find-skills
Search, install, update, and remove third-party Agent Skills from skills.sh or any GitHub/GitLab repo via the `npx skills` CLI.
Skill by mgiovani
Install
Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.
npx agentmarket install skill/mgiovani-find-skills
Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.
Get the weekly diff
The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.
About
Use cases: agent-building
Reviews
Write a reviewNo reviews yet. Installed it? Reviews come from verified installers only. How reviews work
Permissions
What this skill can do and what it asks for, from its SKILL.md and code. Checked Oct 25, 2026.
- Tools
- No tools found
- Secrets
- None asked for
- Install scripts
- None found
Network hosts it talks to 1
codeload.github.com· found in install command
Files it touches
~/.claude/skills/find-skills
What's inside
- Skill name
find-skills- Description
- Search, install, update, and remove third-party Agent Skills from skills.sh or any GitHub/GitLab repo via the `npx skills` CLI. Use when the user wants to "find a skill", "install a skill from github", "search skills.sh", or add third-party capabilities to Claude Code/Cursor/other agents. Not for authoring new skills (see create-skill).
- License
- MIT
- Metadata
- summary: Discover and install third-party agent skills from skills.sh
- Instructions
- 153 lines in SKILL.md · view on GitHub
Files (5)
- SKILL.md
- evals.json · evals/
- trigger-eval.json · evals/
- commands.md · references/
- workflows.md · references/
SKILL.md (first lines)
# Find Skills Discover and install third-party agent skills from the open Agent Skills ecosystem powered by skills.sh. ## Overview The **Agent Skills** format is an open standard for packaging procedural knowledge, workflows, and tools that AI agents load on demand. The `npx skills` CLI (maintained by Vercel Labs) serves as "npm for AI agents", enabling discovery and installation of community skills from any Git repository. **skills.sh** is the public directory and leaderboard for the ecosystem, hosting thousands of skills across categories like frontend, backend, DevOps, and more. Before installing an external skill, check `ls skills/` in this repo (or run `/find-skills` again after browsing). cc-arsenal may already cover the same ground, and a hardcoded list here would just go stale. ## Ask First, Never Mutate to "Show" Something `add`, `remove`/`rm`, and `update` all touch the user's real filesystem (project `.claude/skills/` or global `~/.claude/skills/`). A wrong guess costs the user real state, not a free re-run. Two hard stops, both end the turn on a question rather than acting and reporting after: - **Scope or target is ambiguous.** If it isn't clear which skill/repo to install, or whether it belongs at project vs. global scope, end your response with the clarifying question. Don't run `npx skills add` first and confirm after, and don't install to a throwaway/local mock "just to show the flow", which still runs a real command against the user's real directories. Ask, stop, and install only in a later turn once the user answers. - **Any removal, one skill or all of them.** Removal is destructive and not undoable via the CLI. Run `npx skills list` (and `-g` if scope is unclear) to show what's actually installed, then end your response asking the user to confirm exactly what gets removed. Run `remove`/`rm`/`--all` only in a later turn, after the user replies with an explicit yes. The request is never the confirmation: "remove the foo skill, I don't use it anymore" names the action but does not green-light it. If you catch yourself reasoning "the user already confirmed by naming it", that reasoning is exactly the failure this rule exists to stop. If a source can't be verified (repo doesn't exist, network/auth error), report the failure and stop. Never substitute a synthetic local repo and install it to demonstrate what would have happened. ## Quick Start Requires Node.js for `npx` (`fnm install --lts` or `brew install node`). ### 1. Find Skills ```bash # Interactive fuzzy search across skills.sh npx skills find # Search by keyword npx skills find typescript npx skills find react npx skills find testing ``` ### 2. Review Available Skills in a Repository ```bash # List skills in a repository without installing npx skills add owner/repo --list # Example: list Vercel's official skills npx skills add vercel-labs/agent-skills --list # Example: list Anthropic's skills npx skills add anthropics/skills --list ``` ### 3. Install Skills ```bash # Interactive installation (choose skills and target agents) npx skills add owner/repo # Install a specific skill for Claude Code npx skills add owner/repo --skill skill-name -a claude-code # Install globally (available across all projects) npx skills add owner/repo --skill skill-name -a claude-code -g # Install all skills from a repo to all detected agents npx skills add owner/repo --all ``` ## Worked Examples Map the user's request to the right subcommand and scope before running anything: | User says | Command | |---|---| | "find a skill for testing" | `npx skills find testing` | | "install the frontend-design skill from vercel-labs/agent-skills for this project" | `npx skills add vercel-labs/agent-skills --skill frontend-design -a claude-code` | | "install code-review globally so I have it everywhere" | `npx skills add owner/repo --skill code-review -a claude-code -g` | | "what skills do I have installed?" | `npx skills list` | | "remove the web-design-guidelines skill" | `npx skills list` to confirm it's installed, then ask "remove web-design-guidelines, confirm?" and run `npx skills remove web-design-guidelines` only after a yes | See "Ask First, Never Mutate to 'Show' Something" above for exactly when to end the turn on a question instead of running the command. ## Essential Commands | Command | Purpose | |---------|---------| | `npx skills find [query]` | Search skills.sh directory | | `npx skills add <source>` | Install skills from a repository | | `npx skills list` | View installed skills | | `npx skills check` | Check for available updates | | `npx skills update` | Update all installed skills | | `npx skills remove [name]` | Uninstall a skill | | `npx skills init [name]` | Create a new skill template | ## Installation Scopes **Project scope** (default): Installs to `.claude/skills/` in the current project directory. Committed with the project and shared with team members. **Global scope** (`-g` flag): Installs to `~/.claude/skills/` in the home directory. Available across all projects for the current user. **Recommendation**: Install domain-specific skills (e.g., a framework skill) at project scope. Install general-purpose skills (e.g., code review, testing patterns) at global scope. ## Source Formats The `add` command accepts multiple source formats: ```bash # GitHub shorthand (most common) npx skills add owner/repo # Full GitHub URL npx skills add https://github.com/owner/repo # Direct path to a specific skill npx skills add https://github.com/owner/repo/tree/main/skills/skill-name # GitLab URL npx skills add https://gitlab.com/org/repo # Local directory (for development) npx skills add ./my-local-skills
From mgiovani/cc-arsenal, MIT.
More from mgiovani/cc-arsenal
- 0.631score
ci-generate
mgiovani
Generate a production-ready CI/CD pipeline config (GitHub Actions, GitLab CI, CircleCI, or Jenkins) by discovering the project's actual stack, test/build…
SkillAFreshness: A★ 8Claude Code +9 - 0.631score
docs-diagram
mgiovani
Generate a Mermaid diagram (ER, architecture, deployment, or security) by reading the actual codebase and writing it to docs/.
SkillAFreshness: A★ 8Claude Code +9 - 0.631score
agent-browser
mgiovani
Headless browser automation CLI optimized for AI agents: drives a real browser via accessibility-tree snapshots and @e1-style refs for ~93% less context than…
SkillAFreshness: A★ 8Claude Code +9 - 0.631score
anything-to-skill
mgiovani
Turns a docs site, local folder, PDF or book, YouTube video, playlist or channel, or a topic into a source-grounded, token-efficient agent skill (hub…
SkillAFreshness: A★ 8Claude Code +9 - 0.631score
codex-imagegen
mgiovani
Generates images and polished raster art (logos, mascots, hero images, icons, characters, sprite sheets, illustrations, product mockups) by driving Codex…
SkillAFreshness: A★ 8Claude Code +9 - 0.631score
create-rule
mgiovani
Create a new memory/instruction rule for whatever AI coding tool a project actually uses, a CLAUDE.md entry or .claude/rules/*.md file for Claude Code, an…
SkillAFreshness: A★ 8Claude Code +9 - 0.631score
create-skill
mgiovani
Create a new agent skill (or Claude Code slash command) from a plain-language description, using live spec fetching, pattern research, and an approval-gated…
SkillAFreshness: A★ 8Claude Code +9 - 0.631score
db-migrate
mgiovani
Creates, checks the status of, and validates database migrations by auto-detecting the project's migration framework (Alembic, Prisma, Knex, Django…
SkillAFreshness: A★ 8Claude Code +9 - 0.631score
docker-init
mgiovani
Generates production-ready docker-compose.yml and Dockerfile(s) for a project by scanning its manifest files (package.json, pyproject.toml, Gemfile, go.mod…
SkillAFreshness: A★ 8Claude Code +9 - 0.631score
docs-check
mgiovani
Read-only audit of documentation against the current codebase, flags stale docs, missing sections, broken links, and hallucinated claims (wrong file…
SkillAFreshness: A★ 8Claude Code +9 - 0.631score
docs-update
mgiovani
Refresh existing docs (architecture, onboarding, data-model, deployment, security, contributing) so they match the current codebase, verifying every claim…
SkillAFreshness: A★ 8Claude Code +9 - 0.631score
env-setup
mgiovani
Scans a codebase for environment variable usage to generate or sync .env.example, validate .env completeness against what the code actually reads, and detect…
SkillAFreshness: A★ 8Claude Code +9
Signals
- Stars
- 8
- Forks
- 1
- Open issues
- 6
- Last commit (this folder)
- Oct 5, 2026 (23 days ago)
- Last release
- Oct 7, 2026 (22 days ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- MIT
- Repository
- github.com/mgiovani/cc-arsenal
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from mgiovani
- 0.631score
docs-diagram
mgiovani
Generate a Mermaid diagram (ER, architecture, deployment, or security) by reading the actual codebase and writing it to docs/.
SkillAFreshness: A★ 8Claude Code +9 - 0.631score
agent-browser
mgiovani
Headless browser automation CLI optimized for AI agents: drives a real browser via accessibility-tree snapshots and @e1-style refs for ~93% less context than…
SkillAFreshness: A★ 8Claude Code +9 - 0.631score
anything-to-skill
mgiovani
Turns a docs site, local folder, PDF or book, YouTube video, playlist or channel, or a topic into a source-grounded, token-efficient agent skill (hub…
SkillAFreshness: A★ 8Claude Code +9 - 0.631score
codex-imagegen
mgiovani
Generates images and polished raster art (logos, mascots, hero images, icons, characters, sprite sheets, illustrations, product mockups) by driving Codex…
SkillAFreshness: A★ 8Claude Code +9 - 0.631score
create-rule
mgiovani
Create a new memory/instruction rule for whatever AI coding tool a project actually uses, a CLAUDE.md entry or .claude/rules/*.md file for Claude Code, an…
SkillAFreshness: A★ 8Claude Code +9 - 0.631score
ci-generate
mgiovani
Generate a production-ready CI/CD pipeline config (GitHub Actions, GitLab CI, CircleCI, or Jenkins) by discovering the project's actual stack, test/build…
SkillAFreshness: A★ 8Claude Code +9
Cite this page
find-skills. Agent Mart. https://agentmart.dev/skills/mgiovani-find-skills (last updated 2026-10-24)