iannuttall/claude-agents vs anthropics/skills
anthropics/skills scores higher overall: 81/100 (A-tier) against 49/100 (Deprecated-tier). iannuttall/claude-agents leads on no dimension; anthropics/skills leads on reliability, skill leverage, documentation. Scored 2026-07-07, methodology v1.0.
Dimension by dimension
| Dimension | claude-agents-iannuttall | anthropic-skills |
|---|---|---|
| Reliability | 52 | 78 |
| Skill Leverage | 58 | 82 |
| Documentation | 66 | 88 |
| Maintenance | 10 | 85 |
| Safety / Governance | 54 | 80 |
| Evaluation Readiness | 30 | 60 |
| Composability | 62 | 88 |
| Adoption (capped) | 48 | 90 |
| Overall | 49 · Deprecated | 81 · A |
The entries
An early custom-subagent collection for Claude Code, archived by its maintainer in 2025. Indexed with a deprecation warning as format…
Anthropic's first-party public skill collection: the de facto reference for SKILL.md structure, frontmatter conventions, and…
Frequently asked questions
iannuttall/claude-agents or anthropics/skills?
anthropics/skills scores higher overall (81 vs 49, methodology v1.0). But they are the same category, so the dimension table below is the real answer.
How is this comparison generated?
Both scorecards come from the same public rubric with evidence notes, scored by the same editorial process. This page presents them side by side; it adds no new judgments beyond the scores themselves.