277
+ ---
278
+
279
+ ## Guardrails
280
+
281
+ - **Don't implement** - Never write code or implement features. Creating OpenSpec artifacts is fine, writing application code is not.
282
+ - **Don't fake understanding** - If something is unclear, dig deeper
283
+ - **Don't rush** - Discovery is thinking time, not task time
284
+ - **Don't force structure** - Let patterns emerge naturally
285
+ - **Don't auto-capture** - Offer to save insights, don't just do it
286
+ - **Do visualize** - A good diagram is worth many paragraphs
287
+ - **Do explore the codebase** - Ground discussions in reality
288
+ - **Do question assumptions** - Including the user's and your own
@@ -0,0 +1,110 @@
1
+ ---
2
+ name: openspec-propose
3
+ description: Propose a new change with all artifacts generated in one step. Use when the user wants to quickly describe what they want to build and get a complete proposal with design, specs, and tasks ready for implementation.
4
+ license: MIT
5
+ compatibility: Requires openspec CLI.
6
+ metadata:
7
+ author: openspec
8
+ version: "1.0"
9
+ generatedBy: "1.3.0"
10
+ ---
11
+
12
+ Propose a new change - create the change and generate all artifacts in one step.
13
+
14
+ I'll create a change with artifacts:
15
+ - proposal.md (what & why)
16
+ - design.md (how)
17
+ - tasks.md (implementation steps)
18
+
19
+ When ready to implement, run /opsx:apply
20
+
21
+ ---
22
+
23
+ **Input**: The user's request should include a change name (kebab-case) OR a description of what they want to build.
24
+
25
+ **Steps**
26
+
27
+ 1. **If no clear input provided, ask what they want to build**
28
+
29
+ Use the **AskUserQuestion tool** (open-ended, no preset options) to ask:
30
+ > "What change do you want to work on? Describe what you want to build or fix."
31
+
32
+ From their description, derive a kebab-case name (e.g., "add user authentication" → `add-user-auth`).
33
+
34
+ **IMPORTANT**: Do NOT proceed without understanding what the user wants to build.
35
+
36
+ 2. **Create the change directory**
37
+ ```bash
38
+ openspec new change "<name>"
39
+ ```
40
+ This creates a scaffolded change at `openspec/changes/<name>/` with `.openspec.yaml`.
41
+
42
+ 3. **Get the artifact build order**
43
+ ```bash
44
+ openspec status --change "<name>" --json
45
+ ```
46
+ Parse the JSON to get:
47
+ - `applyRequires`: array of artifact IDs needed before implementation (e.g., `["tasks"]`)
48
+ - `artifacts`: list of all artifacts with their status and dependencies
49
+
50
+ 4. **Create artifacts in sequence until apply-ready**
51
+
52
+ Use the **TodoWrite tool** to track progress through the artifacts.
53
+
54
+ Loop through artifacts in dependency order (artifacts with no pending dependencies first):
55
+
56
+ a. **For each artifact that is `ready` (dependencies satisfied)**:
57
+ - Get instructions:
58
+ ```bash
59
+ openspec instructions <artifact-id> --change "<name>" --json
60
+ ```
61
+ - The instructions JSON includes:
62
+ - `context`: Project background (constraints for you - do NOT include in output)
63
+ - `rules`: Artifact-specific rules (constraints for you - do NOT include in output)
64
+ - `template`: The structure to use for your output file
65
+ - `instruction`: Schema-specific guidance for this artifact type
66
+ - `outputPath`: Where to write the artifact
67
+ - `dependencies`: Completed artifacts to read for context
68
+ - Read any completed dependency files for context
69
+ - Create the artifact file using `template` as the structure
70
+ - Apply `context` and `rules` as constraints - but do NOT copy them into the file
71
+ - Show brief progress: "Created <artifact-id>"
72
+
73
+ b. **Continue until all `applyRequires` artifacts are complete**
74
+ - After creating each artifact, re-run `openspec status --change "<name>" --json`
75
+ - Check if every artifact ID in `applyRequires` has `status: "done"` in the artifacts array
76
+ - Stop when all `applyRequires` artifacts are done
77
+
78
+ c. **If an artifact requires user input** (unclear context):
79
+ - Use **AskUserQuestion tool** to clarify
80
+ - Then continue with creation
81
+
82
+ 5. **Show final status**
83
+ ```bash
84
+ openspec status --change "<name>"
85
+ ```
86
+
87
+ **Output**
88
+
89
+ After completing all artifacts, summarize:
90
+ - Change name and location
91
+ - List of artifacts created with brief descriptions
92
+ - What's ready: "All artifacts created! Ready for implementation."
93
+ - Prompt: "Run `/opsx:apply` or ask me to implement to start working on the tasks."
94
+
95
+ **Artifact Creation Guidelines**
96
+
97
+ - Follow the `instruction` field from `openspec instructions` for each artifact type
98
+ - The schema defines what each artifact should contain - follow it
99
+ - Read dependency artifacts for context before creating new ones
100
+ - Use `template` as the structure for your output file - fill in its sections
101
+ - **IMPORTANT**: `context` and `rules` are constraints for YOU, not content for the file
102
+ - Do NOT copy `<context>`, `<rules>`, `<project_context>` blocks into the artifact
103
+ - These guide what you write, but should never appear in the output
104
+
105
+ **Guardrails**
106
+ - Create ALL artifacts needed for implementation (as defined by schema's `apply.requires`)
107
+ - Always read dependency artifacts before creating a new one
108
+ - If context is critically unclear, ask the user - but prefer making reasonable decisions to keep momentum
109
+ - If a change with that name already exists, ask if user wants to continue it or create a new one
110
+ - Verify each artifact file exists after writing before proceeding to next
@@ -0,0 +1,52 @@
1
+ ---
2
+ name: vsaf-build
3
+ description: Implement code theo tài liệu spec đã có. Dùng sau /vsaf-doc, khi PRD và spec đã được approve. Tự động đọc memory trước khi code.
4
+ ---
5
+
6
+ # VSAF Build
7
+
8
+ ## Mục tiêu
9
+ Implement code đúng theo spec, từng task một, với TDD — đảm bảo mỗi commit có tests pass.
10
+
11
+ ## Điều kiện tiên quyết
12
+ - Đã chạy `/vsaf-doc` và có file spec trong `openspec/`
13
+ - User đã approve plan
14
+
15
+ ## Các bước thực hiện
16
+
17
+ ### Bước 1 — Đọc memory tự động trước khi code (bắt buộc)
18
+ Thực hiện AUTO-READ từ `.claude/skills/vsaf-memory-protocol.md` với keyword là tên module/feature sắp implement.
19
+
20
+ ### Bước 2 — Đọc spec
21
+ - Đọc file spec trong `openspec/` liên quan đến feature hiện tại
22
+ - Xác nhận task list và verification steps với user trước khi bắt đầu
23
+
24
+ ### Bước 3 — Implement từng task (TDD)
25
+ Với mỗi task trong spec:
26
+ 1. **RED**: Viết test trước, chạy test → phải fail
27
+ 2. **GREEN**: Viết code tối thiểu để test pass
28
+ 3. **REFACTOR**: Clean up code, giữ test vẫn pass
29
+ 4. Chạy `mcp__gitnexus__detect_changes` để verify chỉ đúng files thay đổi
30
+ 5. Chạy `/opsx:verify` để check task đúng spec
31
+ 6. Commit: `git commit -m "feat: <task description>"`
32
+
33
+ ### Bước 4 — ECC (tự động)
34
+ - ECC hooks chạy tự động — không cần gọi thủ công
35
+ - Nếu bị block: đọc message, không dùng `--no-verify` để bypass
36
+
37
+ ### Bước 5 — Xử lý khi fail
38
+ - Fail 1-2 lần: thử approach khác
39
+ - Fail 3 lần cùng 1 task: DỪNG, báo user, quay lại `/vsaf-plan`
40
+
41
+ ### Bước 6 — Output sau mỗi task
42
+ ```
43
+ ✓ Task [N]: [tên task]
44
+ - Files changed: [danh sách]
45
+ - Tests: [X passed]
46
+ - Commit: [hash]
47
+ ```
48
+
49
+ ## Lưu ý
50
+ - 1 commit = 1 task, không gộp nhiều tasks vào 1 commit
51
+ - Không sửa file ngoài scope của task hiện tại
52
+ - Sau khi hoàn thành tất cả tasks: chạy `/vsaf-test` để viết tài liệu test
@@ -0,0 +1,66 @@
1
+ ---
2
+ name: vsaf-doc
3
+ description: Viết tài liệu plan cho feature đã được phân tích. Dùng sau /vsaf-plan, khi đã có scope và approach rõ ràng, cần chuyển thành tài liệu có cấu trúc với task list atomic.
4
+ ---
5
+
6
+ # VSAF Doc
7
+
8
+ ## Mục tiêu
9
+ Chuyển kết quả plan thành tài liệu chính thức: PRD, spec proposal, và task list có verification step.
10
+
11
+ ## Điều kiện tiên quyết
12
+ Phải đã chạy `/vsaf-plan` và có output trước khi chạy skill này.
13
+
14
+ ## Các bước thực hiện
15
+
16
+ ### Bước 0 — Đọc memory tự động
17
+ Thực hiện AUTO-READ từ `.claude/skills/vsaf-memory-protocol.md` với keyword từ feature hiện tại.
18
+
19
+ ### Bước 1 — Sinh PRD (BMAD pm)
20
+ - Dùng skill `bmad-agent-pm` để tạo PRD từ kết quả plan
21
+ - PRD phải bao gồm: FRs, NFRs, Epics, User Stories
22
+ - Lưu vào `docs/` theo cấu trúc project
23
+
24
+ ### Bước 2 — Tạo spec proposal (OpenSpec)
25
+ - Dùng skill `opsx:propose` với tên feature
26
+ - OpenSpec sẽ tạo task list atomic (mỗi task 2-5 phút)
27
+ - Mỗi task PHẢI có verification step rõ ràng
28
+ - Lưu vào `openspec/`
29
+
30
+ ### Bước 3 — Fast-forward docs (OpenSpec)
31
+ - Dùng skill `opsx:explore` để sync tất cả docs liên quan
32
+ - Đảm bảo không có inconsistency giữa PRD và spec
33
+
34
+ ### Bước 4 — Chi tiết hoá task list (Superpowers)
35
+ - Dùng skill `superpowers:writing-plans` để review và làm rõ task list
36
+ - Kiểm tra: mỗi task có đủ context để implement không?
37
+ - Kiểm tra: verification step có đo lường được không?
38
+
39
+ ### Bước 5 — Lưu architecture decision (MemPalace)
40
+ - Gọi `mcp__mempalace__mempalace_add_drawer` để lưu decision quan trọng
41
+ - Nội dung: approach được chọn, lý do, alternatives đã bỏ qua
42
+
43
+ ### Bước 6 — Output cho user
44
+ Thông báo các file đã tạo:
45
+
46
+ ```
47
+ ## Tài liệu đã tạo
48
+
49
+ ### PRD
50
+ - docs/[feature]-prd.md
51
+
52
+ ### Spec
53
+ - openspec/[feature]-spec.md
54
+ - [X] tasks, mỗi task có verification step
55
+
56
+ ### Architecture Decision
57
+ - Đã lưu vào MemPalace
58
+
59
+ ## Next step
60
+ Chạy /vsaf-build để bắt đầu implement
61
+ ```
62
+
63
+ ## Lưu ý
64
+ - Không bắt đầu code trong bước này
65
+ - Nếu task list quá dài (>10 tasks): đề nghị split thành nhiều PRs
66
+ - Commit docs trước khi chuyển sang build: `git commit -m "spec: <feature>"`
@@ -0,0 +1,51 @@
1
+ # VSAF Memory Protocol
2
+
3
+ Đây là protocol chung được tất cả vsaf skills sử dụng.
4
+ Thực hiện tự động — không cần user nhắc.
5
+
6
+ ---
7
+
8
+ ## AUTO-READ (thực hiện ở đầu mỗi skill)
9
+
10
+ Thực hiện tuần tự, không bỏ qua:
11
+
12
+ 1. **claude-mem** — kiểm tra session context đã sẵn sàng:
13
+ - Nếu có `$ARGUMENTS`: search claude-mem với keyword từ arguments
14
+ - Dùng `mcp__plugin_claude-mem_mcp-search__search` nếu có thể
15
+
16
+ 2. **MemPalace — search theo topic**:
17
+ - Gọi `mcp__mempalace__mempalace_search` với keyword chính từ task/feature
18
+ - Gọi `mcp__mempalace__mempalace_search` với tên module/domain liên quan
19
+ - Gọi `mcp__mempalace__mempalace_search` với "pattern" hoặc "decision" nếu cần context rộng hơn
20
+
21
+ 3. **Áp dụng kết quả**:
22
+ - Nếu tìm thấy relevant memories: tóm tắt ngắn gọn trước khi bắt đầu ("Từ memory: team đã dùng pattern X, tránh Y")
23
+ - Nếu không tìm thấy: tiếp tục bình thường, không báo lỗi
24
+
25
+ ---
26
+
27
+ ## AUTO-WRITE (thực hiện ở cuối vsaf-ship và vsaf-doc)
28
+
29
+ Thực hiện tuần tự sau khi task hoàn tất:
30
+
31
+ 1. **Diary** — ghi tóm tắt session:
32
+ - Gọi `mcp__mempalace__mempalace_diary_write`
33
+ - Nội dung: feature gì, approach nào, kết quả ra sao
34
+
35
+ 2. **Decisions** — lưu từng quyết định quan trọng:
36
+ - Với mỗi decision không hiển nhiên (pattern mới, workaround, trade-off):
37
+ - Gọi `mcp__mempalace__mempalace_add_drawer`
38
+ - Format: "Quyết định: [X]. Lý do: [Y]. Alternatives bỏ qua: [Z]"
39
+
40
+ 3. **Reasoning chain** — capture knowledge graph:
41
+ - Gọi `mcp__mempalace__mempalace_kg_add` để lưu relationships giữa các concepts
42
+ - Ưu tiên: gotchas phát hiện khi implement, dependencies ẩn, edge cases thực tế
43
+
44
+ ---
45
+
46
+ ## Nguyên tắc
47
+
48
+ - **Đọc trước, không đoán** — dù đã biết domain, vẫn phải check memory trước
49
+ - **Ghi decisions, không ghi code** — code ở trong repo, memory lưu lý do và context
50
+ - **Không báo user** khi memory trống — tiếp tục bình thường
51
+ - **Không chờ user confirm** để đọc/ghi memory — làm tự động
@@ -0,0 +1,55 @@
1
+ ---
2
+ name: vsaf-onboard
3
+ description: Hiểu toàn bộ context dự án mới. Dùng khi lần đầu tiếp nhận project, cần nắm kiến trúc, decisions cũ, và codebase trước khi làm bất cứ điều gì.
4
+ ---
5
+
6
+ # VSAF Onboard
7
+
8
+ ## Mục tiêu
9
+ Xây dựng full mental model về dự án trước khi chạm vào bất kỳ code nào.
10
+
11
+ ## Các bước thực hiện
12
+
13
+ ### Bước 0 — Đọc memory tự động
14
+ Thực hiện AUTO-READ từ `.claude/skills/vsaf-memory-protocol.md` với keyword "architecture".
15
+
16
+ ### Bước 1 — Kiến trúc tổng thể (Graphify)
17
+ - Đọc file `graphify-out/GRAPH_REPORT.md` nếu đã tồn tại
18
+ - Nếu chưa có: thông báo user chạy `/graphify .` để build graph trước
19
+ - Tóm tắt: các module chính, dependencies, entry points
20
+
21
+ ### Bước 2 — Code intelligence (GitNexus)
22
+ - Dùng `mcp__gitnexus__context` để lấy codebase overview
23
+ - Dùng `mcp__gitnexus__group_list` để xem các functional clusters
24
+ - Tóm tắt: execution flows quan trọng, symbols có nhiều dependencies nhất
25
+
26
+ ### Bước 3 — Decisions cũ (MemPalace)
27
+ - Gọi `mcp__mempalace__mempalace_search` với query "architecture"
28
+ - Gọi `mcp__mempalace__mempalace_search` với query "decision"
29
+ - Gọi `mcp__mempalace__mempalace_search` với query "pattern"
30
+ - Tóm tắt: các quyết định kiến trúc quan trọng team đã đưa ra
31
+
32
+ ### Bước 4 — Output cho user
33
+ Trình bày tóm tắt theo format:
34
+
35
+ ```
36
+ ## Project Overview
37
+ [Mô tả ngắn về dự án]
38
+
39
+ ## Kiến trúc
40
+ [Các layer/module chính và quan hệ]
41
+
42
+ ## Patterns đang dùng
43
+ [Tech stack, design patterns, conventions]
44
+
45
+ ## Decisions quan trọng
46
+ [Những gì team đã quyết định và lý do]
47
+
48
+ ## Cần chú ý
49
+ [Risk areas, legacy code, known issues]
50
+ ```
51
+
52
+ ## Lưu ý
53
+ - KHÔNG sửa bất kỳ file nào trong bước này
54
+ - Nếu bộ nhớ MemPalace trống: thông báo user chạy `mempalace mine` để populate
55
+ - Sau khi hoàn thành: gợi ý user dùng `/vsaf-plan <feature>` để bắt đầu task
@@ -0,0 +1,68 @@
1
+ ---
2
+ name: vsaf-plan
3
+ description: Lên plan cho 1 feature/task mới. Dùng khi nhận được yêu cầu cần phân tích scope, impact, và chiến lược tiếp cận. Ví dụ: /vsaf-plan tạo module quản lý user
4
+ ---
5
+
6
+ # VSAF Plan
7
+
8
+ ## Mục tiêu
9
+ Hiểu đầy đủ yêu cầu, phân tích impact, và xác định chiến lược implement trước khi viết bất kỳ dòng code nào.
10
+
11
+ ## Input
12
+ `$ARGUMENTS` — mô tả feature/task cần làm (ví dụ: "tạo module quản lý dashboard")
13
+
14
+ ## Các bước thực hiện
15
+
16
+ ### Bước 1 — Đọc memory tự động (bắt buộc)
17
+ Thực hiện AUTO-READ từ `.claude/skills/vsaf-memory-protocol.md` với keyword từ `$ARGUMENTS`.
18
+
19
+ ### Bước 2 — Clarify scope (BMAD analyst)
20
+ - Dùng skill `bmad-agent-analyst` để phân tích yêu cầu
21
+ - Xác định: FRs, NFRs, edge cases, assumptions, out-of-scope
22
+ - DỪNG và hỏi user nếu còn điểm chưa rõ
23
+
24
+ ### Bước 3 — Impact analysis (GitNexus)
25
+ - Dùng `mcp__gitnexus__impact` với target là module/symbol liên quan
26
+ - Dùng `mcp__gitnexus__query` để tìm code liên quan
27
+ - Báo cáo blast radius: bao nhiêu module bị ảnh hưởng, risk level
28
+
29
+ ### Bước 4 — Trace dependencies (Graphify)
30
+ - Nếu cần trace path giữa 2 services: dùng `/graphify path ServiceA ServiceB`
31
+ - Xác định: integration points, shared dependencies
32
+
33
+ ### Bước 5 — Architecture decision (BMAD architect)
34
+ - Dùng skill `bmad-agent-architect` để đề xuất architecture approach
35
+ - So sánh alternatives, chọn approach phù hợp nhất
36
+
37
+ ### Bước 6 — Brainstorm (Superpowers)
38
+ - Dùng skill `superpowers:brainstorming` để explore alternatives
39
+ - Đặt câu hỏi Socratic: "What if...", "What could go wrong..."
40
+
41
+ ### Bước 7 — Output cho user
42
+ Trình bày kết quả theo format:
43
+
44
+ ```
45
+ ## Feature: [tên feature]
46
+
47
+ ## Scope
48
+ - In: [những gì sẽ làm]
49
+ - Out: [những gì không làm]
50
+
51
+ ## Impact Analysis
52
+ - Modules bị ảnh hưởng: [danh sách]
53
+ - Risk level: [LOW/MEDIUM/HIGH]
54
+ - Breaking changes: [có/không, chi tiết]
55
+
56
+ ## Approach được chọn
57
+ [Mô tả architecture approach]
58
+
59
+ ## Alternatives đã xem xét
60
+ [Tại sao không chọn]
61
+
62
+ ## Next step
63
+ Chạy /vsaf-doc để viết tài liệu plan
64
+ ```
65
+
66
+ ## Lưu ý
67
+ - Nếu Impact > 3 modules: cảnh báo user, đề nghị split thành nhiều PRs
68
+ - Nếu risk level HIGH/CRITICAL: DỪNG, báo user trước khi tiếp tục