OpenAgentSkill
GitHub200+

Skill audit report

eval-code Audit report.

Write deterministic, code-based evaluator functions for an AI product. Use this skill whenever you need to write evaluators that check structural properties of AI outputs (format, count, presence, schema compliance) without calling another LLM. Also use when auditing existing code-based evaluators for brittleness, coverage gaps, or false positives.

EXPERIMENTAL · REVIEWNeeds reviewGenerated Nov 5, 2026Heuristic metadata audit
76
Audit
74
Trust
60
Quality
78
Security
100
Maintain
92
Install

OpenAgentSkill Trust Score

74
Strong shortlist

OpenAgentSkill Trust Score

The Trust Score helps an agent decide whether a skill is safe enough to shortlist before installation.

GitHub adoption

WARN

48

75 GitHub stars

Stars/forks activity

WARN

43

75 stars, 8 forks; issue activity unavailable in current metadata

Recent maintenance

PASS

100

19d since push

License clarity

PASS

86

MIT

README/SKILL.md completeness

PASS

86

Metadata includes enough usage and workflow context

Dependency/runtime risk

PASS

90

no major dependency risk hints in public metadata

Install availability

PASS

92

npx skills add Calibre-Labs/reforge-ai-evals --skill eval-code

Install command safety

INFO

68

dynamic command execution, standard package or runtime install path

Permission surface

INFO

74

filesystem or document access, database access

Repository evidence

PASS

86

https://github.com/Calibre-Labs/reforge-ai-evals/tree/main/skills/eval-code

Review status

WARN

46

AI review approval is missing

Agent Proven outcomes

INFO

54

No agent outcome data yet

Checks

Install and adoption review

6 Passed · 9 Needs review

Install path

92

PASS

npx skills add Calibre-Labs/reforge-ai-evals --skill eval-code

Repository

88

PASS

https://github.com/Calibre-Labs/reforge-ai-evals/tree/main/skills/eval-code

License

86

PASS

MIT

Maintenance

100

PASS

19d since push

AI review

55

CHECK

Review approval is missing

README/SKILL.md completeness

86

PASS

Usable description available

Dependency risk

90

PASS

no major dependency risk hints in public metadata

Install command safety

68

CHECK

dynamic command execution, standard package or runtime install path

Permission surface

74

CHECK

filesystem or document access, database access

Stars/forks activity

43

FIX

75 stars, 8 forks; issue activity unavailable in current metadata

Adoption

68

INFO

75 GitHub stars

Warnings

  • AI review approval is missing
  • Quality score needs review
  • GitHub adoption: 75 GitHub stars
  • Stars/forks activity: 75 stars, 8 forks; issue activity unavailable in current metadata
  • Review status: AI review approval is missing

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

Related skills to audit next

Code Review

Review a branch or diff against repository standards and the originating spec in two independent analysis passes.

169K Stars · Audit report

Appsmith

Platform to build admin panels, internal tools, and dashboards. Integrates with 25+ databases and any API.

41K Stars · Audit report

Vercel React Best Practices

React and Next.js performance guidance for writing, reviewing, and refactoring production UI code.

33K Stars · Audit report