AI skills by job function
Thousands of MCP servers and agent skills, filed by the work you do — and audited before you install one: known vulnerabilities, what runs at install time, and what it can reach on your machine.
Already running things
One command reads your Claude Code, Cursor and Desktop configs and flags known advisories, install-time scripts, and anything deprecated, archived or abandoned. Local only — nothing is uploaded.
npx tashan-cli doctor ›
About to install something
Filed by the work you're doing — code review, data pipelines, PRDs — not by what a tool happens to touch. Each one ranked on measured evidence, with the raw signal shown beside it.
Browse by the work ›
You are an agent
A 50 KB lookup of every score, the full set in MCP-registry shape, and a SKILL.md you can install so checking is a tool call. An absent name means unmeasured, never bad.
curl tashan.sh/v0.1/scores ›
The Index
| # | Capability | tashan | Evidence | Health |
|---|---|---|---|---|
Loading measured data… | ||||
Why trust this
Adoption, upkeep, freshness, real expertise — every rank comes from public evidence. No stars, no sponsorships, no louder listing moving up the board.
Directories list; we open each capability and grade the real thing — deep domain work versus a thin wrapper or AI-slop. GitHub evaluates code. Nobody else evaluates the expertise.
No black box. Each signal is defined and checkable against public sources — the registry, npm, git history. If you don't believe a number, verify it.