agentleFS
alexzhu0alexzhu0/agent-ready-skills/skills/bug-report-to-repro/SKILL.md

bug-report-to-repro

Skill0 starsChanged 5 months agoMITView on GitHub

Use when converting bug reports, user complaints, screenshots, logs, or QA notes into a reproducible case with environment, steps, expected behavior, actual behavior, and missing evidence.

The file

We split this skill into the rules it gives an agent

3 rules. About 0 are common, 3 are distinctive, and 0 are 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.

  • 0

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Use when a bug report has enough symptom evidence to form a reproducible test path or triage brief.

    line 14
  2. Distinctive:

    Do not use when the request is root-cause debugging without a concrete observed failure.

    line 15
  3. Distinctive:

    Add diagnostic questions that would reduce uncertainty fastest.

    line 29

≈ “Common” is an estimate: at least 1 in 5 of the 364,980 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 To Repro

Purpose

Turn vague bug reports into a clear reproduction brief that engineering or QA can use.

Fit

  • Use when a bug report has enough symptom evidence to form a reproducible test path or triage brief.
  • Do not use when the request is root-cause debugging without a concrete observed failure.

Inputs

  • Bug text, screenshot notes, logs, environment details, or user complaint.
  • Version, browser, device, account role, feature area, and regression clues if available.
  • Known expected behavior.

Workflow

  1. Extract symptom, environment, user role, and affected feature.
  2. Draft the smallest plausible reproduction path.
  3. Separate known facts from missing evidence.
  4. Record expected versus actual behavior.
  5. Add diagnostic questions that would reduce uncertainty fastest.

Output

Produce Markdown with:

  • Reproduction Brief
  • Environment
  • Repro Steps
  • Expected Vs Actual
  • Evidence
  • Missing Data
  • Triage Notes

Validation

  • Steps are ordered and executable.
  • Expected behavior is not invented when unknown.
  • Missing environment details are listed.
  • Regression claims include the evidence source.
  • The brief is short enough to paste into an issue tracker.

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.