メニュー
Use when implementing an approved OpenSpec change, progressing through tasks, updating task status, or continuing an incomplete implementation.
Codex または Claude でインストール この Prompt をコピーして Codex、Claude、または他のアシスタントに貼り付けると、Skill ページを確認してインストールできます。
SOC 職業分類に基づく
| name | team-apply-guard |
| description | Use when implementing an approved OpenSpec change, progressing through tasks, updating task status, or continuing an incomplete implementation. |
/team-apply is the coordination entry point. It dispatches to team-implementation-guard and TDD process.
Use this skill when:
/team-apply <change-id> is executedDo NOT use this skill when:
team-openspec-guard)team-verification-guard)team-review-guard)/team-propose firstteam-implementation-guard to govern each task's implementationteam-implementation-guard)User: /team-apply add-user-auth
AI:
1. Read openspec/changes/add-user-auth/tasks.md
2. Find 5 incomplete tasks
3. Pick task 1.1: Create User model
4. Write tests first: tests/models/test_user.py
5. Implement models/user.py
6. Run pytest: 8 passed
7. Update tasks.md: mark 1.1 complete
8. Continue to task 1.2...
User: /team-apply add-user-auth
AI:
1. Read tasks.md
2. Find tasks 2.1 and 2.2 complete, 3.1 incomplete
3. Resume from task 3.1
4. "Continuing add-user-auth, completed 4/5, current task 3.1"
User: /team-apply add-payment
AI:
1. Read proposal.md
2. Find unresolved hard blocker:
- Q1: Payment gateway selection (Hard block)
3. Stop implementation: "Unresolved hard blocker exists. Please confirm payment gateway before continuing."
/team-apply
├── team-implementation-guard (implementation guardrails)
├── TDD guidance (test-first)
└── Progress reporting (done/in-progress/remaining/blocked)
When this skill fails, record in badCases/ directory:
See badCases/ for case history.
Use when implementing OpenSpec tasks, writing code, running tests, or fixing bugs. Guards TDD flow, execution modes, and spec compliance.
Use when creating, reviewing, or updating OpenSpec proposals, designs, tasks, spec deltas, acceptance criteria, or archiving changes.
Use when diagnosing and fixing bugs, applying security patches, or making small enhancements with /team-repair. Guards DIVE protocol, dual-track closure, and evidence-driven repair.
Use when exploring requirements, doing deep design exploration, or brainstorming before proposing. Guards OpenSpec environment and brainstorm output location.
Use when reviewing task breakdowns, checking dependency ordering, optimizing task granularity, or deciding whether to proceed to implementation.
Use when retrospecting on AI collaboration, recording bad cases, updating skill rules, or managing skill versions.