The private skills registry for your team

Your team already runs on AI skills. Nobody controls which version.

Playbooks, procedures, and coding standards become version-controlled skills in your GitHub repo — reviewed by PR, assigned by role, synced to every person and agent with one command.

Free to evaluate No credit card GitHub is the source of truth
~/.claude/skills/
$ skillinvoke sync
Fetching skill manifest...
Found 12 skills across 3 packs.
 
frontend/react-patterns ··········
frontend/css-standards ···········
backend/rails-conductor ··········
backend/api-standards ············
shared/code-review ··············
... and 7 more
 
Sync complete: 12 installed, 0 unchanged.
 
$

Built on the open Agent Skills standard

Claude Code MCP REST API CLI

Plain Markdown your agents already read. Nothing proprietary, nothing to migrate.

The problem

Your teams already give company knowledge to AI. Most of it is invisible, unreviewed, and trapped with individual experts.

Knowledge trapped in people and prompts

Critical playbooks live with subject-matter experts or in private AI conversations that the company cannot reuse.

No approval or review process

Agent instructions change without ownership, version history, or agreement on the approved way to work.

Zero visibility for leads

Engineering managers have no idea what instructions their team's AI agents are following.

New joiners start from scratch

Institutional knowledge about how to use AI effectively stays locked in individual machines.

How it works

Three steps to governed AI skills

01

Write SKILL.md files in your repo

No proprietary format. No new language to learn. Each directory with a SKILL.md becomes a skill. Use YAML frontmatter for metadata, Markdown for instructions. Your team already knows how.

  • Open Markdown format with CLI, API, and MCP access
  • Full git history and version control
  • Easy to write, review, and understand
frontend/react-patterns/SKILL.md
1---
2name: React Patterns
3description: Standard React component patterns
4category: Frontend
5tags: [react, components, hooks]
6user-invocable: true
7---
8
9# React Patterns
10
11When building React components, follow
12these conventions:
13
14## Component Structure
15- Use functional components with hooks
16- Extract custom hooks for shared logic
terminal
$ skillinvoke list
 
PACKS
──────────────────────────────────────────
Frontend Essentials 4 skills [mandatory]
Backend Toolkit 5 skills
Shared Standards 3 skills [mandatory]
 
SKILLS PACK
──────────────────────────────────────────
react-patterns Frontend Essentials
css-standards Frontend Essentials
testing-guide Frontend Essentials
accessibility Frontend Essentials
rails-conductor Backend Toolkit
... 7 more

02

Bundle and govern in SkillInvoke

Group related skills into packs. Mark them as mandatory or optional. Assign by team or role. Edits go through pull requests, so changed playbooks and policies do not reach assigned people until someone approves them.

  • Mandatory and optional pack policies
  • PR-based review workflow
  • Role-based team assignments

03

Sync the right skills to every person and agent

One command to install. One command to sync. Single Go binary, zero dependencies. Sync globally or per-project — skills land exactly where your AI tools expect them.

  • Install with a single curl command
  • --global for shared skills, --project for repo-specific
  • SHA-verified downloads, secure by default
terminal
# Install the CLI
$ curl -fsSL https://skillinvoke.com/install.sh | sh
Installed to /usr/local/bin/skillinvoke
 
# Authenticate (opens browser)
$ skillinvoke login
Authenticated as acme-corp
 
# Pull skills globally or per-project
$ skillinvoke sync # → ~/.claude/skills/
$ skillinvoke sync --project # → .claude/skills/
 
Sync complete: 12 installed, 0 unchanged.
$

Features

Everything teams need to govern AI skills

GitHub-native

Skills live in your repo as SKILL.md files — the open Agent Skills format. Full git history. No vendor lock-in. GitHub is the source of truth.

Pack system

Bundle related skills into mandatory or optional packs. Assign by role, team, or project. Define in YAML or manage in the app.

PR workflow

Edits go through pull requests for review. Approve or request changes before skills reach assigned users and agents.

CLI sync

Single Go binary. No runtime dependencies. Install via curl. Sync globally or per-project with one command.

Feedback & analytics

Developers rate skills after use. See what's working, what isn't, and who's contributing the most value.

Audit trail

Every edit, sync, and assignment is logged with full provenance. Export audit logs for compliance reporting.

Pricing

Evaluate alone. Govern skills as a team.

Start free for one user. Upgrade when company knowledge needs controlled distribution.

Free

£0

For one person evaluating version-controlled AI skills.

  • 10 skills
  • 1 user
  • 1 pack
  • CLI sync

FAQ

Common questions

Why can't I just write scripts or keep a shared folder of prompts?

You can, and most teams start there. But a shared folder can't assign skills by role, revoke access when someone leaves, or tell you which version anyone is actually running. SkillInvoke adds PR review, assigned skill packs, controlled distribution, and an audit trail — while the skills themselves stay as plain Markdown in your repo.

Claude already has skills built in. Why do I need this?

For one person, it's enough. For a team, the question is control: who approved this skill, who's assigned it, and is anyone running a stale version? SkillInvoke adds PR review, role-based assignment, and sync on a flat £39/month — no per-seat enterprise plan required. Anthropic's own enterprise docs recommend keeping skills in Git and implementing your own sync process. SkillInvoke is that process, productised.

Is this vendor lock-in? What if I stop using SkillInvoke?

No lock-in. Your skills are plain Markdown files stored in your own GitHub repo; we never host or own them. Pack manifests are YAML. If you cancel, nothing changes in your repo and previously synced files remain under your control.

Isn't this just another abstraction layer I don't need?

No. There's no SDK, no wrapper, no background process. The CLI is a single binary that copies approved files from your repo to your skills directory — closer to a deployment tool than an abstraction layer. Your AI tools read the same SKILL.md files they always would; SkillInvoke just makes sure the right ones reach the right machines.

How can AI tools access SkillInvoke skills?

The CLI provides first-class Claude Code sync. Other agent workflows can retrieve approved skills through the REST API or MCP endpoint. The source files remain open Markdown, so additional delivery adapters can be added without migrating your content.

Where are my skills actually stored?

In your GitHub repository. SkillInvoke reads SKILL.md files from your repo — it never stores skill content on our servers. GitHub is the source of truth. If you stop using SkillInvoke, your skills stay exactly where they are.

How do team members install the CLI?

Single binary, no dependencies. Run curl -fsSL https://skillinvoke.com/install.sh | sh to install. Then skillinvoke login to authenticate via browser and skillinvoke sync to pull skills. Use --project to sync to the current repo instead of globally. Takes about two minutes.

Can SkillInvoke access or modify my code?

No. We use a GitHub App with read-only access to the specific repository you connect. We read SKILL.md files and pack manifests. We cannot see your source code, push commits, or modify anything in your repo.

Can I use SkillInvoke for free?

Yes. The free plan covers 10 skills, one user, and one pack — enough to prove the workflow on your own machine before involving the team. No credit card required. Upgrade to Team when you need assigned packs, PR review, analytics, and seats for up to 15 people.

What happens if I cancel?

Your skills stay in your GitHub repo — we never touch them. The CLI continues to work with whatever was last synced. Your access to the web dashboard continues until the end of your billing period. No lock-in, no data hostage.

Stop the AI skill free-for-all.

Give every team and AI agent the approved skills they need.

Free forever for small teams. 14-day trial of Team features.