Menu
Investigate and fix a GitHub issue or bug report. Reads the issue, reproduces it, identifies root cause, implements fix, adds regression test.
Install with Codex or Claude Copy this prompt, paste it into Codex, Claude, or another assistant, and let it review the skill page and install it for you.
Based on SOC occupation classification
Automated visual testing with Playwright MCP - test web apps, presentations, websites, and documents with scalable reviewer perspectives
Expert guidance on RAG (Retrieval-Augmented Generation) system design including chunking strategies, embedding selection, retrieval methods, and vector database choices
Design complex system architectures, evaluate tradeoffs, and make critical technical decisions requiring deep reasoning
Deep code analysis identifying subtle bugs, security issues, performance problems, and architectural concerns requiring expert-level reasoning
Efficient context state inspection, task lifecycle management, and session tracking
Systematic codebase onboarding. Builds a mental model of a new or unfamiliar project by exploring structure, architecture, key data models, entry points, and auth patterns.
| name | fix-issue |
| description | Investigate and fix a GitHub issue or bug report. Reads the issue, reproduces it, identifies root cause, implements fix, adds regression test. |
| short_desc | investigate + fix GitHub issue + regression test |
| keywords | ["GitHub issue","bug report","regression test","root cause","fix bug","fix this bug","bug fix","resolve issue","debug and fix","repro the bug","reproduce the issue"] |
| argument-hint | [issue-url-or-description] |
| model | sonnet |
Structured workflow for investigating and fixing a reported bug or GitHub issue.
/fix-issue 42 # Fix GitHub issue #42 (reads via gh CLI)
/fix-issue "auth fails on logout" # Fix by description
/fix-issue # Fix current known bug (from CONTEXT_STATE.md)
If issue number provided:
gh issue view <number>
Otherwise, read description from the prompt or CONTEXT_STATE.md.
Extract:
KG-first: hybrid_search("error description or symptom")
Code graph: search_code_graph("function or component name")
Then Grep: for exact error messages, function names, stack traces
Run existing tests to confirm failure:
pytest tests/ -k "relevant_test" -v
If no existing test covers it, write a failing test first (TDD approach).
Read the relevant files. Trace the execution path. Document root cause in 1-2 sentences before writing any fix.
test_<bug_description>_regressionpytest tests/ -q # all pass
pytest tests/ -k "regression" # new test passes
gh issue close <number> --comment "Fixed in <commit>. Added regression test."
Summary: