agentleFS
QBT-LabsQBT-Labs/openmm-mcp/.claude/skills/new-tool/SKILL.md

new-tool

Skill3 starsChanged 8 months agoMITView on GitHub

Follow this exact pattern when adding a new tool. Do not invent new registration patterns or file structures.

5 other projects use a version of this.

Adopted by

Most recently taken up by

  • Other versions5 projects use a version of this.

    Word for word · 0

    None found.

    Edited · 0

    None found.

    Wrote their own version · 5

    1. ShenSeanChen/waku-agent★ 2.2ksame name
    2. OpenC3/cosmos★ 261same name
    3. TobiasMue91/tobiasmue91.github.io★ 59same name
    4. jamesmccomish/mp-mcp★ 2same name
    5. wnkinc/claude-custom-connector-server★ 1same name

    How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.

  • In this repository2 other files it gives its agents.

The file

We split this skill into the rules it gives an agent

8 rules. 0 are common, 3 are distinctive, and 5 are very specific to this project.

  • 0

    Common

    Most of the 5 edited versions we read keep these.

  • 3

    Distinctive

    This author's own choices. Worth a look.

  • 5

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Follow this exact pattern when adding a new tool.

    line 3
  2. Very specific:

    Add the handler inside the existing register*Tools(server, exchangeManager) function

    line 9
  3. Very specific:

    If you created a new category file, import and call its register*Tools() function here

    line 13
  4. Distinctive:

    Add the tool to the tools table with name, description, and parameters

    line 17
  5. Very specific:

    Add the tool name to the appropriate tier in TOOL_PRICING

    line 21
  6. Distinctive:

    Test parameter validation and expected output shape

    line 25
  7. Very specific:

    Create new files under src/ for a single tool — add to the matching category file

    line 28
  8. Very specific:

    Use require() — this project is ESM (NodeNext)

    line 29

“Common” is measured: kept by at least 6 in 10 of the 5 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Adding a New MCP Tool

Follow this exact pattern when adding a new tool. Do not invent new registration patterns or file structures.

Steps

  1. Implement in src/tools/<category>.ts
    • Define a Zod schema for the tool's parameters using validators from src/utils/validators.ts
    • Add the handler inside the existing register*Tools(server, exchangeManager) function
    • Return { content: [{ type: 'text', text: JSON.stringify(...) }] }
  2. Register in src/tools/index.ts
    • If you created a new category file, import and call its register*Tools() function here
    • Existing categories (market-data, account, trading, cardano, strategy) are already wired up
  3. Update README.md
    • Add the tool to the tools table with name, description, and parameters
    • Assign a pricing tier: free (list_exchanges only), read ($0.001), or write ($0.01)
  4. Add pricing in src/payment/index.ts
    • Add the tool name to the appropriate tier in TOOL_PRICING
  5. Add unit test in src/tests/
    • Mock the exchange connector via getConnectorSafe()
    • Test parameter validation and expected output shape

Do NOT

  • Create new files under src/ for a single tool — add to the matching category file
  • Use require() — this project is ESM (NodeNext)
  • Skip npm run typecheck after changes

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.