← 返回 Skills 市场

Nm Abstract Skill Graph Audit

Name: Nm Abstract Skill Graph Audit
Author: athola

作者 athola · GitHub ↗ · v1.0.0 · MIT-0

cross-platform ✓ 安全检测通过

总下载

当前安装

版本数

在 OpenClaw 中安装

/install nm-abstract-skill-graph-audit

功能描述

Audit Skill() refs; detect hubs, isolates, and dangling targets

使用说明 (SKILL.md)

Night Market Skill — ported from claude-night-market/abstract. For the full experience with agents, hooks, and commands, install the Claude Code plugin.

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

python3 plugins/abstract/scripts/skill_graph.py \
  --plugins-root plugins --top-n 10

For machine-readable output:

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:

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.
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.

Related Skills

Skill(abstract:skills-eval) -- per-skill quality scoring
Skill(abstract:plugin-review) -- plugin manifest + 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

安全使用建议

Install if you want this workflow assistance. As with any agent skill that can guide tool use, review requested commands before allowing account, GitHub, moderation, or other high-impact changes.

能力评估

✓ Purpose & Capability

The reviewed artifacts fit a workflow-assistance purpose and do not show unrelated data access, exfiltration, destructive behavior, or deceptive capability claims.

ℹ Instruction Scope

The skill may guide the agent to use local or service-specific tools when the user asks for those workflows, but the behavior is disclosed and user-directed rather than automatic or hidden.

✓ Install Mechanism

No suspicious installer, package hook, background worker, or automatic execution mechanism was identified in the supplied scan context or inspected artifacts.

ℹ Credentials

Use of existing workspace tools or authenticated services is proportionate when the user explicitly requests those tasks; no credential harvesting or unexpected environment capture was found.

✓ Persistence & Privilege

No unbounded persistence, privilege escalation, or hidden long-running behavior was identified.

如何使用

确保已安装 OpenClaw（本地或 Docker 部署）
在对话框中输入安装命令：/install nm-abstract-skill-graph-audit
安装完成后，直接呼叫该 Skill 的名称或使用 /nm-abstract-skill-graph-audit 触发
根据 Skill 的参数说明提供必要输入，即可获得结构化输出

版本历史

v1.0.0

- Initial release of skill-graph-audit for auditing Skill() references across the marketplace - Identifies graph patterns: hubs, orchestrators, isolates, and dangling skill references - Supports machine-readable and CLI output for integration into workflows - Provides actionable guidance for each report type (e.g., how to address dangling or isolated skills) - Includes verification steps and test coverage for reliable audits - Documents related audit skills for deeper or alternative analyses

元数据

Slug nm-abstract-skill-graph-audit

版本 1.0.0

许可证 MIT-0

累计安装 0

当前安装数 0

历史版本数 1

常见问题