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

Builders who want one shared source for AI CLI skills, agents, and rules across their tools and machines.
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
- 1Run
curl -fsSL https://raw.githubusercontent.com/runkids/skillshare/main/install.sh | sh
- 2Run
irm https://raw.githubusercontent.com/runkids/skillshare/main/install.ps1 | iex
- 3Run
brew install skillshare
- 4Add an alias to your shell config (~/.zshrc or ~/.bashrc)
alias ss='skillshare'
- 5Run
skillshare init # Create config, source, and detected targets skillshare sync # Sync skills to all targets
README
skillshare
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.
Website • Install • Quick Start • Highlights • Screenshots • Docs
[!NOTE] Latest: v0.20.0 — choose what
commit/push/pullversion 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.mdtargets, 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 │ ...
└───────────┘ └───────────┘ └───────────┘
| Platform | Skills Source | Agents Source | Extras Source | Link 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 truth | Skills copied independently | Single source → symlinks (or copies) |
| New machine setup | Re-run every install manually | git clone config + sync |
| Security audit | None | Built-in audit + auto-scan on install/update |
| Web dashboard | None | skillshare ui |
| Runtime dependency | Node.js + npm | None (single Go binary) |
CLI and UI Preview
| Skill Detail | Security Audit |
|---|---|
![]() | ![]() |
| UI Dashboard | UI Skills |
|---|---|
![]() | ![]() |
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 upgradeto 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
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.
If you find skillshare useful, consider giving it a ⭐
Star History
License
MIT
Files in the repo
- .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 itSign in to join the discussion.
No comments yet. Be the first to say what this is good for.
More tools
The best-benchmarked open-source AI memory system. And it's free.
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.

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



















































































