agentleFS
rayketcham-labrayketcham-lab/qn-claude-web/.claude/skills/investigate/SKILL.md

investigate

Skill2 starsChanged 8 months agoApache-2.0View on GitHub

Debug and investigate issues — trace symptoms to root cause. Use when something is broken, a test fails mysteriously, or behavior is unexpected.

129 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use pair-agent, plan-devex-review and 10 more.

Other files people use alongside this one.

Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
  • seek888Skill

    pair-agent

    Pair a remote AI agent with your browser. One command generates a setup key and prints instructions the other agent can follow to connect. Works with OpenClaw, Hermes, Codex, Cursor, or any agent that can make HTTP requests. The remote agent gets its own tab with scoped access (read+write by default, admin on request). Use when asked to "pair agent", "connect agent", "share browser", "remote browser", "let another agent use my browser", or "give browser access". (gstack) Voice triggers (speech-to-text aliases): "pair agent", "connect agent", "share my browser", "remote browser access".

    Also in 10 projects that use this

  • seek888Skill

    plan-devex-review

    Interactive developer experience plan review. Explores developer personas, benchmarks against competitors, designs magical moments, and traces friction points before scoring. Three modes: DX EXPANSION (competitive advantage), DX POLISH (bulletproof every touchpoint), DX TRIAGE (critical gaps only). Use when asked to "DX review", "developer experience audit", "devex review", or "API design review". Proactively suggest when the user has a plan for developer-facing products (APIs, CLIs, SDKs, libraries, platforms, docs). (gstack) Voice triggers (speech-to-text aliases): "dx review", "developer experience review", "devex review", "devex audit", "API design review", "onboarding review".

    Also in 13 projects that use this

  • ShreyRaviSkill

    landing-report

    Read-only queue dashboard for workspace-aware ship. Shows which VERSION slots are currently claimed by open PRs, which sibling Conductor workspaces have WIP work likely to ship soon, and what slot /ship would pick next. No mutations — just a snapshot. Use when asked to "landing report", "what's in the queue", "show me open PRs", or "which version do I claim next". (gstack)

    Also in 7 projects that use this

  • ayudaySkill

    setup-deploy

    Configure deployment settings for /land-and-deploy. Detects your deploy platform (Fly.io, Render, Vercel, Netlify, Heroku, GitHub Actions, custom), production URL, health check endpoints, and deploy status commands. Writes the configuration to CLAUDE.md so all future deploys are automatic. Use when: "setup deploy", "configure deployment", "set up land-and-deploy", "how do I deploy with gstack", "add deploy config".

    Also in 14 projects that use this

  • ramybarsoumSkill

    document-release

    Post-ship documentation update. Reads all project docs, cross-references the diff, updates README/ARCHITECTURE/CONTRIBUTING/CLAUDE.md to match what shipped, polishes CHANGELOG voice, cleans up TODOS, and optionally bumps VERSION. Use when asked to "update the docs", "sync documentation", or "post-ship docs". Proactively suggest after a PR is merged or code is shipped.

    Also in 18 projects that use this

  • GeiserXSkill

    docs-loop

    Use when the user asks to audit docs, check documentation for stale claims, or verify docs against the code.

    Also in 3 projects that use this

  • +1 more from seek888

The file

We split this skill into the rules it gives an agent

12 rules. 0 are common, 10 are distinctive, and 2 are very specific to this project.

  • 0

    Common

    Most of the 116 edited versions we read keep these.

  • 10

    Distinctive

    This author's own choices. Worth a look.

  • 2

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Run the failing command/test and capture exact output

    line 23
  2. Distinctive:

    If intermittent, run 3 times and note frequency

    line 25
  3. Distinctive:

    Search codebase for the error message text

    line 30
  4. Very specific:

    Check recent changes: git log --oneline -20 -- <relevant files>

    line 32
  5. Very specific:

    Check if this worked before: git log --all -S "<error string>" --oneline

    line 33
  6. Distinctive:

    Read the relevant code

    line 49
  7. Distinctive:

    Check the specific condition that would cause this failure

    line 50
  8. Distinctive:

    If possible, add temporary debug output to confirm

    line 51
  9. Distinctive:

    Stop at the first confirmed hypothesis

    line 52
  10. Distinctive:

    Hard cap: 5 hypotheses total: If you've tested 5 hypotheses without confirming a root cause:

    line 54
  11. Distinctive:

    Check the obvious first: config, permissions, dependencies, typos.

    line 82
  12. Distinctive:

    Don't fix symptoms. Find the actual cause.

    line 84

“Common” is measured: kept by at least 6 in 10 of the 116 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

/investigate — Root Cause Analysis

Given a symptom, systematically trace it to root cause and propose a fix.

Target

$ARGUMENTS

Process

Step 1 — Reproduce

Confirm the problem exists and is reproducible:

  • Run the failing command/test and capture exact output
  • Note: error message, exit code, stack trace, log lines
  • If intermittent, run 3 times and note frequency

Step 2 — Locate

Find where the error originates:

  • Search codebase for the error message text
  • Trace the call chain: who calls the failing function? What calls that?
  • Check recent changes: git log --oneline -20 -- <relevant files>
  • Check if this worked before: git log --all -S "<error string>" --oneline

Step 3 — Hypothesize (Extended Thinking)

Think deeply and step by step about potential causes. Consider second-order effects, timing issues, and non-obvious interactions.

Form 2-3 hypotheses ranked by likelihood:

  1. Most likely cause (based on evidence)
  2. Alternative explanation
  3. Long-shot possibility

For each, identify what evidence would confirm or rule it out.

Step 4 — Test Hypotheses

For each hypothesis (most likely first):

  • Read the relevant code
  • Check the specific condition that would cause this failure
  • If possible, add temporary debug output to confirm
  • Stop at the first confirmed hypothesis

Hard cap: 5 hypotheses total. If you've tested 5 hypotheses without confirming a root cause:

  1. Report what you've ruled out and what evidence you have
  2. Return status: ESCALATING — "Root cause not confirmed after 5 hypotheses. User context may be needed."
  3. Include your best guess with confidence level

Step 5 — Root Cause + Fix

## Investigation: [Symptom]

**Root Cause**: [One sentence — what's actually wrong]
**Location**: `file:line`
**Evidence**: [What confirmed this diagnosis]

### Fix
[Concrete code change or configuration fix]

### Regression Test
[Test that would catch this if it recurred]

### Related Risks
[Anything else that might have the same problem]

Principles

  • Evidence over intuition. Read the code, don't guess.
  • Binary search: narrow the scope by half each step.
  • Check the obvious first: config, permissions, dependencies, typos.
  • "It worked before" → find the commit that broke it with git bisect or log search.
  • Don't fix symptoms. Find the actual cause.

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.