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".
git clone https://github.com/rohitg00/pro-workflow.git--- 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.
[{"step":"Provide the bug description conversationally. Include any user-reported steps to reproduce, expected vs. actual outcomes, and impact (e.g., 'Users lose drafts when typing fast').","tip":"Avoid technical jargon or file paths. Focus on the user experience and business impact."},{"step":"Specify a draft title (optional). If omitted, the AI will generate one based on the bug description.","tip":"Use a concise title that describes the issue from the user’s perspective, e.g., 'Mobile users cannot upload images from gallery'."},{"step":"Let the AI explore the codebase silently for context. It will infer the relevant components/features without exposing internal details.","tip":"If the bug is domain-specific (e.g., e-commerce checkout), mention the feature name to help the AI focus (e.g., 'This is related to the cart persistence feature')."},{"step":"Review the generated GitHub issue. Adjust the title, priority, or labels if needed, then copy-paste it into your repository.","tip":"Use GitHub’s issue templates or labels to standardize formatting. The AI’s output can be pasted directly or lightly edited for tone."},{"step":"Close the loop with the user who reported the bug. Share the issue link and thank them for the report.","tip":"Link the issue in your response to the user (e.g., 'I’ve filed this as [GitHub Issue #123](link) and assigned it to the team. Thanks for catching this!')."}]
No install command available. Check the GitHub repository for manual installation instructions.
git clone https://github.com/rohitg00/pro-workflow/tree/main/skills/bug-captureCopy the install command above and run it in your terminal.
Launch Claude Code, Cursor, or your preferred AI coding agent.
Use the prompt template or examples below to test the skill.
Adapt the skill to your specific use case and workflow.
A user reported: "[BUG_DESCRIPTION]". Capture this as a GitHub issue in the project's domain language. Do not include file paths, line numbers, or stack traces. Instead, describe the behavior in terms of user impact and expected vs. actual outcomes. If context is needed, explore the codebase silently to understand the feature's purpose. Issue title: [TITLE_IDEA].
### **Issue: User cannot save drafts in the editor when typing quickly** **Description** When editing a document, users who type rapidly (e.g., 3+ words per second) lose unsaved changes if they navigate away or refresh the page. The editor does not auto-save drafts during rapid input, unlike slower typing patterns where drafts are retained. **Steps to Reproduce** 1. Open a document in the editor. 2. Type at least 3 words per second for 5+ seconds. 3. Without pausing, navigate to another page or refresh. 4. Return to the document—unsaved changes are lost. **Expected Behavior** The editor should auto-save drafts at regular intervals (e.g., every 2 seconds) regardless of typing speed, ensuring no data loss during rapid input. **Additional Context** This issue was reported by a user during a QA session. The editor’s draft-saving mechanism currently relies on a debounce timer that may not trigger consistently under high typing loads. The feature is part of the `DocumentEditor` component, which handles real-time collaboration and offline persistence. **Priority**: Medium (data loss risk) **Labels**: `bug`, `editor`, `data-loss`
skills-collection
Take a free 3-minute scan and get personalized AI skill recommendations.
Take free scan