Update to AI DevKit

{
  "name": "structured-debug",
  "description": "AI DevKit · Guide structured debugging before code changes by clarifying expected behavior, reproducing issues, identifying likely root causes, and agreeing on a fix plan with validation steps. Use when users ask to debug bugs, investigate regressions, triage incidents, diagnose failing behavior, handle failing tests, analyze production incidents, investigate error spikes, or run root cause analysis (RCA).",
  "included_files": [
    {
      "relative_path": "agents/openai.yaml",
      "size_in_bytes": 322
    }
  ],
  "skill_md_contents": "---\nname: structured-debug\ndescription: AI DevKit · Guide structured debugging before code changes by clarifying expected behavior, reproducing issues, identifying likely root causes, and agreeing on a fix plan with validation steps. Use when users ask to debug bugs, investigate regressions, triage incidents, diagnose failing behavior, handle failing tests, analyze production incidents, investigate error spikes, or run root cause analysis (RCA).\n---\n\n# Local Debugging Assistant\n\nDebug with an evidence-first workflow before changing code.\n\n## Hard Rule\n- Do not modify code until the user approves a selected fix plan.\n\n## Workflow\n\n1. Clarify\n- Restate observed vs expected behavior in one concise diff.\n- Confirm scope and measurable success criteria.\n- Before investigating, search for similar past incidents: `npx ai-devkit@latest memory search --query \"<observed behavior>\" --tags \"debug,root-cause\"`\n\n2. Reproduce\n- Capture minimal reproduction steps.\n- Capture environment fingerprint: runtime, versions, config flags, data sample, and platform.\n\n3. Hypothesize and Test\nFor each hypothesis, include:\n- Predicted evidence if true.\n- Disconfirming evidence if false.\n- Exact test command or check.\n- Prefer one-variable-at-a-time tests.\n\n4. Plan\n- Present fix options with risks and verification steps.\n- Recommend one option and request approval.\n\n## Validation\n- Confirm a pre-fix failing signal exists.\n- Confirm post-fix success using the `verify` skill — including regression verification for bug fixes.\n- Summarize remaining risks and follow-ups.\n- Store root cause and fix for future sessions: `npx ai-devkit@latest memory store --title \"<root cause>\" --content \"<diagnosis and fix>\" --tags \"debug,root-cause\"`\n\n## Task Tracing\n\nIf task tracing is usable, choose a short kebab-case debug task name when no\ntask name exists, then use `task` optionally: record repro/final results as\n`evidence`, the current hypothesis as `next`, and blockers only when they\nmaterially affect progress. Never block debugging because task tracing is\nunavailable.\n\n## Red Flags and Rationalizations\n\n| Rationalization | Why It's Wrong | Do Instead |\n|---|---|---|\n| \"I already know the cause\" | Assumptions skip evidence | Reproduce and prove it first |\n| \"This is urgent, just fix it\" | A wrong fix wastes more time | 10 minutes of diagnosis saves hours |\n| \"The fix is obvious from the stack trace\" | Stack traces show symptoms, not causes | Trace backward to the root cause |\n\n## Output Template\nUse this response structure:\n- Observed vs Expected\n- Repro and Environment\n- Hypotheses and Tests\n- Options and Recommendation\n- Validation Plan and Results\n- Open Questions\n"
}