Important
This is the Cheesecake Labs internal fork of
tech-leads-club/agent-skills.
Install through Claude Code or Cowork using our private marketplace β
not through the upstream CLI or npm.
One-time setup, per machine:
/plugin marketplace add CheesecakeLabs/agent-skills
Install plugins (pilot scope β more coming as we validate each):
/plugin install creation@ckl-agent-skills
/plugin install tlc-spec-driven@ckl-agent-skills
The same flow works from Claude Cowork for non-developer teammates β your org-level marketplace setting already covers it (same setup as ckl-ai-skills).
Adding a new skill to the marketplace? See CONTRIBUTING.md β "Adding a Skill to the CKL Marketplace".
The original upstream README is preserved below for reference. Sections that document the upstream CLI install path are marked with [!NOTE] callouts β those don't apply to CKL employees.
The secure, validated skill registry for professional AI coding agents
In an ecosystem where over 13% of marketplace skills contain critical vulnerabilities, Agent Skills stands apart as a hardened library of verified, tested, and safe capabilities. Extend Antigravity, Claude Code, Cursor, and more with absolute confidence.
https://tech-leads-club.github.io/agent-skills/
- π§ Cheesecake Labs Fork (Start Here)
- β¨ What are Skills?
- π‘οΈ Security & Trust
- π€ Supported Agents
- π Featured Skills
- π Quick Start
- β‘ How It Works
- π MCP Server
- π€ Contributing
- π‘οΈ Content & Authorship
- π License and Attribution
Skills are packaged instructions and resources that extend AI agent capabilities. Think of them as plugins for your AI assistant β they teach your agent new workflows, patterns, and specialized knowledge.
packages/skills-catalog/skills/
(category-name)/
skill/
SKILL.md β Main instructions
templates/ β File templates
references/ β On-demand documentation
Your environment's safety is our top priority. Unlike open marketplaces where 13.4% of skills contain critical issues, agent-skills is a managed, hardened library: 100% open source (no binaries), static analysis in CI/CD, immutable integrity via lockfiles and content hashing, and human-curated prompts. The CLI uses defense-in-depth (sanitization, path isolation, symlink guards, atomic lockfile, audit trail); every skill is scanned with Snyk Agent Scan (formerly mcp-scan) before publishing.
β Full threat model, implementation details, and vulnerability reporting: SECURITY.md
Note
CKL employees: the multi-agent install paths below don't apply to us β we install via the Claude marketplace (see the banner at the top of this README). This section documents the agents supported by the upstream CLI installer.
Install skills to any of these AI coding agents:
| Tier 1 (Popular) | Tier 2 (Rising) | Tier 3 (Enterprise) |
|---|---|---|
| Claude Code | Aider | Amazon Q |
| Cline | Antigravity | Augment |
| Cursor | Gemini CLI | Droid (Factory.ai) |
| GitHub Copilot | Kilo Code | OpenCode |
| Windsurf | Kiro | Sourcegraph Cody |
| OpenAI Codex | Tabnine | |
| Roo Code | ||
| TRAE |
Missing your favorite agent? Open an issue and we'll add support!
A glimpse of what's available in our growing catalog:
| Skill | Category | Description |
|---|---|---|
| tlc-spec-driven | Development | Project and feature planning with 4 phases: Specify β Design β Tasks β Implement. Creates atomic tasks with verification criteria and maintains persistent memory across sessions. |
| aws-advisor | Cloud | Expert AWS Cloud Advisor for architecture design, security review, and implementation guidance. Leverages AWS MCP tools for documentation-backed answers. |
| playwright-skill | Automation | Complete browser automation with Playwright. Test pages, fill forms, take screenshots, validate UX, and automate any browser task. |
| figma | Design | Fetch design context from Figma and translate nodes into production code. Design-to-code implementation with MCP integration. |
| security-best-practices | Security | Language and framework-specific security reviews. Detect vulnerabilities, generate reports, and suggest secure-by-default fixes. |
Note
CKL employees: ignore this section. Install via the Claude marketplace β see the banner at the top of this README.
This section documents the upstream CLI install path for users of tech-leads-club/agent-skills. It is collapsed by default so you don't accidentally follow it.
Upstream CLI usage (kept for reference)
npx @tech-leads-club/agent-skillsThis launches an interactive wizard:
- Choose Action β "Install skills" or "Update installed skills"
- Browse & Select β Filter by category or search
- Choose agents β Pick target agents (Cursor, Claude Code, etc.)
- Installation method β Copy (recommended) or Symlink
- Scope β Global (user home) or Local (project only)
Each step shows a β Back option to return and revise your choices.
Note: You can use either
npx @tech-leads-club/agent-skillsor install globally and useagent-skillsdirectly.
# Interactive mode (default)
npx @tech-leads-club/agent-skills
# or: agent-skills (if installed globally)
# List available skills
agent-skills list
agent-skills ls # Alias
# Install one skill
agent-skills install -s tlc-spec-driven
# Install multiple skills at once
agent-skills install -s aws-advisor coding-guidelines docs-writer
# Install to specific agents
agent-skills install -s my-skill -a cursor claude-code
# Install multiple skills to multiple agents
agent-skills install -s aws-advisor nx-workspace -a cursor windsurf cline
# Install globally (to ~/.gemini, ~/.claude, etc.)
agent-skills install -s my-skill -g
# Use symlink instead of copy
agent-skills install -s my-skill --symlink
# Force re-download (bypass cache)
agent-skills install -s my-skill --force
# Update a specific skill
agent-skills update -s my-skill
# Update all installed skills
agent-skills update
# Remove one skill
agent-skills remove -s my-skill
# Remove multiple skills at once
agent-skills remove -s skill1 skill2 skill3
agent-skills rm -s my-skill # Alias
# Remove from specific agents
agent-skills remove -s my-skill -a cursor windsurf
# Force removal (bypass lockfile check)
agent-skills remove -s my-skill --force
# Manage cache
agent-skills cache --clear # Clear all cache
agent-skills cache --clear-registry # Clear only registry
agent-skills cache --path # Show cache location
# View audit log
agent-skills audit # Show recent operations
agent-skills audit -n 20 # Show last 20 entries
agent-skills audit --path # Show audit log location
# Show contributors and credits
agent-skills credits
# Show help
agent-skills --helpnpm install -g @tech-leads-club/agent-skills
agent-skills # Use 'agent-skills' instead of 'npx @tech-leads-club/agent-skills'Note
CKL employees: this describes the upstream CLI's cache/CDN flow. CKL employees install via the Claude marketplace, which has its own plugin cache mechanism (~/.claude/plugins/cache/) managed by Claude Code itself.
The CLI fetches skills on-demand from our CDN:
- Browse β The CLI fetches the skills catalog (~45KB)
- Select β You choose the skills you need
- Download β Selected skills are downloaded and cached locally
- Install β Skills are installed to your agent's configuration
Downloaded skills are cached in ~/.cache/agent-skills/ for offline use.
# Clear the cache
rm -rf ~/.cache/agent-skillsNote
CKL employees: ignore this section. You install skills as Claude plugins via the marketplace (banner at top), not via an MCP server. This section documents the upstream MCP server for users of tech-leads-club/agent-skills.
@tech-leads-club/agent-skills-mcp is an MCP server that exposes the skills catalog directly to AI agents via progressive disclosure β search first, then fetch only what's needed.
| Tool | Purpose |
|---|---|
list_skills |
Browse all skills by category |
search_skills |
Find skills by intent (fuzzy search) |
read_skill |
Load a skill's main instructions |
fetch_skill_files |
Fetch specific reference files |
list_skills should be called only when the user explicitly asks to browse/list the catalog.
Quick install (works with any MCP-compatible client):
{
"mcpServers": {
"agent-skills": {
"command": "npx",
"args": ["-y", "@tech-leads-club/agent-skills-mcp"]
}
}
}β Full setup for all clients (Cursor, Claude Code, VS Code, etc.), caching, and error reference: packages/mcp/README.md
We welcome contributions! Please see our CONTRIBUTING.md file for detailed guidelines on how to set up your local environment, create new skills, contribute to the marketplace, and follow our release processes.
This repository is a collection of curated skills intended to benefit the community. We deeply respect the intellectual property and wishes of all creators.
If you are the author of any content included here and would like it removed or updated, please open an issue or contact the maintainers.
- Software Engine: The application source code (CLI, scripts, tools) is licensed under the MIT License.
- Tech Leads Club Skills: Unless otherwise stated, all skill files (
SKILL.md) authored by the repository maintainers are licensed under the Creative Commons Attribution 4.0 International License (CC-BY-4.0). - Third-Party Skills: Some skills included in this catalog are created by the community or original authors. These skills retain their original licenses and copyrights. Please check the individual
SKILL.mdfiles for specific licensing and author attribution.
If you use our skills catalog, you must provide attribution to Tech Leads Club, regardless of how it is used.
Built with β€οΈ by the Tech Leads Club community
