菜单
Decompile any SKILL.md into deterministic YAML for structural security analysis. Extracts permissions, surfaces, risk signals, and produces a scored verdict.
默认使用会先检查来源的 Prompt；你也可以切换为直接命令，或下载本地副本。
决定是否安装前，请先阅读 SKILL.md，以及 SkillsMP 当前展示的配套文件。
基于 SOC 职业分类
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。
直接命令不会经过审查 Prompt；运行前请先检查来源。
npx skills add https://github.com/lev-os/agents --skill skill-decompile命令会保持在同一行。复制前请横向滚动并检查完整内容。
想先保存到本地？可下载 SkillsMP 当前能够提供的文件。
正在显示 SKILL.md
| name | skill-decompile |
| description | Decompile any SKILL.md into deterministic YAML for structural security analysis. Extracts permissions, surfaces, risk signals, and produces a scored verdict. |
| skill_type | tool |
| category | security |
| allowed-tools | Bash(python3:*), Read |
| argument-hint | <skill.md> [--output yaml|json] [--verbose] | --dir <path> [--report] |
Converts freeform SKILL.md files into normalized, machine-auditable YAML structures. Bridges the gap between human-authored skill definitions and deterministic security scanning.
# Single file
python3 ~/.agents/skills-db/security/skill-decompile/decompile.py ~/.agents/skills/auth-sniffer/SKILL.md
# Single file, JSON output
python3 ~/.agents/skills-db/security/skill-decompile/decompile.py ~/.agents/skills/auth-sniffer/SKILL.md --output json --verbose
# Scan entire skills directory with summary report
python3 ~/.agents/skills-db/security/skill-decompile/decompile.py --dir ~/.agents/skills/ --report
# Full directory scan as YAML
python3 ~/.agents/skills-db/security/skill-decompile/decompile.py --dir ~/.agents/skills/ --output yaml
| Category | Details |
|---|---|
| meta | name, description, skill_type, source (local/external) |
| permissions | allowed_tools, requests for bash/write/network/env |
| surfaces | URLs, shell commands, env vars, file paths |
| risk_signals | eval, base64, obfuscation, exfil patterns, prompt injection |
| complexity | line count, code blocks, reference files, decision tree depth |
| verdict | risk_score (0-100), risk_level, specific flags |
Routes adaptive multi-agent deliberation with fractal context cycles. Use when using /cdo, think/deep/debug/parliament work, or long runs paired with autoresearch scheduling.
Use when you need an evidence-first provenance report from `cass`, repo docs, `.lev`, `~/.agents/diagrams`, `qmd`, or Grep/Glob tools.
Use the codebase knowledge graph for structural code queries. Triggers on: explore the codebase, understand the architecture, what functions exist, show me the structure, who calls this function, what does X call, trace the call chain, find callers of, show dependencies, impact analysis, dead code, unused functions, high fan-out, refactor candidates, code quality audit, graph query syntax, Cypher query examples, edge types, how to use search_graph.