Skill audit report

EasyLM audit report.

Large language models (LLMs) made easy, EasyLM is a one stop solution for pre-training, finetuning, evaluating and serving LLMs in JAX/Flax.

REVIEWED · REVIEWNeeds reviewGenerated Jun 16, 2026Heuristic metadata audit

Audit

Trust

Quality

Security

Maintain

Install

OpenAgentSkill Trust Score

Strong shortlist

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

PASS

2.5K GitHub stars

Recent maintenance

FAIL

2y since push

License clarity

PASS

Apache-2.0

README/SKILL.md completeness

PASS

Metadata includes enough usage and workflow context

Dependency risk

PASS

no major dependency risk hints in public metadata

Install availability

PASS

npx skills add young-geng/EasyLM

Repository evidence

PASS

https://github.com/young-geng/EasyLM

Review status

PASS

AI review data available

Checks

Install and adoption review

7 passed · 5 review

Install path

PASS

npx skills add young-geng/EasyLM

Repository

PASS

https://github.com/young-geng/EasyLM

License

PASS

Apache-2.0

Maintenance

FIX

2y since push

AI review

PASS

Approved with no listed issues

README/SKILL.md completeness

PASS

Usable description available

Dependency risk

PASS

no major dependency risk hints in public metadata

Adoption

PASS

2.5K GitHub stars

Warnings

Repository appears stale
Repository looks stale
Quality score needs review
Recent maintenance: 2y since push

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.

Install path

Review the report before installing into production agents.

$ npx skills add young-geng/EasyLM

Signals

Audit score: 78/100
Quality: 74/100
Trust: 85/100
Maintenance: 2y since push
Events: No events yet
GitHub stars: 2.5K
Last push: Aug 13, 2024

Agent safety v2

62/100 · Review before install

Reviewed with permission notesreview

Usable candidate, but the agent should surface permission and audit notes before installation.

Require human approval before installing into a real workspace.

Repository appears stale
62/100 agent safety score

Network access

medium

Skill likely fetches remote pages, APIs, repositories, or external services.

Filesystem access

medium

Skill may read or write project files, documents, generated artifacts, or local workspace state.

Repository appears stale

Back to skill Alternatives Audit badge SVG

Compare nearby options

EasyLM audit report.

Stars, maintenance, license, docs, dependency risk, and installability.

Install and adoption review

Related skills to audit next

Gpt4free

Chatbox

Chatwoot