agentleFS
Sign inStart free
d-o-hubd-o-hub/github-template-ai-agents/.agents/skills/debugger/SKILL.md

debugger

Skill2 starsChanged 9 days agoMITView on GitHub

Diagnose failing builds and runtime errors with root-cause discipline. Use when a build, deploy, or service crashes, or an error appears at runtime — even if they just say "debug this crash" or "why does the server 502". Not for test-runner (failing or flaky tests in a suite), iterative-refinement (repeat-until-pass loops), security-code-auditor (vulnerabilities).

32 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use security-engineer, planner and 5 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.
  • belokonmSkill

    security-engineer

    Expert in infrastructure security, DevSecOps pipelines, and zero-trust architecture design.

    Also in 4 projects that use this

  • am-willSkill

    planner

    Create comprehensive, phased implementation plans with sprints and atomic tasks. Use when user says: "make a plan", "create a plan", "plan this out", "plan the implementation", "help me plan", "design a plan", "draft a plan", "write a plan", "outline the steps", "break this down into tasks", "what's the plan for", or any similar planning request. Also triggers on explicit "/planner" or "/plan" commands.

    Also in 3 projects that use this

  • VercelSkill

    technical-writer

    Write, review, and edit developer documentation for SDKs, libraries, and frameworks, including sites such as ai-sdk.dev and chat-sdk.dev. Use for getting-started guides, tutorials, API references, conceptual explanations, integration guides, migration guides, troubleshooting, and code examples.

    Also in 4 projects that use this

  • leonardomsoSkill

    test-writer

    Generate comprehensive Vitest tests for code examples in JavaScript concept documentation pages, following project conventions and referencing source lines

    Also in 3 projects that use this

  • GitHubSkill

    documentation-writer

    Diátaxis Documentation Expert. An expert technical writer specializing in creating high-quality software documentation, guided by the principles and structure of the Diátaxis technical documentation authoring framework.

    Also in 3 projects that use this

  • AnthropicSkill

    system-design

    Design systems, services, and architectures. Trigger with "design a system for", "how should we architect", "system design for", "what's the right architecture for", or when the user needs help with API design, data modeling, or service boundaries.

    Also in 3 projects that use this

The file

We split this skill into the rules it gives an agent

1 rule. 0 are common, 1 is distinctive, and 0 are very specific to this project.

  • 0

    Common

    Most of the 29 edited versions we read keep these.

  • 1

    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:

    If it only fails in CI, diff the environments (versions, env vars, cwd).

    line 26

“Common” is measured: kept by at least 6 in 10 of the 29 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

Debugger

Root-cause diagnosis for failing builds and runtime errors. Symptoms first, theories second, fixes last.

When to Use

  • Build, deploy, or CI pipeline fails
  • Runtime crash, panic, exception, or hang
  • Error output that is cryptic or misleading
  • Even if they just say "debug this crash" or "the build is red"

Steps

  1. Read the error first — full output, not the last line. Note exit codes, file:line locations, and the first failure (later ones cascade).
  2. Reproduce minimally — smallest command or input that triggers it. If it only fails in CI, diff the environments (versions, env vars, cwd).
  3. Form one hypothesis — state the suspected cause before changing code.
  4. Bisect — halve the search space (recent commits, config halves, feature flags) until the trigger commit or line is isolated.
  5. Fix at the root — patch the cause, not the symptom; add the minimal reproducer as a regression test.
  6. Verify — rerun the reproducer plus the surrounding suite green.

Common Traps

  • Fixing the second error in the log while the first (causal) one remains.
  • "Works on my machine" without diffing dependency or environment versions.
  • Treating flaky as fixed after one green run — rerun at least 3 times.

Rationalizations

RationalizationReality
"The error message says what's wrong, just fix that line"Error text reports where it surfaced, not where it started; trace to the cause.
"I'll just retry, it was probably flaky"Uninvestigated flakes become incidents; reproduce or explicitly classify with evidence.

Red Flags

  • Changing code before stating a hypothesis
  • Closing as flaky without rerun evidence or a tracking issue
  • Fix without a regression test

See Also

  • test-runner — Execute tests and diagnose failures inside a test suite
  • iterative-refinement — Repeat-until-pass validation loops once the cause is known
  • security-code-auditor — Vulnerability analysis, not failure diagnosis

References

  • evals/evals.json — diagnostic cases incl. misleading-error negative

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