agentsclimarketplace

Mcp docs and implement

Skill wchen02/cursor-agent-learning/.cursor/skills/mcp-docs-and-implement

A hands-on project to learn Cursor’s agent customization: rules, skills, subagents, commands, hooks, and AGENTS.md. Everything is set up with examples and docs so you can try things and tweak them.

Install
npx -y skills add wchen02/cursor-agent-learning --skill mcp-docs-and-implement

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

2 things to look at

  • no licenseNo license file was found in the repository. Code published without one is not open source by default, so using it at work is a question for whoever answers licensing questions where you are.
  • 1 stars1 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.

What its author says it does

Copied from the file, not written here

Implement using up-to-date docs or APIs via MCP. Use when the user wants to build something with current library/API docs (e.g. Context7, Stripe) and MCP is available.

SKILL.md

2.6 KB, as published. Nobody here has run it

MCP Docs → Plan → Implement

This skill runs a workflow that uses MCP (Model Context Protocol) to fetch current documentation or API schemas, then plans and implements. Use when the project depends on external APIs or libraries and you want up-to-date references without pasting docs manually.

MCP best practice: check tool schema first

Before calling any MCP tool, read the tool’s descriptor/schema (e.g. under mcps/<server>/tools/<tool>.json) so you use correct parameters and required fields. Do not guess; check the schema.

Steps

  1. Fetch docs or schema via MCP

    • Use MCP tools or resources to get current docs or API schema for the library/API the user asked about (e.g. Context7 for library docs, Stripe MCP for payments).
    • Use resources for read-only docs/data; use tools when you need to perform an action (query, API call). Check each tool’s schema before calling.

  2. Plan (optional)

    • Optionally invoke the planner subagent with the fetched context to refine scope and steps (e.g. “what endpoints exist?”). Planner inherits MCP; it can call the same servers if needed.

  3. Implement

    • Implement using the retrieved docs. Call MCP again during implementation if you need finer-grained details (signatures, options, examples).
    • Follow project rules. Prefer checking tool schema before each MCP call.

  4. Verify (optional)

    • Optionally invoke the verifier subagent to confirm the implementation matches the docs or passes tool-based checks. Verifier can use MCP for compliance checks.

Notes

Keep looking

Skills are one crate of 328,083. Ordering is by how many stacks a row turns up in, so the top of any crate is what has actually been picked rather than what has the most stars.