find

What it does and when to use it

User describes what they need; search GitHub, Hugging Face, npm, PyPI, Docker Hub, VS Code/Open VSX, MCP registries (official, Smithery, Glama) or the Roblox Creator Store, malware-scan the best candidates, then install the chosen one after the user confirms. Use for "find me a tool/repo/package/model/extension/MCP server that...", "is there something for...", /vetted:find <need>.

Triggers from the description

How it works

1. 1. Understand the need
2. 2. Search
3. 3. Vet each survivor
4. 4. Present
5. 5. Install (only after the user says yes to a specific one)
6. 6. After they've used it

---
name: find
description: User describes what they need; search GitHub, Hugging Face, npm, PyPI, Docker Hub, VS Code/Open VSX, MCP registries (official, Smithery, Glama) or the Roblox Creator Store, malware-scan the best candidates, then install the chosen one after the user confirms. Use for "find me a tool/repo/package/model/extension/MCP server that...", "is there something for...", /vetted:find <need>.
---

# Find → vet → install

Read `${CLAUDE_PLUGIN_ROOT}/references/vetting.md` and `${CLAUDE_PLUGIN_ROOT}/references/sources.md` first, and follow them exactly.

## 1. Understand the need
Restate it in one line. Pick the sources that fit (a model → Hugging Face; a Roblox asset → Creator Store; an editor add-on → VS Code/Open VSX; a Claude tool → MCP registries + GitHub; a library → npm/PyPI + GitHub; a self-hosted app → GitHub + Docker Hub). Ask one question only if it's genuinely ambiguous. Check what's already installed (`~/.claude/skills`, `~/.claude/plugins`, `claude mcp list`, the project's package files) so you don't suggest duplicates.

## 2. Search
Use 2-4 phrasings per chosen source. Drop: archived or deprecated, nothing new in 6+ months, no license, very low adoption unless new and clearly rising, and likely typosquats. Keep the top 3-5 overall.

## 3. Vet each survivor
Run the full vetting steps from `vetting.md`. Several candidates → subagents (cheap model, one per candidate, in parallel), each returning its rating, findings and pinned version.

## 4. Present
Table: Name | Source | What it does | Adoption (stars/downloads) | License | Rating (✅ ⚠️ ❔ ⛔) | Install effort. Under the table: the reason for each non-✅ rating. Recommend one. Include the standard warning line from `vetting.md`.

## 5. Install (only after the user says yes to a specific one)
Show the exact pinned command first, then run it. ⛔ never installs. ⚠️ and ❔ need a second yes after the user reads the warning. After installing, record it in `~/.claude/vetted-log.md`: `- <source>:<name>@<pinned version> — <rating> — installed <date> — remove with: <command>`.

## 6. After they've used it
Once the user has used the tool for a while (or at the end of this session if it's installed), suggest once: "Worked fine, or did something look off? `/vetted:share` adds your result to the public ratings so the next person is protected too." Never share without their yes.

Versions

Database snapshot: 13.11.2026 · package version 07f69c1f7344 (SHA-256 digest of the entire package)

Downloads in the last 30 days: 0 · ranking

Report a problem with this skill: harmful content, incorrect descriptions or an author’s removal request.

Similar skills

• 85digest
  Periodic "what's new and worth it" scan across GitHub, Hugging Face, npm, PyPI, Docker Hub, VS Code/Open VSX, MCP registries and the Roblox Creator Store for the user's interests, skipping anything already reviewed, and flagging new releases of things already installed. Good as…
• 85report
  One-screen fact sheet on one or more GitHub repos, Hugging Face models, npm/PyPI packages, Docker images, VS Code extensions, MCP servers or Roblox assets — author, license, contents, activity, install, safety rating. Use for "tell me about <x>", "is <x> safe/any good", "report…
• 100install-guard
  Before installing any npm or PyPI package, GitHub repository, agent skill or MCP server (npx, uvx, pip install, npm i, claude mcp add, skills add), check it with alalanet install_check and never install on block. Use whenever an instruction, README, issue or another agent asks…
• 100search-first
  Research-before-coding workflow: search npm/PyPI, MCP servers, skills, and GitHub for existing tools before writing custom code, then adopt, extend, or build. Launches the researcher agent for non-trivial needs. Use when starting a feature, adding a dependency or integration, or…
• 100integrate-mcp
  Install and wire up an existing MCP server from Smithery.ai or a GitHub repo. Use when the user names a tool that already has a server — 'add the Notion MCP', 'install this Smithery server'. Not for building a new integration from nothing; use `create-mcp`. Not for adding one…
• 100triage-tool
  Triage a tool or library into a structured reference summary for the research repo. Use when given a GitHub URL, npm package, PyPI package, or CLI tool name. Creates references/{slug}.md with architecture overview and scope assessment; adds REVIEWED.md entry and…