find-skills
An agent skill by vercel-labs, from vercel-labs/skills. Tags: automation, developer-tools, local-workflow.
What it does
Helps users discover and install agent skills when they ask questions like "how do I do X", "find a skill for X", "is there a skill that can...", or express interest in extending capabilities. This skill should be used when the user is looking for functionality that might exist as an installable skill.
Install
With the skills CLI, which installs into Claude Code, Codex, Cursor and other agents:
npx skills add vercel-labs/skills --skill find-skills
Or copy the skill folder into Claude Code's skills directory by hand (~/.claude/skills for every project, or .claude/skills inside one):
git clone --depth 1 https://github.com/vercel-labs/skills
cp -r skills/skills/find-skills ~/.claude/skills/find-skills
Safety box score
Grade C, moderate risk: 35 of 100 risk points, rated 2026-09-25. The grade rates what the skill and its scripts can reach on the machine of whoever installs it, across eight categories from shell execution to secrets access. How the score works.
This is a documentation-only skill that helps the agent search for and install other skills, but it depends on the external `npx skills` CLI and remote sources like skills.sh and GitHub. The main risks are running registry code, fetching from the network, and making global user-level changes when installing or updating skills.
| Category | Level | Why |
|---|---|---|
| Code & shell execution | 2 (moderate) | The core commands are `npx skills find`, `npx skills add`, and `npx skills update`, which execute a package fetched at runtime from the npm registry. |
| Network access | 2 (moderate) | It directs the agent to browse `https://skills.sh/` and install skills from GitHub or other sources, so search and installation depend on external network access. |
| Filesystem reach | 2 (moderate) | The install example uses `-g` and the skill recommends `npx skills update`, both of which modify user-level files outside the current project. |
| Secrets & credentials | 0 (none) | The skill does not ask for API keys, tokens, passwords, `.env` files, or other credentials. |
| Privilege & persistence | 1 (low) | `-g` changes the user's global environment, but the skill does not require sudo or system-service changes. |
| Instruction hijack surface | 1 (low) | It explicitly suggests `-y` to skip confirmation prompts on installs, reducing a human check before environment changes. |
| Irreversible actions | 1 (low) | It can install or update skills for the user, but only after the user asks to proceed and without sending messages or paying for anything. |
| Transparency | 0 (none) | The file is plain markdown; there are no binaries, encoded blobs, or unreadable payloads in the skill itself. |
Before installing
- Run `npx skills find <query>` without `-g -y` first and inspect the output.
- Verify the exact repo/package and source reputation on skills.sh and GitHub before installing.
- Check where global skills are written on your machine so you know what `-g` and `update` will modify.
- Test the install in a throwaway user account or clean environment first.
Rated 2026-09-25 by an automated review of 1 file from the skill's repository.
Source
- Repository
- vercel-labs/skills (all skills from this repository)
- Path
- skills/find-skills/SKILL.md
- Branch
- main
- Updated
- 2026-09-19
Related skills
- devcontainer-setup — Creates devcontainers with Claude Code, language-specific tooling (Python/Node/Rust/Go), and persistent volumes.
- cad — Create/edit parametric CAD models, organize CAD projects, export STEP/STL/3MF/GLB files, resolve prompt references, and measure geometry with cadgen.
- dxf — Generate, regenerate, and validate 2D DXF drawings from Python build123d sources.
- filesystem-context — This skill should be used when agent work needs file-backed context: durable scratchpads, tool-output offloading, just-in-time discovery.
- hosted-agents — This skill should be used when designing hosted or background agent infrastructure: sandboxed execution, remote coding environments, warm pools.
- agents-get-started — Use when a developer wants to create a new agent project or get started with AgentCore.