Menu
Fix QA issues: reads qa-issues.json written by superharness qa, fixes each issue using TDD, then re-runs QA to verify.
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
Session start guide: explains how to use superharness skills and conventions. Injected by SessionStart hook.
Superharness brainstorming skill. You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.
Use when implementation is complete, all tests pass, and you need to decide how to integrate the work - guides completion of development work by presenting structured options for merge, PR, or cleanup
Main entry point: end-to-end workflow for building features. Use /superharness:go 'requirement' to start. Orchestrates brainstorm → plan → TDD implementation → review → QA.
Infrastructure skill: start a local visualization server that renders Mermaid diagrams in the browser. Write .mmd files with pure Mermaid code, the browser updates in real-time via WebSocket (no page reload). Used by brainstorm, writing-plans, and other skills.
Surface unresolved decisions in a development request and ask the user before implementing. Use when starting a non-trivial dev task whose requirements leave open questions that would change the implementation (scope, data shape, UX behavior, compatibility), or when the user asks to confirm first ("先确认一下", "有不清楚的先问").
| name | sh-fix |
| description | Fix QA issues: reads qa-issues.json written by superharness qa, fixes each issue using TDD, then re-runs QA to verify. |
Read qa-issues.json and fix pending issues using TDD, then re-run QA to verify fixes.
superharness qa (CLI or /superharness:sh-qa skill) must have already run and written qa-issues.json to the current task directory.
cat .superharness/tasks/{task}/qa-issues.json
Filter for status: "pending" issues. Sort by severity: critical → major → minor → suggestion.
If no pending issues, report "No pending QA issues" and stop.
For each pending issue, in severity order:
"fixed" and increment fix_roundLog trace events:
echo '{"ts":"...","phase":"fix","event":"fix_start","detail":"修复中: {issue.id}"}' >> .superharness/tasks/{task}/trace.jsonl
echo '{"ts":"...","phase":"fix","event":"fix_complete","detail":"已修复: {issue.id}"}' >> .superharness/tasks/{task}/trace.jsonl
After fixing all critical and major issues, re-run QA:
superharness qa --task .superharness/tasks/{task}
This performs incremental verification:
If new issues appear or regressions are detected:
fix_round exceeds max_fix_rounds (default 3), mark remaining issues as "escalated"