New Open source · v0.5.0

Your team's AI skills, in one place — and on every agent.

Publish once — skael versions it, scans it for secrets and prompt injection, and syncs it to Claude Code, Cursor, Codex, and OpenCode on every machine. The only registry that shows you which skills actually fire — by which agent, how often, even in headless agentic runs.

Free for solo devs · self-host on day one
~/acme/skills — skael
$ skael setup https://skills.company.com sk-xxx Connected to skills.company.com Configuration saved Hook installed for claude-code Hook installed for codex Setup complete. Skills are live. $ skael publish ./code-review → scanning for security issues… ok → published code-review v5 (checksum a3f8…) $
6
platforms
macOS · Linux · Windows
4
agents
Claude · Cursor · Codex · OpenCode
30+
rules
security scan on every publish
1
command
skael setup and you're done
// capabilities

Run your skills like infrastructure — not scattered markdown.

Centralize, distribute, secure, and measure every SKILL.md across every agent your team uses.

Centralize, don't copy-paste

One source of truth for every skill. skael sync places them in each developer's Claude Code, Cursor, Codex, and OpenCode — across every project and machine. Update once; everyone gets it.

See what actually fires

Native telemetry counts "Skill" calls but never which skill. skael's hooks report every activation — which skill, which agent, how often, even in headless agentic runs. Turn "we have 50 skills" into "these 12 do the work."

Scanned before it ships

Every publish runs a security scan for hardcoded secrets, prompt injection, data exfiltration, and obfuscation. Critical findings block the publish — no curl | bash for your agent's brain.

Versioned by default

Every publish is an immutable, content-addressable version. Roll back, diff, and always know which version your team is actually on.

Instant search

Full-text search across skill names, descriptions, and content, with fuzzy matching on names. Find the right skill in milliseconds.

Self-hosted, no lock-in

One container against your own Postgres, or Docker Compose with a bundled database. Your skills stay on your infrastructure.

// the dashboard

Every skill, every version, every activation — one workspace.

app.skael.dev / acme / skills
skael dashboard — per-skill activations broken down by agent over 30 days
// three commands

Drop it into any agent stack in under a minute.

01 / INSTALL

Install the CLI.

Single binary for macOS, Linux, and Windows. No dependencies.

$ brew install skael-dev/skael/skael
02 / SETUP

Connect to your registry.

One command configures the CLI, syncs all skills, and installs activation tracking hooks for every detected agent.

$ skael setup https://skills.company.com sk-xxx
03 / PUBLISH

Share a skill.

Security scan runs automatically. Next time anyone runs skael sync, they get it.

$ skael publish ./code-review
// the obvious question

"Can't I just use a git repo?"

Can't I just commit .claude/skills/ to a repo?

You can — if everyone's on the same agent, in the same project, and remembers to pull. A git folder gives you a folder. It doesn't place skills into Cursor and Codex and OpenCode, doesn't sync across machines, doesn't scan for injection, doesn't tell you which version everyone's on, and has no idea which skills your agents actually use. skael is the layer that turns a folder of markdown into managed infrastructure.

Doesn't Claude already do org skill sharing?

For Claude.ai and Desktop, on Team and Enterprise plans — not Claude Code, and not Cursor, Codex, or OpenCode. skael is vendor-neutral by design: it manages the SKILL.md standard across every agent your team runs, not one vendor's walled garden.

Ship skills like you ship code.

Free and open source. Self-host on day one.

$ brew install skael-dev/skael/skael && skael setup copy