investigation
Investigate a technical question and return a cited explanation or recommendation.
- License 许可
- MIT
- 所属仓库
- syanga/astack
- 最近更新
- 2026-11-14
- Stars
- ★ 0
- Forks
- 0
01 前言 Front Matter
- name
- investigation
- description
- Investigate a technical question and return a cited explanation or recommendation.
- disable-model-invocation
- true
02 资源文件 1
- 许可证LICENSE-pstack1.0 KB
03 SKILL.md 正文
Investigation
You own the answer. Plan, route, write.
Investigation requests are read-only. They produce a cited explanation or a recommendation. State the question and the evidence needed to answer it. Reuse the scope already established with the user.
- Choose the method that answers the question. For code behavior, read how. For motivation or regression history, also read why. For a suspected failure, read diagnosing-bugs in diagnosis-only scope. For an existing profile, trace, or heap snapshot, follow trace forensics.
- Keep the inquiry read-only, including delegated work. Use existing code, captures, history, and checks that fit that scope. If an experiment needs instrumentation or other writes, report the missing evidence and the proposed experiment. A question alone does not authorize it.
- Produce the
how-shaped explanation, or a recommendation with a tradeoffs table for a decision between alternatives. Cite the evidence, separate observations from hypotheses, and name any gaps that limit the conclusion. For "are we sure?", give your judgment and reasons, including evidence against the premise. - Apply unslop to the reply.
Stop with the answer. When the user requests implementation, route to bug-fix, perf-issue, or implement. Carry forward the findings rather than repeating the inquiry. For a session transfer, read handoff and preserve the current scope and evidence pointers.
Reply: the answer or recommendation, cited evidence, confidence, and unresolved questions.
04 同仓库更多 Skills
replace-with-skill-name
Replace with when this skill should be reached.
writing-for-agents
Writing documents for agents. Use when creating or editing skills, or modifying AGENTS.md or CLAUDE.md.
worktree-cleanup
Worktree cleanup. Use for cleanup, resource audits, close this lane, or close out.
wizard
Generate an interactive Bash wizard that walks a human through steps only they can perform. Use when provisioning, credential setup, or a one-off migration needs such steps.
why
Use for 'why does X work this way', 'why we picked Y', design rationale, regressions, postmortems, or data-backed thresholds. Returns a cited read on decisions and tradeoffs.
wayfinder
Plan a huge chunk of work (more than one agent session can hold) as a shared map of decision tickets on your issue tracker, and resolve them one at a time until the way to the destination is clear.