bug-capture — Claude Code skill: what it does and how to install
bug-capture is a Claude Code skill that turns reported defects into GitHub issues using the project’s own terms. It activates after a conversational bug report, a QA pass, or a request to file an issue.
MIT ★ 2,966 updated 2026-09-29
/plugin marketplace add rohitg00/pro-workflow
/plugin install pro-workflow@pro-workflowWhat bug-capture does
bug-capture asks for missing details about expected behavior, actual results, reproduction steps, or how often the defect occurs. While the reporter responds, it explores the relevant part of the codebase and checks a project glossary when one is available.
Before filing, the skill searches existing open and closed issues with gh issue list. If it finds a likely match, it asks whether to comment there instead. Independent failure modes become separate issues with dependency links; gh issue create files them.
Issue bodies describe behavior and reproduction steps, not file paths, line numbers, function names, or PR numbers. The search and filing steps use the GitHub CLI gh.
What it helps with
- turn a conversational bug report into a GitHub issue
- check for matching issues before opening another
- split independent failure modes into linked issues
- record reproduction steps without tying the report to code locations
Example prompts for the agent
- Turn this bug report into a GitHub issue.
- I found a defect during QA; ask for any missing details and file it.
- Search for matching issues, then record this behavior as a bug.
How to install bug-capture
1Plugin marketplace
/plugin marketplace add rohitg00/pro-workflow/plugin install pro-workflow@pro-workflowThis installs the whole pro-workflow plugin with all its skills
2Skills CLI (Vercel)
npx skills add rohitg00/pro-workflow --skill bug-capture -a claude-code3Manually: put the files in place
~/.claude/skills/bug-capture/SKILL.mdCopy the whole skill folder; for one project use .claude/skills/bug-capture/
1Skills CLI (Vercel)
npx skills add rohitg00/pro-workflow --skill bug-capture -a codex2Manually: put the files in place
.agents/skills/bug-capture/SKILL.mdFor all projects use ~/.agents/skills/
1Skills CLI (Vercel)
npx skills add rohitg00/pro-workflow --skill bug-capture -a cursor2Manually: put the files in place
.cursor/skills/bug-capture/SKILL.mdCursor also reads .agents/skills/ and .claude/skills/
1GitHub CLI
gh skill install rohitg00/pro-workflow skills/bug-capture2Manually: put the files in place
.github/skills/bug-capture/SKILL.md1Skills CLI (Vercel)
npx skills add rohitg00/pro-workflow --skill bug-capture -a gemini-cli2Platform CLI
gemini skills install https://github.com/rohitg00/pro-workflow --path skills/bug-captureManually: put the files in place
.devin/skills/bug-capture/SKILL.mdThe legacy .windsurf/skills/ path still works
Claude.ai
Zip the folder and upload it in Settings → Capabilities → Skills
Step by step, with commands for each platform: How to install skills in Claude Code: five ways
Questions about bug-capture
How do I install bug-capture in Claude Code?
Add the marketplace with /plugin marketplace add rohitg00/pro-workflow, then install the skill with /plugin install pro-workflow@pro-workflow.
What does bug-capture do?
It turns a reported defect into a GitHub issue, searches for duplicates, and separates independent failure modes into linked issues. Reports focus on behavior and reproduction steps rather than code locations.
What does bug-capture need to work?
It uses the GitHub CLI gh to search issues with gh issue list and file them with gh issue create.
Source text
SKILL.md · MIT
--- name: bug-capture description: Capture a user-reported defect as a durable GitHub issue written in the project's own domain language. Explores the codebase in parallel for context but never leaks file paths or line numbers into the issue. Use when the user reports a bug conversationally, runs a QA pass, or says "file an issue", "log this as a bug", "capture this". --- # bug-capture Turn a conversation into an issue that still reads correctly after a major refactor. ## Flow ### 1. Listen, then clarify minimally Let the user describe the problem in their own words. Ask at most two short clarifying questions, drawn from: - Expected behavior vs. actual behavior. - Concrete reproduction steps if not already implied. - Frequency: deterministic, intermittent, or one-off. If the description already answers these, skip straight to filing. Over- interviewing is a tax the reporter pays for your uncertainty. ### 2. Explore in parallel While the user is answering, start a background exploration of the relevant area. The goal is **not** to propose a fix. The goal is to absorb the project's own vocabulary — the nouns and verbs the codebase uses for this feature — so the issue reads like it was written by a maintainer. If the repo has a glossary file (common names: GLOSSARY.md, UBIQUITOUS_LANGUAGE.md, docs/domain.md), read it first. ### 3. Check for duplicates before filing Run `gh issue list --search "<key phrase>" --state all --limit 10`. If a live or recently closed issue matches, surface it to the user and ask whether to add a comment instead of opening a new issue. Do not silently skip filing. ### 4. Decide: single issue or breakdown Break down when the report contains two or more independent failure modes that a different contributor could fix in parallel. Keep as one when every symptom traces to a single wrong behavior. For a breakdown, file in dependency order so each child issue can reference a real parent number, and mark honest `Blocked by` links. Avoid inventing dependencies to make the tree look tidier. ### 5. File with `gh issue create` File without asking the user to review the draft. Send back the URLs. #### Single-issue template ``` ## What happened <observed behavior, in domain terms> ## What I expected <expected behavior> ## Reproduction 1. <step> 2. <step> 3. <step> ## Context <anything that narrows where the bug lives, in domain terms — e.g. "only affects the import path, not the export path"> ``` #### Child-issue template ``` ## Parent #<parent-number> ## What is wrong <one behavior, narrow slice> ## What I expected <expected for this slice> ## Reproduction 1. <step> ## Blocked by <#issue or "none — independent"> ## Context <notes that apply only to this slice> ``` ### 6. Rules that apply to every issue body - No file paths, line numbers, function names, or PR numbers. These go stale. Describe behavior, not code. - Use the project's domain nouns, not generic tech terms. "The sync worker drops the patch" beats "`applyPatch()` throws". - Reproduction steps are mandatory. If you cannot derive them, go back to the user once before filing. - Thirty-second read target. Cut anything that does not help a maintainer decide whether to pick it up. ### 7. Keep going After each issue, print the URL and ask whether there is a next one. Do not batch multiple reports into one filing pass — each bug deserves its own scoped issue.
© Rohit Ghumare · MIT · rohitg00/pro-workflow