agentleFS
Sign inStart free
artaasd95artaasd95/SLM-skills/root-cause-investigator/SKILL.md

root-cause-investigator

Skill0 starsChanged 4 months agoMITView on GitHub

Find the exact root cause of a bug or error using a temporary investigation markdown file. Use when debugging, analyzing stack traces, logs, failing tests, or unexpected behavior. Do not use for feature planning or code writing.

2 other projects use a version of this.

Adopted by

Most recently taken up by

  • Other versions2 projects use a version of this.

    Word for word · 0

    None found.

    Edited · 0

    None found.

    Wrote their own version · 2

    1. khadir-syed/k_ai-agent-skills★ 19same name
    2. future-mine/claude-skill★ 1same name

    How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.

  • In this repository3 other files it gives its agents.

The file

We split this skill into the rules it gives an agent

8 rules. About 0 are common, 8 are distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈8

    Distinctive · estimate

    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:

    Create a temporary investigation file named:

    line 13
  2. Distinctive:

    After every file or method you inspect, append exactly one line in the format:

    line 41
  3. Distinctive:

    When the root cause is confirmed, append:

    line 47
  4. Distinctive:

    Stop immediately after completing the investigation.

    line 57
  5. Distinctive:

    Keep observations extremely short (prefer one line each).

    line 62
  6. Distinctive:

    Read at most 8–10 files.

    line 63
  7. Distinctive:

    If a path is a dead end, record "dead-end" and try one alternative starting point.

    line 64
  8. Distinctive:

    Keep the investigation document under ~80 lines.

    line 65

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “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

Root-Cause Investigator

You investigate only. Never edit source code.

Process

  1. Create a temporary investigation file named:

    [short-problem]-investigation.md

    Example:

    null-logger-investigation.md

  2. At the top of the file write:

    ## Summary
[1–2 sentences describing the failure]

## Critical Evidence
[Only the 3–8 most relevant log or error lines]

## Starting Point
File: path/to/file
Method: methodName

  3. Trace execution through the codebase.

    After every file or method you inspect, append exactly one line in the format:

    method [name] → [observation] | next: [file or stop]

  4. When the root cause is confirmed, append:

    ## Root Cause
[One clear paragraph describing the actual cause]

## Suggested Fix
[Exact change required, without writing code]
  5. Stop immediately after completing the investigation.

Hard Rules

  • Investigate only. Never modify source code.
  • Keep observations extremely short (prefer one line each).
  • Read at most 8–10 files.
  • If a path is a dead end, record "dead-end" and try one alternative starting point.
  • Keep the investigation document under ~80 lines.
  • Deliver only the completed *-investigation.md file.

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