Skill audit report
Compose For Agents audit report.
Build and run AI agents using Docker Compose. A collection of ready-to-use examples for orchestrating open-source LLMs, tools, and agent runtimes.
OpenAgentSkill Trust Score
Stars, maintenance, license, docs, dependency risk, and installability.
The Trust Score is OpenAgentSkill's adoption layer. It is designed to help an agent decide whether a skill is safe enough to shortlist before installation.
GitHub adoption
INFO76
980 GitHub stars
Recent maintenance
PASS100
11d since push
License clarity
PASS86
Apache-2.0
README/SKILL.md completeness
PASS100
Metadata includes enough usage and workflow context
Dependency risk
INFO80
external package install surface
Install availability
PASS92
npx skills add docker/compose-for-agents
Repository evidence
PASS86
https://github.com/docker/compose-for-agents
Review status
PASS88
AI review data available
Checks
Install and adoption review
Install path
92
npx skills add docker/compose-for-agents
Repository
88
https://github.com/docker/compose-for-agents
License
86
Apache-2.0
Maintenance
100
11d since push
AI review
88
Approved with no listed issues
README/SKILL.md completeness
100
Usable description available
Dependency risk
80
external package install surface
Adoption
88
980 GitHub stars
Warnings
- Quality score needs review
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