Skill audit report
Use when writing or reviewing AI agent configs, system prompts, or tool definitions (JSON/YAML/Python) and you need to catch ambiguous tool descriptions, missing stop conditions, schema/description mismatches, or embedded prompts before they reach runtime. Deterministic static analysis, no LLM or network calls.
The Trust Score helps an agent decide whether a skill is safe enough to shortlist before installation.
GitHub adoption
INFO62
127 GitHub stars
Stars/forks activity
WARN57
127 stars, 12 forks; issue activity unavailable in current metadata
Recent maintenance
PASS100
3d since push
License clarity
PASS86
Apache-2.0
README/SKILL.md completeness
PASS86
Metadata includes enough usage and workflow context
Dependency/runtime risk
INFO62
command execution surface, external package install surface
Install availability
PASS92
npx skills add hermes-labs-ai/lintlang --skill lintlang
Install command safety
PASS92
standard package or runtime install path
Permission surface
FAIL36
shell or command execution, filesystem or document access
Repository evidence
PASS86
https://github.com/hermes-labs-ai/lintlang/tree/main/.agents/skills/lintlang
Review status
WARN46
AI review approval is missing
Agent Proven outcomes
INFO54
No agent outcome data yet
Checks
Install path
92
npx skills add hermes-labs-ai/lintlang --skill lintlang
Repository
88
https://github.com/hermes-labs-ai/lintlang/tree/main/.agents/skills/lintlang
License
86
Apache-2.0
Maintenance
100
3d since push
AI review
55
Review approval is missing
README/SKILL.md completeness
86
Usable description available
Dependency risk
62
command execution surface, external package install surface
Install command safety
92
standard package or runtime install path
Permission surface
36
shell or command execution, filesystem or document access
Stars/forks activity
57
127 stars, 12 forks; issue activity unavailable in current metadata
Adoption
68
127 GitHub stars
Warnings
Method
This report combines public metadata, AI review output, repository freshness, install readiness, OpenAgentSkill events, quality scoring, trust checks, and the agent safety gate. It is not a full source-code security review.
Compare nearby options