agentleFS
Sign inStart free
toilanguyen2910toilanguyen2910/claude-code-starter-pack/skills/bug-report/SKILL.md

bug-report

Skill1 starsChanged 40 days agoMITView on GitHub

Turns a description of broken behavior into a structured bug report with reproduction steps, and optionally investigates the likely cause in the codebase. Use when the user reports something is broken, wants to file an issue, or asks to debug a problem.

33 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use setup-engine, team-polish 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.
  • CoralGameSkill

    setup-engine

    Configure the project's game engine and version. Pins the engine in CLAUDE.md, detects knowledge gaps, and populates engine reference docs via WebSearch when the version is beyond the LLM's training data.

    Also in 13 projects that use this

  • CoralGameSkill

    team-polish

    Orchestrate the polish team: coordinates performance-analyst, technical-artist, sound-designer, and qa-tester to optimize, polish, and harden a feature or area for release quality.

    Also in 15 projects that use this

  • lilangMaxSkill

    asset-spec

    Generate per-asset visual specifications and AI generation prompts from GDDs, level docs, or character profiles. Produces structured spec files and updates the master asset manifest. Run after art bible and GDD/level design are approved, before production begins.

    Also in 10 projects that use this

  • lilangMaxSkill

    create-control-manifest

    After architecture is complete, produces a flat actionable rules sheet for programmers — what you must do, what you must never do, per system and per layer. Extracted from all Accepted ADRs, technical preferences, and engine reference docs. More immediately actionable than ADRs (which explain why).

    Also in 10 projects that use this

  • +4 more from CoralGame
  • +4 more from lilangMax

The file

We split this skill into the rules it gives an agent

7 rules. 0 are common, 7 are distinctive, and 0 are very specific to this project.

  • 0

    Common

    Most of the 31 edited versions we read keep these.

  • 7

    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 the user's description is missing pieces (no repro steps, no expected vs.

    line 34
  2. Distinctive:

    Search the codebase for the error message, function name, or relevant keywords using Grep/Glob.

    line 40
  3. Distinctive:

    Read the surrounding code to form a hypothesis about the cause.

    line 42
  4. Distinctive:

    If you can reproduce it locally (e.g.

    line 45
  5. Distinctive:

    If this is going into an issue tracker, output the report as a single markdown block ready to paste.

    line 50
  6. Distinctive:

    If investigation found a likely cause, add a Suspected cause section with file:line references, separate from the user-facing report.

    line 52
  7. Distinctive:

    Don't open a fix without being asked — this skill's job is to produce a clear report, not to silently patch things.

    line 54

“Common” is measured: kept by at least 6 in 10 of the 31 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

Bug report

Step 1: Structure the report

Turn $ARGUMENTS (or the user's most recent description) into this format:

## Summary
One sentence: what's broken.

## Steps to reproduce
1. ...
2. ...
3. ...

## Expected behavior
What should happen.

## Actual behavior
What happens instead, including exact error messages or stack traces if any.

## Environment
- OS / platform:
- Version / commit:
- Relevant config:

If the user's description is missing pieces (no repro steps, no expected vs. actual distinction), ask for the minimum needed to fill the template rather than inventing plausible-sounding steps.

Step 2: Investigate (only if asked, or if the fix looks quick)

  1. Search the codebase for the error message, function name, or relevant keywords using Grep/Glob.
  2. Read the surrounding code to form a hypothesis about the cause.
  3. State the hypothesis explicitly and how confident you are — don't present a guess as a confirmed diagnosis.
  4. If you can reproduce it locally (e.g. a script or test), do so before proposing a fix.

Step 3: Output

  • If this is going into an issue tracker, output the report as a single markdown block ready to paste.
  • If investigation found a likely cause, add a Suspected cause section with file:line references, separate from the user-facing report.
  • Don't open a fix without being asked — this skill's job is to produce a clear report, not to silently patch things.

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