メニュー
Investigate agent-side failures in the autofix-skills plugin. Covers wrong verdicts, review loop issues, state machine bugs, and prompt problems. Use when the agent ran but produced wrong results.
Codex または Claude でインストール この Prompt をコピーして Codex、Claude、または他のアシスタントに貼り付けると、Skill ページを確認してインストールできます。
SOC 職業分類に基づく
Use when assessing a Jira bug ticket for AI autofix readiness. Produces a structured JSON verdict (ready/needs_info/not_fixable) based on a three-gate rubric. Designed for CI pipeline use with the autofix pipeline orchestrator.
Use when orchestrating CVE remediation for a Jira Vulnerability ticket. Uses a Python state machine (cve_pipeline.py) for deterministic routing between scan, fix, verify, VEX, review, and PR creation agents. Never writes fix code directly.
Use when orchestrating a Jira ticket fix end-to-end. Dispatches to implement and review prompt agents in a loop, uses state.py for persistence, and evaluates findings to decide iteration. Never writes code directly.
| name | debug-autofix-skills |
| description | Investigate agent-side failures in the autofix-skills plugin. Covers wrong verdicts, review loop issues, state machine bugs, and prompt problems. Use when the agent ran but produced wrong results. |
| allowed-tools | Bash Read Grep Glob |
Investigate failures in the agent-side layer: skill prompts, review orchestration, verdict generation, and state management.
| Area | Entry point |
|---|---|
| Orchestration | skills/autofix-resolve/SKILL.md, skills/autofix-cve-resolve/SKILL.md |
| Triage | skills/autofix-triage/SKILL.md |
| State machine | scripts/state.py (duplicated in each skill's scripts/ dir) |
| Review merging | scripts/merge_findings.py |
| Verdict writing | scripts/write_json.py + schemas/*.json |
| Prompts | prompts/*.md within each skill directory |
| Hook recovery | hooks/hooks.json, tmp/dispatch-recovery.sh |
AGENTS.md for architecture context.