# Skillstore

> Probe-verified (tier 2 of 3). Last checked 2026-08-23. 3 of 5 capability checks passed.

- host: skillstore.io
- url: https://skillstore.io/
- category: ai skills catalog
- type: tool
- language: en

## Probe-verified · tier 2 of 3

Probed live on 2026-08-23 against rubric v1. 3 of 5 checks passed.

- PASS — Markdown negotiation
- fail — Markdown twin at a predictable URL
- fail — llms.txt
- PASS — API catalog
- PASS — MCP server answers

MCP tools (from tools/list on 2026-08-23): search_skills, get_pack, install_pack, list_scenarios

## Unverified actions

Read from the page's own content, with the wording each was drawn from. Inference is kept separate from tested facts; an agent completing the action is tier 3.

- **search** — "Search with JSON APIs or MCP search_skills" → `https://skillstore.io/api/skills`
- **query_api** — "API catalog: https://skillstore.io/.well-known/api-catalog" → `https://skillstore.io/.well-known/api-catalog`

## Summary

Skillstore is a public catalog of AI skills and skill packs for Claude, Codex, and Claude Code with security audits and installation manifests.

## Context

297 sites in this index share the type "tool"; 110 are transactional.

## How we grade

- tier 1 — **Declared**: The site says agents are welcome in its robots.txt. A permission, not a capability.
- tier 2 — **Probe-verified** (this site): We fetched the site and tested each signal ourselves. Dated, repeatable, re-checked on a schedule.
- tier 3 — **Behaviourally verified**: An agent completed the action end to end — booked, bought, submitted — and it worked.

## About this record

Known-Good probes sites live and publishes what was tested and when.
Method: https://knowngood.sh/about.md · Rubric: https://knowngood.sh/benchmark