finding-skills
Skill0 starsChanged 3 months agoMITView on GitHub
Check Skillselion for a community skill before writing code in a domain you do not have a local skill for, such as a payments, auth, cloud, or browser-automation SDK, a test framework, an infra or CI config, or any fast-moving library. Use when the task depends on API details or conventions that change often, and when the user asks what skills or MCP servers exist for something.
1 other project uses a version of this.
Adopted by
Most recently taken up by
- oaustegard/claude-skillstheir own version, first seen Mar 11, 2026
Other versions1 project uses a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 1
- oaustegard/claude-skills★ 158same 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
6 rules. About 0 are common, 2 are distinctive, and 4 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈2
Distinctive · estimate
This author's own choices. Worth a look.
4
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 15
Search first when the task involves:
- Very specific: line 30
Call load_skill from the skillselion MCP server with the task as query and the stack plus constraints as context.
- Very specific: line 34
Follow the returned SKILL.md instead of reciting practices from memory.
- Distinctive: line 35
Check it against the repo first: versions and conventions may differ.
- Very specific: line 36
Use synthesize_skills when you want the shared rules across the top matches rather than one author's approach.
- Very specific: line 38
Use search_skillselion to browse options and top_skillselion for the leaderboard.
≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Find a proven skill before improvising
The Skillselion directory holds community-written skills, real SKILL.md
files plus their bundled scripts, ranked by install count. When a task lands in
a domain that no installed skill covers, a loaded skill is usually more current
than recalled API details.
When to reach for it
Search first when the task involves:
- an SDK whose API moves fast: payments, auth, cloud, browser automation, AI providers
- a framework convention you would otherwise guess at: file layout, config keys, migration steps
- infrastructure that is easy to get subtly wrong: Docker, CI pipelines, deploy configs
- a question about which skills or MCP servers exist for a tool
Skip it when a skill already installed in this session covers the domain, or when the work is plain application logic with no external contract.
How to use it
- Call
load_skillfrom theskillselionMCP server with the task asqueryand the stack plus constraints ascontext. The scoped name ismcp__plugin_skillselion_skillselion__load_skillwhen the server comes from this plugin. - Follow the returned
SKILL.mdinstead of reciting practices from memory. Check it against the repo first: versions and conventions may differ. - Use
synthesize_skillswhen you want the shared rules across the top matches rather than one author's approach. - Use
search_skillselionto browse options andtop_skillselionfor the leaderboard.
Loading is read only and cheap. If nothing matches, the tool says so, and you carry on as you were.
Directory: https://skillselion.com
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.

