We Scored the Skills Inside the Most-Starred Agent Repos. Star Count Is Not a Score.
Star counts are the only signal most people use when picking skills. We have per-skill scores for 74 skills spread across the seven most-starred agent repos. The two numbers barely talk to each other.
Here is the whole finding in one table. Stars are live from the GitHub API on 2026-10-10; scores are ours, on the six-dimension rubric, published per skill with written rationale.
| Repo | Stars | Skills we've scored | Score range | Highest |
|---|---|---|---|---|
| obra/superpowers | 297,128 | 14 | 7.9 – 9.1 | verification-before-completion (9.1) |
| anthropics/skills | 180,294 | 19 | 6.7 – 9.8 | xlsx (9.8) |
| DietrichGebert/ponytail | 160,220 | 6 | 8.0 – 9.0 | ponytail-review (9.0) |
| addyosmani/agent-skills | 104,373 | 24 | 7.9 – 9.5 | constraint-driven-development (9.5) |
| Egonex-AI/Understand-Anything | 85,826 | 9 | 7.0 – 9.0 | understand-explain (9.0) |
| ayghri/i-have-adhd | 56,254 | 1 | 9.0 | i-have-adhd (9.0) |
| OthmanAdi/planning-with-files | 27,374 | 1 | 8.3 | planning-with-files (8.3) |
A repo is not a skill
Look at the third column. anthropics/skills has 180k stars and a 6.7 at the bottom of its own range. addyosmani/agent-skills spans 7.9 to 9.5 across 24 skills. Understand-Anything spans 7.0 to 9.0.
That's the thing a star count can't express: a repo is a bundle, and the skills inside it were written at different times by different people with different amounts of care. Starring the repo tells you the bundle got attention. It tells you nothing about whether the skill you are about to install is the 9.8 or the 6.7.
We see this everywhere, not just here: the misses inside popular repos are usually the ones added last, when the repo was already popular and contributions started arriving faster than review.
The individual skills that scored highest
Across these seven repos, the top of the range belongs to:
xlsx(9.8) andclaude-api(9.8) — the official spreadsheet skill and the API reference. Both win on the same dimension: they verify their own output instead of declaring success.constraint-driven-development(9.5) — binds your agent to a written quality contract for the whole session. The most interesting idea in the set.i-have-adhd(9.0) andponytail/ponytail-review(9.0) — two very different answers to the same problem: agents that over-explain or over-build.verification-before-completion(9.1) — the discipline half of the superpowers suite, and the skill most worth stealing if you write your own.
What this table is not
It is not a ranking of the biggest repos. Three of the largest — mattpocock/skills (283k), affaan-m/ECC (276k), JuliusBrussee/caveman (110k) — aren't in the table because we haven't evaluated their skills yet. Same for claude-mem, impeccable, and scientific-agent-skills. A missing repo means we haven't scored it, not that it scored badly.
It is not a complete count of those repos either. We've scored 24 of addyosmani's skills and 14 of the superpowers suite; both have more. And every number here is a snapshot: stars move daily, and repositories add skills.
And a score is an opinion, not a fact. Ours is one rubric applied consistently — trigger quality, structure, workflow design, content, engineering, security — with the rationale written on every skill page so you can disagree with a specific number rather than the whole system.
The practical version
Pick skills, not repos. Open the repo, find the one skill that does the thing you need, and check whether anyone has read its scripts. If you use our scorecards as the filter, use them at that granularity — per skill, per version — because that's the only granularity at which the number means anything.
Every score above, with the written rationale and the security scan behind it, is on the skill page. The evaluation methodology is public, and the adversarial injection-test results for 47 of these skills are open data.