技能图审核
- 作者仓库星标 289
- 作者仓库 claude-night-market
- 领域
- 安全
- 作者声明的智能体
- 未找到明确声明;不据此推断已兼容或已测试
- 静态检查
- 88 / 100 · 启发式扫描,不代表运行安全
- 运行环境证据
- 未执行;当前没有隔离运行测试证据
- 作者 / 版本 / 许可证
- @athola · 未声明许可证
- 上下文用量评级
- 低消耗
- 接入复杂程度
- 即装即用
- 是否需要外部接口密钥
- 不需要
- 兼容的系统
- macOS · Linux · Windows
- 运行环境要求
- Node.js
- 检测到的文件与系统行为
-
- 只读
- 网络行为
- 允许外网请求
- 安装命令数
- 无(仅作为资料)
需要注意: 未声明工具权限范围;实际权限由运行环境决定。
python3 plugins/abstract/scripts/skill_graph.py \
--plugins-root plugins --top-n 10
# Skill Graph Audit
## Overview
Build a directed graph of `Skill(plugin:name)` invocations across the
marketplace and surface composition patterns: which skills are heavily
referenced (hubs), which orchestrate many others (orchestrators), which
have no incoming or outgoing references (isolates), and which point at
non-existent skills (dangling references).
The federation graph is now derivable from source rather than
hand-curated.
## When To Use
- Before a documentation pass on skill composition
- After a renaming or retirement to catch broken `Skill()` references
- During quarterly audits to spot orphaned skills
- When evaluating consolidation candidates (hubs are higher-risk to merge)
- When a new skill's outbound references should be sanity-checked
## When NOT To Use
- For per-skill quality scoring, use `Skill(abstract:skills-eval)` instead
- For frontmatter/structure validation, use `Skill(abstract:plugin-review)`
- For hook-specific audits, use `Skill(abstract:hooks-eval)`
## Quick Start
```bash
python3 plugins/abstract/scripts/skill_graph.py \
--plugins-root plugins --top-n 10
```
For machine-readable output:
```bash
python3 plugins/abstract/scripts/skill_graph.py \
--plugins-root plugins --format json --output reports/skill-graph.json
```
See `modules/usage.md` for full CLI reference and example workflows.
## Core Outputs
| Output | Meaning | Action when high |
|--------|---------|------------------|
| Hubs | Most-referenced skills | Treat as core API; retire with extreme care |
| Orchestrators | Skills that call many others | Verify each ref still resolves |
| Isolates | Zero in / zero out | Check role: library? entrypoint? typo? |
| Dangling: bugs | Missing internal target | Fix immediately (typo or retired skill) |
| Dangling: external | Reference to external plugin | Document plugin dependency |
| Dangling: placeholders | Template text like `-NAME` | Verify intentional |
See `modules/interpretation.md` for false-positive guidance and
isolation taxonomy.
## Dogfood Evidence
This skill itself was scaffolded TDD-first; on first run against
`plugins/`, it caught two genuine dangling refs that the manual
audit (2026-04-25) had missed:
- `attune:makefile-generation -> abstract:makefile-dogfooder`
(script name confused with skill name)
- `imbue:karpathy-principles -> spec-kit:speckit-clarify`
(command referenced as skill)
Both were converted to correct command-style references in the
same session.
## Verification
Two ways to validate the audit output is trustworthy:
1. **Test-suite correctness check**: Run `pytest -o addopts=
plugins/abstract/tests/scripts/test_skill_graph.py` to confirm
extraction, graph construction, ranking, isolate detection, and
dangling-ref classification all pass on the current code. The
`-o addopts=` flag bypasses the package-wide coverage gate, which
would otherwise fail on a single-file run.
2. **Round-trip smoke check**: Note the dangling-ref count from a
baseline run, fix one or more flagged references, then rerun and
verify the count drops by at least the number fixed. If the count
does not move, the report is stale or the regex missed a syntax
variant.
## Exit Criteria
- [ ] The graph builds: `skill_graph.py` runs against `plugins/`
without error and emits a node/edge count.
- [ ] Dangling references are classified into bugs, external, and
placeholders (the three `Core Outputs` rows resolve).
- [ ] Every `Dangling: bugs` entry is either fixed in the same
session or filed as a tracked issue.
- [ ] `pytest -o addopts= plugins/abstract/tests/scripts/test_skill_graph.py`
passes.
- [ ] The round-trip smoke check shows the dangling-ref count drops
by at least the number of references fixed.
## Related Skills
- `Skill(abstract:skills-eval)`: per-skill quality scoring
- `Skill(abstract:plugin-review)`: plugin manifest and structure
- `Skill(abstract:hooks-eval)`: hook-specific validation
- `Skill(abstract:rules-eval)`: rules directory validation
## References
- Implementation: `plugins/abstract/scripts/skill_graph.py`
- Tests: `plugins/abstract/tests/scripts/test_skill_graph.py`
- Composition documentation:
`docs/quality-gates.md#skill-level-quality-gate-composition`
- Skill role taxonomy: `docs/skill-integration-guide.md#skill-role-taxonomy`
章节与文件索引
按说明文件中的顺序排列。
概述
何时使用
何时不使用
快速入门
核心输出
文件/命令 -> Skill(plugin:name) · Skill() · Skill(abstract:skills-eval) · Skill(abstract:plugin-review) · Skill(abstract:hooks-eval) · modules/usage.md · -NAME · modules/interpretation.md
内容校验值 -> eccc79dca41a
当前原文的自动摘译,尚未人工审校。
概述
构建跨市场和表面组合模式的
Skill(plugin:name)调用的有向图:哪些技能被大量引用(中心),哪些技能协调许多其他技能(协调器),哪些没有传入或传出引用(隔离),哪些技能指向不存在的技能(悬空引用)。何时使用
在文档传递技能组合之前 重命名或退役之后,以捕获损坏的
Skill()参考 在季度审核期间发现孤立的技能 评估整合候选者时(中心合并风险较高) 何时应对新技能的出站参考进行健全性检查何时不使用
对于每项技能的质量评分,请使用
Skill(abstract:skills-eval)对于 frontmatter/结构验证,请使用Skill(abstract:plugin-review)对于特定于钩子的审核,请使用Skill(abstract:hooks-eval)快速入门
对于机器可读的输出:请参阅
modules/usage.md以获取完整的 CLI 参考和示例工作流程。核心输出
输出 · 含义 · 高 Hubs 时的操作 · 最常引用的技能 · 视为核心 API;极其小心地退休 协调员 · 调用许多其他人的技能 · 验证每个裁判是否仍然解析隔离 · 归零/归零 · 检查角色:库?入口点?错字?悬空:错误·缺少内部目标·立即修复(拼写错误或已退役的技能)