メニュー
Use when adding or changing product behavior that must ship with explicit purpose, scenarios, and verification. Uses write tools, shell execution, and may spawn subagents. Invoke with enable_write_tools=true and enable_subagent_tools=true.
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 debugging a failing test, broken build, runtime error, or unexpected system behavior. Drives hypothesis-based investigation, root-cause fixes, verification, and reusable learning capture.
Use when a claim, plan, spec, doc, or design must be attacked against source evidence before implementation or approval. Uses write tools, shell execution, and may spawn subagents. Invoke with enable_write_tools=true and enable_subagent_tools=true.
Use when fixing broken behavior and the priority is reproduce, root cause, regression proof, and the smallest safe repair. Uses write tools, shell execution, and may spawn subagents. Invoke with enable_write_tools=true and enable_subagent_tools=true.
Use when reviewing code changes with explicit stage, target, and focus so own-code checks and others’ PR reviews stay distinct but share one contract. Uses write tools, shell execution, and may spawn subagents. Invoke with enable_write_tools=true and enable_subagent_tools=true.
Use when the deliverable is docs or reference material and every claim must stay tied to observed behavior or cited source evidence. Uses write tools, shell execution, and may spawn subagents. Invoke with enable_write_tools=true and enable_subagent_tools=true.
Use when improving structure without changing behavior, with explicit invariants and verification that the contract stays the same. Uses write tools, shell execution, and may spawn subagents. Invoke with enable_write_tools=true and enable_subagent_tools=true.
| name | feature |
| description | Use when adding or changing product behavior that must ship with explicit purpose, scenarios, and verification. Uses write tools, shell execution, and may spawn subagents. Invoke with enable_write_tools=true and enable_subagent_tools=true. |
| status | draft |
Start when the task adds or changes externally observable behavior, a user-visible capability, or a stable internal contract.
goal — plain-language outcomeconstraints — non-goals, boundaries, rejected approachesvalidate — observable proof pathrisk — low | normal | highspec_mode — plain | speckit | autotdd_mode — lightweight | medium | heavy-aggressive | requiredDeliver the requested behavior with the smallest change that satisfies the goal, preserves existing patterns, and keeps vibe-lab out of runtime ownership.
Choose and record a TDD mode before code changes. If no red test is practical, record an explicit exemption and validation substitute.
Stop only when the requested behavior is observed through validation, the TDD evidence or exemption is recorded, and any out-of-scope discoveries are called out instead of silently absorbed.
Stop and report when the goal conflicts with current constraints, required validation cannot be run, or the implementation would require a new runtime/state surface not forced by the request.