agentleFS
Sign inStart free
berntpoppberntpopp/spliceailookup-link/.claude/skills/mcp-tool-change/SKILL.md

mcp-tool-change

Skill0 starsChanged 4 months agoMITView on GitHub

Use when adding, renaming, or modifying an MCP tool in spliceailookup-link

We split this skill into the rules it gives an agent

4 rules. 0 are common, 0 are distinctive, and 4 are very specific to this project.

  • 0

    Common

    Most of the 11 edited versions we read keep these.

  • 0

    Distinctive

    This author's own choices. Worth a look.

  • 4

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Follow this checklist when touching the MCP surface in spliceailookup_link/mcp/.

    line 8
  2. Very specific:

    Add a new error_code only with a recovery action + recovery text.

    line 21
  3. Very specific:

    Capabilities: update mcp/resources.py (tools, parameters, score_glossary, recommended_workflows).

    line 22
  4. Very specific:

    Tests: add a tests/unit/test_tools.py case via mcp.call_tool + the StubService, and a tests/integration case if behavior depends on live …

    line 24

“Common” is measured: kept by at least 6 in 10 of the 11 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 or changing an MCP tool

Follow this checklist when touching the MCP surface in spliceailookup_link/mcp/.

  1. Define the tool in a module under spliceailookup_link/mcp/tools/. Reuse the pattern in spliceai.py: @mcp.tool(name=, title=, annotations=READ_ONLY_OPEN_WORLD, tags=), typed Annotated[..., Field(...)] params, a dense AI-facing docstring (what it does, when to use, what it returns, token cost), an inner async def call(), and return await run_mcp_tool(name, call, context=McpErrorContext(...)).
  2. Register it in spliceailookup_link/mcp/tools/__init__.py:register_splice_tools.
  3. Shape the output in spliceailookup_link/mcp/shaping.py (compact/full/minimal + a headline). Never return raw upstream keys (DS_AG, etc.) — rename to readable classes.
  4. Chain via _meta.next_commands (same-server, ready-to-call) and _meta.see_also (cross-server hints). Use builders in next_commands.py / _common.py.
  5. Errors: raise typed exceptions; the envelope in mcp/errors.py classifies them. Add a new error_code only with a recovery action + recovery text.
  6. Capabilities: update mcp/resources.py (tools, parameters, score_glossary, recommended_workflows).
  7. Tests: add a tests/unit/test_tools.py case via mcp.call_tool + the StubService, and a tests/integration case if behavior depends on live upstream.
  8. Run make ci-local. Keep modules < 600 lines (make lint-loc).

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.

Check your setup, free