菜单
This skill should be used when the user asks to "fix bug", "resolve issue", "fix error", "troubleshoot", "debug", or reports a specific bug or error that needs investigation and fixing.
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
基于 SOC 职业分类
| name | fix-bug |
| argument-hint | bug description or issue number |
| description | This skill should be used when the user asks to "fix bug", "resolve issue", "fix error", "troubleshoot", "debug", or reports a specific bug or error that needs investigation and fixing. |
Bug description: $ARGUMENTS
framing, Trace → plan, Fix → implement, Verify → verifyapproach options upstream conditional — required if multiple layer-fix candidates or missing pattern/review-architecture if layer interactions changed; /security-review if security-relevant) → completion gate (/review-pr)[hotfix] / [긴급] exception is the natural escape for time-critical fixes; verify still mandatory/fix-bug recursively. Do not invoke /plan-feature from insideRead docs/ai/shared/skills/fix-bug.md for detailed steps.
Also refer to docs/ai/shared/project-dna.md §6 for conversion patterns and §9 for router patterns.
Inspect drift between code, shared workflow references, and Claude, Codex, or Antigravity harness assets after architecture or workflow changes.
This skill should be used when the user asks to "sync guidelines", "document inspection", "check skill updates", "update project-dna", "sync patterns", "verify code-document consistency", or after architecture changes to verify Skills/AGENTS.md/CLAUDE.md match the actual code.
Guide a feature from requirements interview through architecture analysis, security check, and task decomposition.
This skill should be used when the user asks to "plan feature", "design feature", or wants to plan and design a new feature before implementation.
Audit a domain or the full repository for architecture compliance using the shared architecture checklist and repository rules.
Review a pull request or local diff against the repository's shared Review Protocol (correctness, regression, stability, contract, architecture, security, governance).