agentleFS
kakarot-oncloudkakarot-oncloud/claude-dev-skills/skills/bug-report-formatter/SKILL.md

bug-report-formatter

Skill0 starsChanged 7 months agoMITView on GitHub

Turns vague or chaotic bug descriptions into structured, reproducible bug reports with steps, expected vs actual behavior, environment, and severity. Use this skill when the user describes a problem they want to file as an issue, says "help me write a bug report", pastes error output, or asks to format something for GitHub Issues / Jira / Linear.

The file

We split this skill into the rules it gives an agent

4 rules. About 0 are common, 3 are distinctive, and 1 is very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈3

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 1

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Title: must name the component and the failure, not just "bug" or "issue".

    line 48
  2. Distinctive:

    Steps must be reproducible: If the user's description lacks them, ask for the missing pieces before formatting.

    line 49
  3. Distinctive:

    Read the user's description carefully.

    line 57
  4. Very specific:

    Ask one focused question if a critical piece is missing.

    line 59

≈ “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

Bug Report Formatter

You turn messy bug descriptions into reports a developer can act on without follow-up questions.

Output template

## Title
<short, specific, includes the component>

## Summary
<one sentence: what's broken>

## Steps to reproduce
1. <action>
2. <action>
3. <action>

## Expected behavior
<what should happen>

## Actual behavior
<what happens instead — include exact error messages>

## Environment
- OS:
- Browser / runtime:
- Version / commit:
- Relevant config:

## Severity
<critical | high | medium | low — with one-line justification>

## Logs / screenshots
<paste or placeholder>

## Additional context
<related issues, recent changes, workarounds tried>

Rules

  1. Title must name the component and the failure, not just "bug" or "issue".
  2. Steps must be reproducible. If the user's description lacks them, ask for the missing pieces before formatting.
  3. Quote exact error text verbatim — don't paraphrase stack traces.
  4. Severity based on impact: data loss / security / outage = critical; broken main flow = high; broken edge case = medium; cosmetic = low.
  5. Strip secrets from logs (tokens, emails, internal URLs) and replace with <redacted>.
  6. Omit sections that genuinely don't apply rather than padding with "N/A".

Process

  1. Read the user's description carefully.
  2. Identify what's missing for reproduction (steps, env, expected behavior).
  3. Ask one focused question if a critical piece is missing; otherwise format with what you have and flag gaps as <unknown — please confirm>.
  4. Output the report in a fenced markdown block, ready to paste.

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.