find
Skill0 starsChanged 6 days agoMITView on GitHub
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>.
7 other projects use a version of this.
Adopted by
Most recently taken up by
- Jamaalx/claude-chat-namertheir own version, first seen Nov 1, 2026
- replybr/plugadvpltheir own version, first seen Nov 1, 2026
- fakechris/obsidian_vault_pipelinetheir own version, first seen Oct 9, 2026
- ZeeshanSultan/DocGovtheir own version, first seen Sep 13, 2026
- bibryam/universal-skill-findertheir own version, first seen Sep 12, 2026
- tonydzi/second-brain-starter-kittheir own version, first seen Sep 8, 2026
Other versions7 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 7
- fakechris/obsidian_vault_pipeline★ 165same name
- tonydzi/second-brain-starter-kit★ 6same name
- bibryam/universal-skill-finder★ 5same name
- Jamaalx/claude-chat-namer★ 5same name
- replybr/plugadvpl★ 1same name
- statzhero/zotero-fulltext★ 0same name
- ZeeshanSultan/DocGov★ 0same name
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
The file
We split this skill into the rules it gives an agent
3 rules. 0 are common, 1 is distinctive, and 2 are very specific to this project.
0
Common
Most of the 6 edited versions we read keep these.
1
Distinctive
This author's own choices. Worth a look.
2
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 8
Read ${CLAUDE_PLUGIN_ROOT}/references/vetting.md and ${CLAUDE_PLUGIN_ROOT}/references/sources.md first, and follow them exactly.
- Distinctive: line 14
Use 2-4 phrasings per chosen source.
- Very specific: line 17
Run the full vetting steps from vetting.md.
“Common” is measured: kept by at least 6 in 10 of the 6 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
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.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.