ワンクリックで
goat
Use when you describe an outcome and need the right goat-* workflow chosen for you.
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。
メニュー
Use when you describe an outcome and need the right goat-* workflow chosen for you.
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
Use when a decision or analysis needs multi-lens critique to surface blind spots before shipping.
Use when diagnosing a bug, unexpected behaviour, system failure, or unfamiliar code that needs structured investigation.
Use when starting a non-trivial implementation that needs structured task breakdown with progress tracking.
Use when evaluating test coverage gaps, planning test strategy, or assessing testing risk for code changes.
Use when reviewing a diff, PR, or set of code changes, or auditing a codebase area for quality issues. Triggers: 'review this', 'code review', 'audit X', 'look at these changes'.
Use when assessing security implications of code changes, architecture decisions, or new features.
| name | goat |
| description | Use when you describe an outcome and need the right goat-* workflow chosen for you. |
| goat-flow-skill-version | 1.11.0 |
Read .goat-flow/skill-docs/skill-preamble.md for shared conventions.
Use when the user describes an outcome and wants the right workflow chosen. If the user names a skill explicitly (/goat-debug, /goat-review, etc.), route to it immediately - no classification, no GATHER.
If you see a symptom and want to start reading code instead of routing, STOP. The dispatcher classifies and routes; the routed skill investigates.
| Excuse | Reality |
|---|---|
| "I can see the issue - routing is overhead" | You are the dispatcher, not the investigator. Route first. |
| "The user said 'just fix it'" | Pragmatic pressure, not a routing override. Route to /goat-debug. |
| "Time pressure means investigate immediately" | Routing takes seconds. Investigating without routing risks the wrong problem. |
| "Multiple symptoms mean I should start reading files" | Multiple intents. Split into numbered intents, route each separately - do not collapse into one. |
.goat-flow/learning-loop/footguns/INDEX.md for the target area; open entries only on hitsgather-degraded and route anywayIntent: [classified intent]
Route: [/goat-* or direct]
Rationale: [concrete signals that justified this route]
| Intent | Route |
|---|---|
| Bug, failure, unexpected behaviour | /goat-debug |
| Verify a fix worked | /goat-debug (post-fix verification) |
| Browser-visible issue | Browser evidence first; /goat-debug Investigate if diagnosis needed |
| Understand, explain, explore unfamiliar code | /goat-debug (Investigate mode) |
| Quality review, audit, diff check | /goat-review |
| Verify a diff/PR before merge | /goat-review |
| Multi-perspective critique | /goat-critique |
| Security, compliance, dependency audit | /goat-security |
| Testing gaps, coverage, verification planning | /goat-qa |
| Verify test coverage | /goat-qa |
| Feature planning, milestones | /goat-plan |
| Bare task path (no action verb) | Bare or ambiguous task paths are read-only context. Do not update .active, milestone status, or code from a path alone |
| Build/plan verb + scope | /goat-plan (Step 0 handles complexity and mode) |
| Simple implementation (single-file, obvious) | No skill; use execution loop directly |
| Simple question | Answer directly |
Ambiguity examples: "This endpoint is slow" → debug or review? "Check this code" → review or debug? "Look at auth" → security or review?