GitSkills Dataset: 3.79M Agent Skill Files from GitHub
JeremyCMorgan · x · 2026-08-22
GitSkills is a new research dataset comprising 3.79 million SKILL.md files collected from 282,200 public GitHub repositories. Following the open specification introduced by Anthropic in October 2025, these files store instructions for language model agents. The deduplicated dataset is packaged as a single SQLite database enriched with metadata, enabling empirical research on the adoption, reuse, structure, authorship, maintenance, and security of agent skills.
Related event: Over half of GitHub Agent skill files are duplicates(2 posts)→
More from coding & agent
- YC F26's Praxis launches AI agents to run law firm ops end to end — ycombinator · 2026-10-16
- Codex's year-long rise: 40M+ weekly users and its leader now runs all of OpenAI's core products — danshipper · 2026-10-16
- Developer builds inter-agent messaging for his AI agents — complete with message undo — baditaflorin · 2026-10-16
- How Codex Happened: inside OpenAI's comeback in coding — danshipper · 2026-10-16
- iOS 'dots' workflow: one Siri command turns screenshots into a background shopping and saving agent — nickbaumann_ · 2026-10-16
- Your widget tree is already a list of options: where Jev fits in Flutter — rseroter · 2026-10-16