Skills Collection

Agent skills are the open standard for packaging specialized knowledge into portable folders. A skill is just a SKILL.md plus optional scripts, references, and assets — installable in Claude Code, OpenCode, Gemini CLI, Codex, Cursor, and 40+ other agents. One skill, every tool.

This collection is a curated catalog, not a registry. The skills.sh marketplace has thousands of unaudited skills; ~26% of them carry security issues ranging from prompt injection to credential exfiltration. Discovery is no longer the bottleneck — judgment is. Launch-baseline entries were reviewed against the open standard and tagged with what we checked and when. The October 2026 guides use a narrower contract: pinned source inspection, explicit non-goals, and no runtime or model-review claim. Either way, review is transparency, not a trust seal: repos change silently, so we ship instructions on every page for you to verify the skill with your own models before installing.

What's in the collection

Each entry links to its full page — find-skills, skill-creator, Superpowers, Anthropic Official Skills, Gemini Skills, HF Skill Pack, Taste-Skill, and Archify.

New skill guides (October 2026)

Eighteen source-inspected guides were added on 2026-10-23 and 2026-10-24. They follow a different review contract from the launch-baseline pages: each one states its pinned revision, what was inspected, and what was not done. None of them was runtime-tested, installed, or model-reviewed. Treat the "Verify it yourself" section on each page as the gate, not this catalog listing.

The open standard

Skills conform to agentskills.io, the open format originally developed by Anthropic and now adopted by ~40 products. Every skill is a folder with a SKILL.md:

my-skill/
├── SKILL.md          # Required: frontmatter + instructions
├── scripts/          # Optional: executable code
├── references/       # Optional: documentation
└── assets/           # Optional: templates, resources

SKILL.md frontmatter has six fields (name, description, license, compatibility, metadata, allowed-tools) and the body is loaded only on skill activation — agents use progressive disclosure so installing 20 skills doesn't cost 20 instruction sets upfront. The same skill file runs unmodified in Claude Code, OpenCode, Codex, and Gemini CLI.

Install it once, run it anywhere

npx skills add <github-org>/<repo>

How to read a skill page

Every skill page follows the same template so you can compare them at a glance:

1. Overview — what it does, who maintains it, adoption signal
2. When to use / when not — the realistic job
3. How it works — the SKILL.md anatomy, scripts, progressive disclosure
4. Install tabs — npx skills add, Claude Code, OpenCode, Codex
5. Source and revision — pinned commit, access date, and either a full-source embed where the license and review permit it or a link to the canonical copy
6. "Verify it yourself" — the condensed red-flag checklist + a copyable review prompt you can paste into your own model
7. Review transparency — what we checked, what we did not, and when
8. Source + credits + license — where it came from, what you can do with it

Before you install anything

Start with the Vetting Guide to learn the methodology, then find-skills to discover more.

Related

• Agent Skills — Open Standard — the conceptual primer
• Skill Packs — the curated pack concept
• Executable Multi-File Skills — when skills go beyond SKILL.md
• Building Antigravity + OpenCode Skills — first-person build log