mirror of
https://github.com/catlog22/Claude-Code-Workflow.git
synced 2026-03-01 15:03:57 +08:00
Root cause: team_msg --team parameter maps directly to filesystem path
.workflow/.team/{value}/.msg/, so using team-name creates wrong directory.
Changes:
- All team skills (14 skills, 80+ files): Changed team=<team-name> to
team=<session-id> with clear documentation
- Added NOTE in every file: "team must be session ID (e.g., TLS-xxx-date),
NOT team name. Extract from Session: field in task description."
- CLI fallback examples updated: --team brainstorm -> --team <session-id>
Skills fixed:
- team-brainstorm, team-coordinate, team-frontend, team-issue
- team-iterdev, team-lifecycle-v3, team-planex, team-quality-assurance
- team-review, team-roadmap-dev, team-tech-debt, team-testing
- team-uidesign, team-ultra-analyze
Also includes new team-executor skill for lightweight session execution.
2.9 KiB
2.9 KiB
role, prefix, additional_prefixes, inner_loop, discuss_rounds, subagents, message_types
| role | prefix | additional_prefixes | inner_loop | discuss_rounds | subagents | message_types | ||||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| reviewer | REVIEW |
|
false |
|
|
|
Reviewer — Phase 2-4
Phase 2: Mode Detection
| Task Prefix | Mode | Dimensions | Inline Discuss |
|---|---|---|---|
| REVIEW-* | Code Review | quality, security, architecture, requirements | None |
| QUALITY-* | Spec Quality | completeness, consistency, traceability, depth, coverage | DISCUSS-006 |
| IMPROVE-* | Spec Quality (recheck) | Same as QUALITY | DISCUSS-006 |
Phase 3: Review Execution
Code Review (REVIEW-*)
Inputs: Plan file, git diff, modified files, test results (if available)
4 dimensions:
| Dimension | Critical Issues |
|---|---|
| Quality | Empty catch, any in public APIs, @ts-ignore, console.log |
| Security | Hardcoded secrets, SQL injection, eval/exec, innerHTML |
| Architecture | Circular deps, parent imports >2 levels, files >500 lines |
| Requirements | Missing core functionality, incomplete acceptance criteria |
Spec Quality (QUALITY-* / IMPROVE-*)
Inputs: All spec docs in session folder, quality gate config
5 dimensions:
| Dimension | Weight | Focus |
|---|---|---|
| Completeness | 25% | All sections present with substance |
| Consistency | 20% | Terminology, format, references |
| Traceability | 25% | Goals -> Reqs -> Arch -> Stories chain |
| Depth | 20% | AC testable, ADRs justified, stories estimable |
| Coverage | 10% | Original requirements mapped |
Quality gate:
| Gate | Criteria |
|---|---|
| PASS | Score >= 80% AND coverage >= 70% |
| REVIEW | Score 60-79% OR coverage 50-69% |
| FAIL | Score < 60% OR coverage < 50% |
Artifacts: readiness-report.md + spec-summary.md
Phase 4: Verdict + Inline Discuss
Code Review Verdict
| Verdict | Criteria |
|---|---|
| BLOCK | Critical issues present |
| CONDITIONAL | High/medium only |
| APPROVE | Low or none |
Spec Quality Inline Discuss (DISCUSS-006)
After generating readiness-report.md, call discuss subagent:
- Artifact:
<session-folder>/spec/readiness-report.md - Round: DISCUSS-006
- Perspectives: product, technical, quality, risk, coverage (all 5)
Handle discuss verdict per team-worker consensus handling protocol.
Note
: DISCUSS-006 HIGH always triggers user pause (final sign-off gate), regardless of revision count.
Report: mode, verdict/gate, dimension scores, discuss verdict (QUALITY only), output paths.
Error Handling
| Scenario | Resolution |
|---|---|
| Missing context | Request from coordinator |
| Invalid mode | Abort with error |
| Analysis failure | Retry, then fallback template |
| Discuss subagent fails | Proceed without final discuss, log warning |