agentleFS
Sign inStart free
syangasyanga/astack/skills/investigation/SKILL.md

investigation

Skill0 starsChanged 55 days agoMITView on GitHub

Investigate a technical question and return a cited explanation or recommendation.

6 other projects use a version of this.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

2 rules. 0 are common, 2 are distinctive, and 0 are very specific to this project.

  • 0

    Common

    Most of the 5 edited versions we read keep these.

  • 2

    Distinctive

    This author's own choices. Worth a look.

  • 0

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Keep the inquiry read-only, including delegated work.

    line 14
  2. Distinctive:

    Stop with the answer. When the user requests implementation, route to bug-fix, perf-issue, or implement.

    line 18

“Common” is measured: kept by at least 6 in 10 of the 5 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

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.

  1. 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.
  2. 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.
  3. 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.
  4. 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.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

Check your setup, free