Files
Willie 3f999b8e85 docs: show team sharing workflows and honest security boundaries
The intro and team pages still described skillshare as a sync tool for one
person, and some security wording promised more than the code does:
"symlink isolation" implied a sandbox, and audit read as runtime
protection. Teams evaluating skillshare need to know what is actually
shared, pinned and enforced.

- Intro and READMEs open with the positioning and a team example: one
  checklist in .skillshare/, shared by teammates on different tools.
- Team onboarding follows the real project flow: install -p (honoring
  skills.lock.json), audit with a threshold, then sync.
- The hub guide walks through a private hub over SSH: an index at the repo
  root or a //path, a pinned CLI version in CI, and pinned actions.
- The security pages separate what audit, .skillignore, the lockfile and
  each AI tool's own permissions control. Blocking follows finding
  severity, not the risk score.
- The SARIF CI example now fails the job on findings. With audit-output
  set, setup-skillshare only records the exit code.

All pages are mirrored to ja, ko, zh-Hans and zh-Hant.
2026-10-02 22:11:39 +08:00

4.9 KiB

sidebar_position, slug
sidebar_position slug
1 /

Introduction

Your AI coding setup, everywhere.

skillshare manages skills, agents, rules, MCP connections and hooks in one place. Use the desktop app or CLI to keep your setup with you as you switch AI tools, machines or projects.

Why skillshare?

  • Switch tools, keep your setup — maintain a source you control and choose what each supported tool receives.
  • Take your setup with you — version your source in Git and bring it to another machine.
  • Share project context — keep team skills and configuration alongside your code, with remote skill commits recorded in a lockfile.

For example, one teammate uses Claude Code and another uses Codex. Both need the same code-review checklist for a legacy API. Keep that checklist in .skillshare/skills/ and commit the project configuration. New teammates install the declared remote skills and sync to the configured targets, instead of finding and copying instructions from chat.

Follow the team onboarding recipe for the full workflow. Shared instructions reduce configuration drift; each AI tool still has its own capabilities, permissions and behavior.

Quick Start

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

If the installer prints PATH setup instructions, follow them before running the commands below. If it prints no PATH warning, no extra setup is needed.


# Initialize (auto-detects CLIs, sets up git)
skillshare init

# Install a skill
skillshare install anthropics/skills/skills/pdf

# Sync to all targets
skillshare sync

Your skill is now available to the configured targets.

:::tip[Try without installing] Want to explore first? Use the Docker Playground — one command, no local install needed:

git clone https://github.com/runkids/skillshare.git && cd skillshare
make playground

:::

How It Works

flowchart LR
    subgraph ORG["GLOBAL"]
        ORG_SRC["~/.config/skillshare/skills/"] -- sync --> ORG_TGT["~/.claude/skills/ etc."]
    end

    subgraph PROJ["PROJECT"]
        PROJ_SRC[".skillshare/skills/"] -- sync --> PROJ_TGT[".claude/skills/ etc."]
    end

Edit an existing skill in source and linked targets see the change immediately. In copy mode, run sync to refresh their copies. In the default merge mode, adding, removing or renaming skills also requires sync.

Global mode holds your personal setup and installed team repositories. Project mode holds resources and configuration for one codebase. A Git pull brings in the project's files; run skillshare install -p and skillshare sync -p to apply its declared skills locally.

Key Features

  • Auto-Detection — cd into a project with .skillshare/ and skillshare switches to project mode automatically
  • Global and Project Scope — Personal and shared organization resources in global mode; codebase-specific resources in project mode
  • Linked Updates — Edits to existing skills reflect immediately in targets that use symlinks
  • Team Ready — Organization skills via tracked repos, project skills via git commit
  • Any Git Host — Install, update, and check from GitHub, GitLab, Bitbucket, Azure DevOps, AtomGit, Gitee, or any self-hosted Git
  • Security Audit — Scan skills for known injection and exfiltration patterns before use. Audit is static analysis; execution permissions remain with your AI tools

Supported Platforms

Platform Source Path Link Type
macOS/Linux ~/.config/skillshare/skills/ Symlinks
Windows %AppData%\skillshare\skills\ NTFS Junctions for folders; symlinks for single files (Developer Mode, otherwise copies)

Next Steps

Individual Developer

  1. First Sync — Get synced in 5 minutes
  2. Creating Skills — Write your first skill
  3. Cross-Machine Sync — Keep skills in sync across machines

Team Lead / Organization

  1. Organization-Wide Skills — Share standards across the team
  2. Project Setup — Set up project-scoped skills
  3. Security Audit — Scan third-party skills before deployment

Already Have Skills?

Explore More