Commit Graph

8 Commits

Author SHA1 Message Date
catlog22
2b5c334bc4 feat: Implement recursive core-memory database discovery and project listing
- Added `findAllCoreMemoryDatabases` function to recursively locate core-memory databases in nested project structures.
- Updated `listAllProjects` to utilize the new recursive function for improved project listing.
- Enhanced `getMemoriesFromProject` and `findMemoryAcrossProjects` to support nested project structures.

feat: Introduce spec context injection in hooks configuration

- Added a new hook configuration for "Spec Context Injection" to load project specs based on prompt keywords.

chore: Add gray-matter dependency for YAML frontmatter parsing

- Included `gray-matter` package in `package.json` for parsing YAML frontmatter in markdown files.

feat: Create Spec Index Builder tool for managing project specs

- Implemented `spec-index-builder.ts` to scan markdown files, extract YAML frontmatter, and generate index cache files for different spec dimensions.

feat: Develop Spec Init tool for initializing spec directories and seed documents

- Created `spec-init.ts` to set up the directory structure and seed documents for the spec system.

feat: Build Spec Keyword Extractor for keyword extraction from prompts

- Added `spec-keyword-extractor.ts` to extract keywords from user prompts, supporting both English and Chinese text.

feat: Implement Spec Loader for loading and filtering specs based on keywords

- Developed `spec-loader.ts` to handle loading of specs, filtering by read mode and keyword matches, and formatting output for CLI or hooks.
2026-02-26 12:51:29 +08:00
catlog22
e92c6ce0b1 fix(skills): replace polling/pre-spawning with Stop-Wait pattern across all team coordinators
All team coordinator roles now follow the Stop-Wait design principle:
- Phase 2: Remove worker pre-spawning, workers are spawned per-stage in Phase 4
- Phase 4: Add Stop-Wait principle note (synchronous Task calls instead of polling)
- monitor.md: Replace while+sleep polling loops with synchronous Task execution

Teams updated: team-brainstorm, team-frontend, team-issue, team-iterdev,
team-lifecycle, team-lifecycle-v2, team-quality-assurance, team-tech-debt,
team-testing, team-uidesign, team-ultra-analyze
2026-02-24 00:05:29 +08:00
catlog22
32d2d534ab fix(team-lifecycle-v2): align skill name with folder name
Update skill name from 'team-lifecycle' to 'team-lifecycle-v2' to match
the folder name convention.
2026-02-18 18:36:52 +08:00
catlog22
3441a3c06c refactor: SKILL.md abstraction cleanup + coordinator frontend detection
- Remove ui-ux-pro-max/Shared Memory sections from SKILL.md (implementation details belong in role.md)
- Replace Frontend Detection code block with reference to coordinator/role.md
- Add detectImplMode() to coordinator Phase 1 for auto-detecting frontend tasks
- Add fe-only/fullstack/full-lifecycle-fe mode choices
- Add fe-developer + fe-qa spawning in Phase 2 for frontend pipelines
- Initialize shared-memory.json when frontend pipeline is active
2026-02-18 13:11:28 +08:00
catlog22
265a77d6e7 feat(team-lifecycle-v2): integrate ui-ux-pro-max + shared memory into frontend pipeline
- fe-developer: add design-intelligence.json consumption, token CSS generation
  (:root + dark mode), self-validation, anti-patterns/checklist in prompts
- fe-qa: add industry-aware audit (standard/strict), Do/Don't rules,
  emoji/focus-visible/prefers-reduced-motion/cursor-pointer checks,
  anti-pattern matching from design-intelligence.json, shared memory update
- fe-qa/commands: add pre-delivery-checklist.md (CSS-level precision checks)
- SKILL.md: add ui-ux-pro-max integration section, shared memory section,
  command tree update for fe-qa/commands
- team-config.json: add ui_ux_pro_max and shared_memory config blocks
2026-02-18 13:03:02 +08:00
catlog22
cc3b219f1b feat(team-lifecycle-v2): add frontend pipeline (fe-developer + fe-qa) with auto-detection
- Add fe-developer role: DEV-FE-* prefix, tech stack detection, design token consumption
- Add fe-qa role: QA-FE-* prefix, 5-dimension review, GC loop (max 2 rounds)
- Add frontend pipelines: fe-only, fullstack, full-lifecycle-fe
- Add frontend detection: keyword-based auto-routing to frontend sub-pipeline
- Update SKILL.md: architecture, dispatch table, roles, message types, pipelines
2026-02-18 12:51:11 +08:00
catlog22
c466ca7334 feat(team-lifecycle-v2): add explorer/architect roles + wisdom accumulation
New roles (on-demand, non-pipeline):
- explorer: multi-strategy code search & pattern discovery (EXPLORE-*)
- architect: multi-mode architecture assessment (ARCH-*)

New files:
- roles/explorer/role.md - service role with 5 search strategies
- roles/architect/role.md - consulting role with 5 consultation modes
- roles/architect/commands/assess.md - mode-specific assessment strategies

Updated:
- SKILL.md: architecture diagram, role router, message types, session dirs, wisdom protocol
- specs/team-config.json: new role definitions + wisdom/explorations/architecture dirs
- roles/coordinator/role.md: wisdom directory initialization on session create
2026-02-18 12:36:34 +08:00
catlog22
f0dda075f0 feat: Add templates for epics, product brief, and requirements PRD
- Introduced a comprehensive template for generating epics and stories, including an index and individual epic files.
- Created a product brief template to outline product vision, problem statements, and target users.
- Developed a requirements PRD template to structure functional and non-functional requirements, including traceability and prioritization.
- Implemented ast-grep processors for JavaScript and TypeScript to extract relationships such as imports and inheritance.
- Added corresponding patterns for JavaScript and TypeScript to support relationship extraction.
- Established comparison tests to validate the accuracy of relationship extraction between tree-sitter and ast-grep methods.
2026-02-18 12:02:02 +08:00