The Open Agent Capability Registry
An open home for agent skills, MCP servers, tools, prompts, workflows, and reusable agent infrastructure.
Counted live from the registry database.
Browse by type
Activity
MCP server for building with the Claude API: probe-verified model reference, request linter and fixer, cost estimates, agent scaffolding, plus live messages, token counting, batches, files and Managed Agents.
Write, review, debug and migrate Claude API code with model tables and a request linter built from live API probes of 15 models. Includes cost estimates and tested agent scaffolds.
Dependency-free local MCP server over stdio with a single echo tool, for testing client configuration.
Checks that every in-text citation in a Markdown or LaTeX manuscript has a bibliography entry, and the reverse.
Minimal example skill: greets the user and explains how Agent Skills are structured.
Install
Every release is an immutable archive with a SHA-256 checksum. The CLI shows declared permissions and the destination, verifies the checksum, copies files and stops there. It never runs package scripts.
skills inspect @spboucher/claude-api-toolkitskills install @spboucher/claude-api-toolkit@1.0.0 --client claude-codeclaude mcp add --transport http skills-registry https://skills.spboucher.ai/mcpCurated
Open publishing
Package a directory, validate it locally, review a dry run, and publish an immutable, checksummed release with a scoped token — from your terminal or directly from Claude Code. Preserve your upstream manifests; the registry adds a thin wrapper, not a new format.
skills validate ./my-skill
skills publish ./my-skill --dry-run
skills publish ./my-skill --visibility public