菜单
Core behavioral corrections for LLM coding. Reduces over-engineering, surfaces assumptions, enforces surgical changes, and defines verifiable success criteria. Use when writing code, reviewing code, fixing bugs, or implementing features.
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
Clean up merged and stale branches from local and remote repositories. Use when branch list is cluttered or after merging PRs.
Generate document index files (manifest, bundles, graph, router) for project documentation. Creates docs/.index/ with searchable registry, feature-grouped bundles, cross-reference dependency graph, and query routing. Supports flat mode (generic projects, script-driven) and grouped mode (projects with doc_id frontmatter, Claude-curated).
Comprehensive markdown document review - anchors, accuracy, SSOT, cross-references, and redundancy analysis.
Enforce complete implementation of all tiers/difficulty levels for tiered features. Prevents partial implementations.
Create well-structured GitHub issues using the 5W1H framework with proper labels and acceptance criteria.
Automate GitHub issue workflow - select issue, create branch, implement, build, test, and create PR.
| name | behavioral-guardrails |
| description | Core behavioral corrections for LLM coding. Reduces over-engineering, surfaces assumptions, enforces surgical changes, and defines verifiable success criteria. Use when writing code, reviewing code, fixing bugs, or implementing features. |
| iso_class | none |
Correct common LLM coding pitfalls. Inspired by Andrej Karpathy's observations.
