catlog22/Claude-Code-Workflow
1
0
Fork 0
mirror of https://github.com/catlog22/Claude-Code-Workflow.git synced 2026-03-06 16:31:12 +08:00
Code Issues Packages Projects Releases Wiki Activity

feat: add dynamic pipeline detection for team sessions v5 architecture

Browse Source 
Backend:
- Fix readLegacyFiles to handle { name, prefix }[] role format
- Add roles backfill in getEffectiveTeamMeta when meta.json exists
- Ensure pipeline_stages and roles flow correctly to API response

Team Skills:
- Add pipeline metadata initialization to all 16 team skill coordinator roles
- Each skill now reports pipeline_stages and roles to meta.json at session init

Documentation:
- Update command references and component documentation
- Add numerical-analysis-workflow skill spec
- Sync zh/en translations for commands and components
This commit is contained in:
catlog22
2026-03-04 14:52:07 +08:00
parent b203ada9c5
commit f389e3e6dd
56 changed files with 2007 additions and 201 deletions
Download Patch File Download Diff File Expand all files Collapse all files

36
.claude/skills/team-lifecycle-v5/roles/coordinator/role.md
View File

@@ -127,17 +127,37 @@ For callback/check/resume: load `commands/monitor.md` and execute the appropriat
4. Initialize wisdom directory (learnings.md, decisions.md, conventions.md, issues.md)
5. Initialize explorations directory with empty cache-index.json
6. Write team-session.json
7. **Initialize meta.json with pipeline metadata** (CRITICAL for UI):
```typescript
// Use team_msg to write pipeline metadata to .msg/meta.json
mcp__ccw-tools__team_msg({
operation: "log",
session_id: "<session-id>",
from: "coordinator",
type: "state_update",
summary: "Session initialized",
data: {
pipeline_mode: "<mode>", // e.g., "full", "spec-only", "impl-only"
pipeline_stages: ["analyst", "writer", "planner", "executor", "tester", "reviewer"], // Roles as stages
roles: ["coordinator", "analyst", "writer", "planner", "executor", "tester", "reviewer"],
team_name: "lifecycle" // Skill name for badge display
}
})
```
**pipeline_stages format**: Array of role names that represent pipeline stages. The UI will display these as the pipeline workflow.
**Task counts by mode**:
| Mode | Tasks |
|------|-------|
| spec-only | 6 |
| impl-only | 4 |
| fe-only | 3 |
| fullstack | 6 |
| full-lifecycle | 10 |
| full-lifecycle-fe | 12 |
| Mode | Tasks | pipeline_stages |
|------|-------|-----------------|
| spec-only | 6 | `["analyst", "writer", "reviewer"]` |
| impl-only | 4 | `["planner", "executor", "tester", "reviewer"]` |
| fe-only | 3 | `["planner", "fe-developer", "fe-qa"]` |
| fullstack | 6 | `["planner", "executor", "fe-developer", "tester", "fe-qa", "reviewer"]` |
| full-lifecycle | 10 | `["analyst", "writer", "planner", "executor", "tester", "reviewer"]` |
| full-lifecycle-fe | 12 | `["analyst", "writer", "planner", "executor", "fe-developer", "tester", "fe-qa", "reviewer"]` |
---