Sandbox
@runkids/skillshare

CLI sync tool for AI skills and agents

skillshare keeps skills, agents, rules, and other reusable files in one source and syncs them to AI CLI tools like Claude Code, Codex, Cursor, and Gemini CLI. It uses a Go binary plus config, schemas, and target integrations to move content into each tool’s expected format and location.

2,644 stars163 forksGoUpdated 6d ago
Who it's for

Builders who want one shared source for AI CLI skills, agents, and rules across their tools and machines.

What it delivers

You can update shared agent files once and push them to every supported CLI tool with one sync.

What it does

Sync skills across tools

Copies or links skills from the shared source into supported AI CLI targets with `skillshare sync`.

Manage agents and extras

Keeps custom agents, rules, commands, prompts, and other file-based resources in the same workflow.

Audit before install

Scans skills for prompt injection and data exfiltration with `skillshare audit`.

Project and org sharing

Supports per-repo `.skillshare/` setups and tracked repositories for team-wide sharing.

Web dashboard

Provides a local UI with `skillshare ui` for browsing and managing skills.

Target-specific filtering

Lets you control what reaches each target with `.skillignore`, target settings, and include/exclude rules.

How to get it

  1. 1Run
    curl -fsSL https://raw.githubusercontent.com/runkids/skillshare/main/install.sh | sh
  2. 2Run
    irm https://raw.githubusercontent.com/runkids/skillshare/main/install.ps1 | iex
  3. 3Run
    brew install skillshare
  4. 4Add an alias to your shell config (~/.zshrc or ~/.bashrc)
    alias ss='skillshare'
  5. 5Run
    skillshare init            # Create config, source, and detected targets
    skillshare sync            # Sync skills to all targets

README

skillshare

skillshare

Website License: MIT Release Platform Go Report Card Ask DeepWiki

Star on GitHub

runkids%2Fskillshare | Trendshift

One source of truth for AI CLI skills, agents, rules, commands & more. Sync everywhere with one command — from personal to organization-wide.
Codex, Claude Code, OpenClaw, OpenCode & 60+ more.

skillshare demo

WebsiteInstallQuick StartHighlightsScreenshotsDocs

[!NOTE] Latest: v0.20.0 — choose what commit/push/pull version with git_root scope (skills, agents, extras, or all together in one repo); extras extension transforms convert Markdown to native formats (Gemini TOML commands, Codex TOML agents) during sync. All releases →

Why skillshare

Every AI CLI has its own skills directory. You edit in one, forget to copy to another, and lose track of what's where.

skillshare fixes this:

  • One source, every agent — sync to Claude, Cursor, Codex & 60+ more with skillshare sync
  • Agent management — sync custom agents alongside skills to agent-capable targets
  • More than skills — manage rules, commands, prompts & any file-based resource with extras
  • Install from anywhere — GitHub, GitLab, Bitbucket, Azure DevOps, or any self-hosted Git
  • Built-in security — audit skills for prompt injection and data exfiltration before use
  • Team-ready — project skills in .skillshare/, org-wide skills via tracked repos
  • Local & lightweight — single binary, no registry, no telemetry, fully offline-capable
  • Fine-grained filtering — control which skills reach which targets with .skillignore, SKILL.md targets, and per-target include/exclude

Coming from another tool? Migration Guide · Comparison

How It Works

  • macOS / Linux: ~/.config/skillshare/
  • Windows: %AppData%\skillshare\
┌─────────────────────────────────────────────────────────────┐
│                    Source Directory                         │
│   ~/.config/skillshare/skills/    ← skills (SKILL.md)       │
│   ~/.config/skillshare/agents/    ← agents                  │
│   ~/.config/skillshare/extras/    ← rules, commands, etc.   │
└─────────────────────────────────────────────────────────────┘
                              │ sync
              ┌───────────────┼───────────────┐
              ▼               ▼               ▼
       ┌───────────┐   ┌───────────┐   ┌───────────┐
       │  Claude   │   │  OpenCode │   │ OpenClaw  │   ...
       └───────────┘   └───────────┘   └───────────┘
PlatformSkills SourceAgents SourceExtras SourceLink Type
macOS/Linux~/.config/skillshare/skills/~/.config/skillshare/agents/~/.config/skillshare/extras/Symlinks
Windows%AppData%\skillshare\skills\%AppData%\skillshare\agents\%AppData%\skillshare\extras\NTFS Junctions (no admin required)
Imperative (install-per-command)Declarative (skillshare)
Source of truthSkills copied independentlySingle source → symlinks (or copies)
New machine setupRe-run every install manuallygit clone config + sync
Security auditNoneBuilt-in audit + auto-scan on install/update
Web dashboardNoneskillshare ui
Runtime dependencyNode.js + npmNone (single Go binary)

Full comparison →

CLI and UI Preview

Skill DetailSecurity Audit
CLI sync outputCLI install with security audit
UI DashboardUI Skills
Web dashboard overviewWeb UI skills page

Installation

macOS / Linux

curl -fsSL https://raw.githubusercontent.com/runkids/skillshare/main/install.sh | sh

Windows PowerShell

irm https://raw.githubusercontent.com/runkids/skillshare/main/install.ps1 | iex

Homebrew

brew install skillshare

Tip: Run skillshare upgrade to update to the latest version. It auto-detects your install method and handles the rest.

GitHub Actions

- uses: runkids/setup-skillshare@v1
  with:
    source: ./skills
- run: skillshare sync

See setup-skillshare for all options (audit, project mode, version pinning).

Shorthand (Optional)

Add an alias to your shell config (~/.zshrc or ~/.bashrc):

alias ss='skillshare'

Quick Start

skillshare init            # Create config, source, and detected targets
skillshare sync            # Sync skills to all targets

Highlights

Install & update skills —from GitHub, GitLab, or any Git host

skillshare install github.com/reponame/skills
skillshare update --all
skillshare target claude --mode copy  # if symlinks don't work

Symlink issues? — switch to copy mode per target

skillshare target <name> --mode copy
skillshare sync

Security audit —scan before skills reach your agent

skillshare audit

Project skills —per-repo, committed with your code

skillshare init -p && skillshare sync

Agents —sync custom agents to agent-capable targets

skillshare sync agents            # sync agents only
skillshare sync --all             # sync skills + agents + extras together

Extras —manage rules, commands, prompts & more

skillshare extras init rules          # create a "rules" extra
skillshare sync --all                 # sync skills + extras together
skillshare extras collect rules       # collect local files back to source

Shell completion —tab-complete commands, flags, and subcommands

skillshare completion bash --install   # also: zsh, fish, powershell, nushell

Local checkpoints — commit source changes without pushing

skillshare commit -m "Update review skill"
skillshare commit --dry-run

Web dashboard — visual control panel

skillshare ui

All commands & guides →

Contributing

Contributions welcome! Open an issue first, then submit a draft PR with tests. See CONTRIBUTING.md for setup details.

git clone https://github.com/runkids/skillshare.git && cd skillshare
make check  # format + lint + test

[!TIP] Not sure where to start? Browse open issues or try the Playground for a zero-setup dev environment.

Contributors

Thanks to everyone who helped shape skillshare.

leeeezx Vergil333 romanr xocasdashdash philippe-granet terranc benrfairless nerveband EarthChen gdm257 skovtunenko TyceHerrman 1am2syman thealokkr JasonLandbridge masonc15 richardwhatever reneleonhardt ndeybach hhh2210 leoarry salmonumbrella daylamtayari dstotijn ipruning massukio kevincobain2000 StephenPAdams mk-imagine Curtion amdoi7 jessica-engel AlimuratYusup thor-shuang bishopmatthew chaosky iFwu ildunari aestilog xarthurx m0cun bit3125 eekryuos Bongseop-Kim sophodex PeterTianbuhan dotned ismferd jblackburn21 jnhu76 jacobleft rhysmcneill druellan 12britz askpatrickw Almost42 Brett-Best isCopyman svob michal-grzelak shikbupt LeoYeAI TIR44 Ajaymamtora vishaldialpad kankan0829 dnabb thinhngotony skaurus jamesbraza 2BAB zdlldz elstiaan EriaWalker FaintFlower yantinglin21 chung1912 r-fynn cescox hhdebb Snurppa


If you find skillshare useful, consider giving it a ⭐

Star History

Star History Chart


License

MIT

Files in the repo

Repository payload36 top-level entries
  • .codegraph
  • .devcontainer
  • .github
  • .mdproof
  • .skillshare
  • .vscode
  • ai_docs
  • cmd
  • docker
  • extensions
  • internal
  • proposals
  • schemas
  • scripts
  • skills
  • tests
  • ui
  • video
  • website
  • .air.toml
  • .dockerignore
  • .gitignore
  • .goreleaser.yaml
  • .pre-commit-hooks.yaml
  • .skillignore
  • CHANGELOG.md
  • CONTRIBUTING.md
  • docker-compose.sandbox.yml
  • go.mod
  • go.sum
  • install.ps1
  • install.sh
  • LICENSE
  • Makefile
  • mise.toml
  • README.md

Discussion (0)

Ask about usage, or say what you built with it

Sign in to join the discussion.

No comments yet. Be the first to say what this is good for.

More tools

JuliusBrussee/
caveman

🪨 why use many token when few token do trick — Claude Code skill that cuts 65% of tokens by talking like caveman

105k
1 add
MemPalace/
mempalace

The best-benchmarked open-source AI memory system. And it's free.

59k
stablyai/
orca

Orca is the ADE for working with a fleet of parallel agents. Run any coding agent with your own subscription. Available on desktop, mobile and remote runtime.

66k

A cross-platform desktop All-in-One assistant for Claude Code, Codex, OpenCode, OpenClaw, Grok Build & Hermes Agent. Only official website: ccswitch.io

132k

Never stop coding. Free MIT AI gateway: one endpoint, 352 providers (150+ free), 1200+ models Kimi, Claude, GPT, Gemini, GLM, DeepSeek, MiniMax. Works with Claude Code, Codex, Cursor, OpenCode, Cline & Copilot. Quota-aware auto-fallback, RTK+Caveman compression saves 15-95% tokens, MCP/A2A, Desktop/PWA. Built by 550+ contributors

64k
headroomlabs-ai/
headroom

Compress tool outputs, logs, files, and RAG chunks before they reach the LLM. 20% fewer tokens for coding agents, 60-95% fewer tokens for JSON, same answers. Library, proxy, MCP server.

71k