A weekly updated, lightweight JSON registry tracking official agent skills and last updated data. Free and open for any developer to use.
SaferSkills independently audited agent-skills-list (Agent Skill) and scored it 100/100 (green). The audit ran 55 deterministic rules across Security, Supply Chain, Maintenance, Transparency, and Community; it found 0 high-severity and 0 lower-severity findings. The full rule-by-rule trace and per-finding evidence are below. Free, methodology-open.
Findings & checks · 0 flagged
Every scanned point with the score it earned and what moved between them.
First recorded scan — no prior version to compare against.
The primary manifest — the file an agent reads to learn what this artifact does.
A public registry tracking official agent skills, their current versions, and their installation commands.
This repository contains a single skills.json file. An automated script runs weekly to check official sources and the GitHub API for updates, updating the last updated week data accordingly.
You can access the raw data directly at this URL: https://raw.githubusercontent.com/raoz0r/agent-skills-list/main/skills.json
The JSON file is structured as an array of objects:
[
{
"name": "analyzing-financial-statements",
"owner": "anthropics",
"repo": "anthropic-cookbook",
"version": "2026.26",
"installCommand": "npx skills add [https://github.com/anthropics/anthropic-cookbook](https://github.com/anthropics/anthropic-cookbook) --skill analyzing-financial-statements"
},
{
"name": "applying-brand-guidelines",
"owner": "anthropics",
"repo": "anthropic-cookbook",
"version": "2026.26",
"installCommand": "npx skills add [https://github.com/anthropics/anthropic-cookbook](https://github.com/anthropics/anthropic-cookbook) --skill applying-brand-guidelines"
}
]~30 seconds. Free. No account. Every finding cites a rule and a line of evidence.