@vpxa/aikit 0.1.65 → 0.1.66

package/scaffold/general/skills/docs/references/project-knowledge-workflow.md

@@ -1,80 +1,80 @@
-# Project Knowledge — Workflow
-
-Detailed workflow for acquiring and documenting project knowledge into `docs/architecture/`.
-
-## Four-Phase Workflow
-
-```
-- [ ] Phase 1: Scan with AI Kit tools, read intent documents
-- [ ] Phase 2: Investigate each documentation area
-- [ ] Phase 3: Populate all seven docs in docs/architecture/
-- [ ] Phase 4: Validate docs, present findings, resolve all [ASK USER] items
-```
-
-### Phase 1: Scan and Read Intent
-
-```
-onboard({ path: "." })                           # Full codebase scan
-produce_knowledge({ path: "." })                  # Comprehensive analysis
-analyze_structure({ path: "." })                  # Project layout, packages, layers
-analyze_dependencies({ path: "." })               # All dependencies + import graph
-```
-
-Then read `README`, `PRD`, `TRD`, `ROADMAP`, `SPEC`, `DESIGN` files if they exist.
-Summarise the stated project intent before reading any source code.
-
-### Phase 2: Investigate
-
-Use Phase 1 tool outputs to answer questions for each of the seven documents. Run additional targeted tools:
-
-| Document | Investigation Tools |
-|----------|-------------------|
-| stack.md | `analyze_dependencies` → manifests, frameworks; `analyze_structure` → runtime signals |
-| structure.md | `analyze_structure` → file tree, packages; `analyze_entry_points` → entry points, key files |
-| design.md | `analyze_structure` → layers; `analyze_patterns` → design patterns; `analyze_diagram` → component diagrams |
-| conventions.md | `analyze_patterns` → naming, formatting; `search("conventions")` → detected conventions |
-| integrations.md | `analyze_dependencies` → external deps; `search("API\|database\|auth\|webhook")` → integration points |
-| testing.md | `analyze_patterns` → test patterns; `search("test framework")` → test setup; `test_run({})` → test health |
-| concerns.md | `audit({ path: "." })` → health issues; `dead_symbols({})` → dead code; `git_context({})` → high-churn files |
-
-### Phase 3: Populate Documents
-
-Create each document in `docs/architecture/` in this order:
-
-1. **stack.md** — Language, runtime version, frameworks, production dependencies, dev tooling
-2. **structure.md** — Directory layout, entry points, key files, package organization
-3. **design.md** — Layers, architectural patterns, data flow, component boundaries
-4. **conventions.md** — Naming conventions, formatting rules, error handling patterns, import conventions
-5. **integrations.md** — External APIs, databases, auth providers, monitoring, CI/CD
-6. **testing.md** — Test frameworks, file organization, mocking strategy, coverage approach
-7. **concerns.md** — Tech debt, known bugs, security risks, performance bottlenecks, high-churn files
-
-Rules:
-- Use `[TODO]` for anything that cannot be determined from code
-- Use `[ASK USER]` where the right answer requires team intent
-- Include an "Evidence" section in each doc with file paths and tool receipts
-
-### Phase 4: Validate, Repair, Verify
-
-Run this mandatory validation loop before finalizing:
-
-1. For each non-trivial claim, confirm at least one evidence reference exists
-2. If any required section is missing or unsupported → fix and re-validate
-3. Repeat until all seven docs pass
-
-Validation pass criteria:
-- No unsupported claims
-- No empty required sections
-- Unknowns use `[TODO]` rather than assumptions
-- Team-intent gaps are explicitly marked `[ASK USER]`
-
-Then present a summary, list every `[ASK USER]` item as a numbered question, and highlight any Intent vs. Reality divergences from Phase 1.
-
-## Focus Area Mode
-
-If the user specifies a focus area (e.g., "architecture only" or "testing and concerns"):
-
-1. Always run Phase 1 in full
-2. Fully complete focus-area documents first
-3. For non-focus documents, keep required sections present and mark unknowns as `[TODO]`
+# Project Knowledge — Workflow
+
+Detailed workflow for acquiring and documenting project knowledge into `docs/architecture/`.
+
+## Four-Phase Workflow
+
+```
+- [ ] Phase 1: Scan with AI Kit tools, read intent documents
+- [ ] Phase 2: Investigate each documentation area
+- [ ] Phase 3: Populate all seven docs in docs/architecture/
+- [ ] Phase 4: Validate docs, present findings, resolve all [ASK USER] items
+```
+
+### Phase 1: Scan and Read Intent
+
+```
+onboard({ path: "." })                           # Full codebase scan
+produce_knowledge({ path: "." })                  # Comprehensive analysis
+analyze_structure({ path: "." })                  # Project layout, packages, layers
+analyze_dependencies({ path: "." })               # All dependencies + import graph
+```
+
+Then read `README`, `PRD`, `TRD`, `ROADMAP`, `SPEC`, `DESIGN` files if they exist.
+Summarise the stated project intent before reading any source code.
+
+### Phase 2: Investigate
+
+Use Phase 1 tool outputs to answer questions for each of the seven documents. Run additional targeted tools:
+
+| Document | Investigation Tools |
+|----------|-------------------|
+| stack.md | `analyze_dependencies` → manifests, frameworks; `analyze_structure` → runtime signals |
+| structure.md | `analyze_structure` → file tree, packages; `analyze_entry_points` → entry points, key files |
+| design.md | `analyze_structure` → layers; `analyze_patterns` → design patterns; `analyze_diagram` → component diagrams |
+| conventions.md | `analyze_patterns` → naming, formatting; `search("conventions")` → detected conventions |
+| integrations.md | `analyze_dependencies` → external deps; `search("API\|database\|auth\|webhook")` → integration points |
+| testing.md | `analyze_patterns` → test patterns; `search("test framework")` → test setup; `test_run({})` → test health |
+| concerns.md | `audit({ path: "." })` → health issues; `dead_symbols({})` → dead code; `git_context({})` → high-churn files |
+
+### Phase 3: Populate Documents
+
+Create each document in `docs/architecture/` in this order:
+
+1. **stack.md** — Language, runtime version, frameworks, production dependencies, dev tooling
+2. **structure.md** — Directory layout, entry points, key files, package organization
+3. **design.md** — Layers, architectural patterns, data flow, component boundaries
+4. **conventions.md** — Naming conventions, formatting rules, error handling patterns, import conventions
+5. **integrations.md** — External APIs, databases, auth providers, monitoring, CI/CD
+6. **testing.md** — Test frameworks, file organization, mocking strategy, coverage approach
+7. **concerns.md** — Tech debt, known bugs, security risks, performance bottlenecks, high-churn files
+
+Rules:
+- Use `[TODO]` for anything that cannot be determined from code
+- Use `[ASK USER]` where the right answer requires team intent
+- Include an "Evidence" section in each doc with file paths and tool receipts
+
+### Phase 4: Validate, Repair, Verify
+
+Run this mandatory validation loop before finalizing:
+
+1. For each non-trivial claim, confirm at least one evidence reference exists
+2. If any required section is missing or unsupported → fix and re-validate
+3. Repeat until all seven docs pass
+
+Validation pass criteria:
+- No unsupported claims
+- No empty required sections
+- Unknowns use `[TODO]` rather than assumptions
+- Team-intent gaps are explicitly marked `[ASK USER]`
+
+Then present a summary, list every `[ASK USER]` item as a numbered question, and highlight any Intent vs. Reality divergences from Phase 1.
+
+## Focus Area Mode
+
+If the user specifies a focus area (e.g., "architecture only" or "testing and concerns"):
+
+1. Always run Phase 1 in full
+2. Fully complete focus-area documents first
+3. For non-focus documents, keep required sections present and mark unknowns as `[TODO]`
 4. Still run the Phase 4 validation loop on all seven documents

package/packages/cli/dist/constants-BjDyZo-l.js

@@ -1 +0,0 @@
-const e=`aikit`,t={type:`stdio`,command:`npx`,args:[`-y`,`@vpxa/aikit`,`serve`]},n=[`aikit`,`brainstorming`,`multi-agents-development`,`session-handoff`,`requirements-clarity`,`lesson-learned`,`c4-architecture`,`adr-skill`,`present`,`frontend-design`,`react`,`typescript`],r=[`aikit-basic`,`aikit-advanced`,`_epilogue`],i={"chat.agentFilesLocations":{"~/.claude/agents":!1},"github.copilot.chat.copilotMemory.enabled":!0,"chat.customAgentInSubagent.enabled":!0,"chat.useNestedAgentsMdFiles":!0,"chat.useAgentSkills":!0,"github.copilot.chat.switchAgent.enabled":!0,"workbench.browser.enableChatTools":!0,"chat.mcp.apps.enabled":!0,"chat.instructionsFilesLocations":{"~/.copilot/instructions":!0,".github/instructions":!0}};export{i as a,n as i,t as n,e as r,r as t};