investigate-first
Diagnose ambiguous failures before editing. Use for unknown causes, intermittent behavior, performance regressions, or investigations needing evidence-ranked hypotheses.
- License 许可
- AGPL-3.0
- 最近更新
- 2026-11-04
- Stars
- ★ 0
- Forks
- 1
01 前言 Front Matter
- name
- investigate-first
- description
- Diagnose ambiguous failures before editing. Use for unknown causes, intermittent behavior, performance regressions, or investigations needing evidence-ranked hypotheses.
02 资源文件 1
- 参考文档agents/openai.yaml202 B
03 SKILL.md 正文
Investigate first
Gather evidence before changing product code.
- Separate observed symptom from inferred cause.
- Trace inputs, state transitions, ownership boundaries, and failure output.
- Rank hypotheses by evidence and cheap falsification value.
- Do not edit until one credible mechanism explains evidence.
- Stop exploration when evidence is sufficient to name cause or exact blocker.
Report cause and proof. Make no fix unless task authorizes implementation.
04 同仓库更多 Skills
writing-plans
Use when you have a spec or requirements for a multi-step task, before touching code
what-the
What the? Use when the user wants a plain-English breakdown of something technical — the who, what, where, why, and when.
verification-before-completion
Use when about to claim work is complete, fixed, or passing, before committing or creating PRs - requires running verification commands and confirming output before making any success claims; evidence before assertions always
using-agent-skills
Discovers and invokes agent skills. Use when starting a session or when you need to discover which skill applies to the current task. This is the meta-skill that governs how all other skills are discovered and invoked.
test-driven-development
Drives development with tests. Use when implementing any logic, fixing any bug, or changing any behavior. Use when you need to prove that code works, when a bug report arrives, or when you're about to modify existing functionality.
spec-driven-development
Creates specs before coding. Use when starting a new project, feature, or significant change and no specification exists yet. Use when requirements are unclear, ambiguous, or only exist as a vague idea.