メニュー
Communication templates and response formatting for AI coding assistants. Defines structured message formats with semantic indicators for status, errors, actions, and progress. Auto-loaded for all interactions.
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
End-of-session routine. Ensures test coverage, performs self-review, runs validation, and commits cleanly. Use when finishing a unit of work.
Full feature implementation workflow with explore, plan, code, test, validate, and commit phases. Use for new features, enhancements, or significant code changes.
Iterate on an open PR until CI passes and all review feedback is addressed. Fetches status, categorizes findings by severity, applies fixes, and loops until clean.
Create a detailed implementation plan without writing code. Read-only analysis and planning with user approval gate. Use before implementing features or making significant changes.
Systematic security audit with confidence-based reporting. Analyzes attack surfaces, checks against OWASP categories, and reports only confirmed or likely vulnerabilities. Use for pre-merge security review or periodic audits.
Run validation checks to ensure code quality, security, and correctness. Supports quick (scoped), full (CI pipeline), fix (auto-correct), and CI mirror modes.
| name | communication-guidelines |
| description | Communication templates and response formatting for AI coding assistants. Defines structured message formats with semantic indicators for status, errors, actions, and progress. Auto-loaded for all interactions. |
| category | protocol |
| user-invocable | false |
Predictable, semantically-colored message formats following CLI UX best practices.
Emoji handling: Templates below use emoji indicators by default. When
config.yamlsetsuse_emojis: false, use plain-text prefixes instead:
Default Plain alternative ✅ STATUS [STATUS]🔴 ACTION [ACTION]⚠️ WARNING [WARNING]❌ ERROR [ERROR]💡 INFO [INFO]📝 INPUT [INPUT]⚡ CONFIRM [CONFIRM]📋 TASK [TASK]💬 NEXT [NEXT]✓ / ⠋ / ○ [done]/[..]/[ ]
INFORMATIONAL (no action): ACTION REQUIRED (must respond):
✅ STATUS - Results 🔴 ACTION - Decision needed
💡 INFO - Context 📝 INPUT - Info needed
💬 NEXT - Follow-up ⚡ CONFIRM - Yes/no
ATTENTION (read carefully): PROGRESS (during work):
⚠️ WARNING - Caution ✓ Complete ⠋ Working
❌ ERROR - Fix suggestion ○ Pending
════════════════════════════════════════════════════════════
📋 TASK: [Brief task description]
════════════════════════════════════════════════════════════
✅ STATUS
────────────────────────────────────────────────────────────
[Results, what changed]
✓ Item completed
✓ Another item
⚠️ WARNING (if applicable)
────────────────────────────────────────────────────────────
[Risk or caution]
🔴 ACTION REQUIRED (if applicable)
────────────────────────────────────────────────────────────
[Question or decision needed]
(A) Option one
(B) Option two
**Select:** (A) or (B)
Always: What failed → Why → How to fix
❌ ERROR
────────────────────────────────────────────────────────────
Build failed
What: Cannot read property 'name' of undefined
Where: src/components/UserProfile.tsx:45
Why: user object is null when component mounts
Fix: Add null check: if (user?.name) { ... }
📋 Running validation
✓ Type check passed
✓ Lint passed
⠋ Running tests...
○ Build (pending)
For general communication principles (conciseness, action-focus, no-summary policy), see ai-assistant-protocol. For voice, tone, and human-AI interaction boundary rules, see interaction-boundaries.