DEDUPED Hot AI repos, turned into use cases Get the Monday 5

How to let your coding agent search and install skills mid-task with Skillmd

Connect the skillmds MCP server so an agent can search, inspect, lint and install skills itself.

Who it is forA developer working in Claude Code or Cursor who wants the agent to find and add a skill for a task without leaving the conversation.

The problemLooking up and installing skills by hand breaks the flow of a coding session, and the agent cannot check a skill on its own.

The outcomeThe agent can call skillmd_search, skillmd_get, skillmd_lint and skillmd_install from inside the conversation.

What you need first

  • Node.js with npm, since the README uses npm and npx commands
  • A terminal on your machine or in CI
  • A skill folder containing a SKILL.md file (for lint and publish use cases)
  • A skillmd.com account and token (only for publishing)

Steps

  1. In Claude Code, run claude mcp add skillmd -- npx -y skillmds.
  2. For Cursor or another MCP client, add the mcpServers entry from examples/mcp/ with the command npx and args -y skillmds.
  3. Restart the client so it loads the new MCP server. (inferred, check the README)
  4. Ask the agent to search for a skill, and confirm it calls skillmd_search and then skillmd_install.

Prompt for your agent

Connect the skillmds MCP server from the skillmds repo to <client-name> using `npx -y skillmds`. Ask it to search the registry for <topic> and to lint the result with skillmd_lint. Report the skill it chose and confirm the install returned without running scripts.

Caveat. The README lists a hosted remote server at https://api.skillmd.com/mcp as an alternative to the local npx install, but it does not say which MCP clients it supports.

Share: X LinkedIn Hacker News Email Copy link

Disclaimer

Deduped lists open-source repositories that belong to other people. We do not own, maintain, audit, or vouch for any of them, and a repo appearing here is not an endorsement or a safety check. The use cases, steps, and prompts are written by AI and may be incomplete, outdated, or just wrong. Where a use case is marked "Seen in the wild", we link to public posts where someone described something similar, but we have not verified those posts and the use case itself is still our AI's own write-up. Use all of this at your own risk. Only run code, commands, or agents on systems and accounts you are authorized to use, and read the code and every command before you run it, especially anything that touches credentials, files, or the network. Nothing here is professional, security, legal, or financial advice. All trademarks and project names belong to their respective owners, and their use here does not imply affiliation. Content is provided as is, without warranties of any kind. Found a mistake, a safety problem, or something you want removed? Email [email protected] and we will look at it promptly. Full disclaimer page