The State of Agent Skills — 2026 Q3

A reproducible snapshot of the public Agent Skills ecosystem on GitHub. Collected 20 October 2026.

Published by groclawa · data collected 2026-10-20

This is a reproducible snapshot of the public Agent Skills ecosystem on GitHub. It exists because the question we get most often isn't "how do I write a skill" — it's "which one should I install?" That's a discovery problem, and discovery problems need numbers.

Cite this page if you use the figures: groclawa, "The State of Agent Skills — 2026 Q3 snapshot", 20 October 2026, groclawa.com/research/state-of-agent-skills.


Headline numbers

MeasureValue
Repositories tagged agent-skills36,028
Repositories tagged claude-skills12,548
Repositories tagged claude-code101,543
Repositories whose metadata mentions SKILL.md4,332
Stars across the top 20 agent-skills repos1,867,707
agent-skills repos created since 2026-07-2022,576 (63%)
SKILL.md repos created since 2026-07-201,993 (46%)

The last two rows are the story. Nearly two-thirds of the tagged ecosystem appeared in a single quarter. Supply is not the constraint anymore; selection is.

Method

Limits. Topic tags are self-assigned, so the population is noisy in both directions: repos with skills but no tag are missed, and repos with the tag but no SKILL.md are included. Treat the numbers as an order-of-magnitude signal, not a census.

What the top of the ecosystem looks like

RepoStarsWhat it is
morluto/rea335,933Reverse-engineering agent toolkit
anthropics/skills182,216The official Agent Skills repository
DietrichGebert/ponytail168,030"Laziest senior dev" reasoning skill
addyosmani/agent-skills108,601Production engineering skills
paperclipai/paperclip104,689Agent management app
nexu-io/open-design102,510Collaborative design agent workspace
Leonxlnx/taste-skill99,326Art direction and reference skills
tt-a1i/archify85,828Idea/codebase → interactive diagram

Two patterns worth noting:

  1. The official repo is not the biggest. Community collections outrank it, which means discovery happens in lists, not in docs.
  2. "Taste" repos are huge. Three of the top eight sell design judgement rather than engineering capability. That's the same thesis our catalog is built on.

What this means if you sell skills

1. A catalog is not a moat; curation is. With 36k repos, "we have 400 skills" is not a value proposition. "We tested 400 and kept 60" is.

2. Install counts beat star counts for buyers. Stars measure developer attention. A buyer wants to know whether the thing runs on their agent version. Publish both, and publish the failure cases.

3. Comparison pages will outperform list pages. In a crowded category, "X vs Y" and "best for Z" queries carry the intent. Lists get skimmed; comparisons get read.

4. The long tail is agent-specific. Skills that work in Claude Code may not load in Windsurf, and the folder layout differs. Pages that answer "does this work in my agent" convert far better than generic skill pages.

Reproducing this

curl -s "https://api.github.com/search/repositories?q=topic:agent-skills&sort=stars&per_page=20"
curl -s "https://api.github.com/search/repositories?q=topic:agent-skills+created:%3E2026-07-20&per_page=1"

Re-run quarterly. The delta between snapshots is more interesting than any single number.

Suggested citation formats

There are more than 36,000 repositories tagged agent-skills on GitHub, and 63% of them were created after July 2026 (groclawa, State of Agent Skills, Oct 2026).
The official anthropics/skills repository has 182k stars, but community collections outrank it — discovery happens in lists, not documentation (groclawa, Oct 2026).
Want the raw data?

The 60-row repo table behind this report is available as CSV. Cite the figures with the date and URL above.

Download the CSV → · Browse tested skills →