agentleFS
refined-elementrefined-element/lightning-enable-mcp/.claude/skills/mcp-publish-prep/SKILL.md

mcp-publish-prep

Skill9 starsChanged 36 days agoMITView on GitHub

Prepare MCP package for publishing (version bump, changelog, validation)

  • Reads credentials

The file

We split this skill into the rules it gives an agent

7 rules. About 0 are common, 2 are distinctive, and 5 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈2

    Distinctive · estimate

    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. Very specific:

    Check description field is ≤100 characters (enforced by MCP Registry and CI)

    line 17
  2. Very specific:

    Update version field if present (CI auto-updates via jq, but good to keep in sync)

    line 18
  3. Distinctive:

    Update changelog: if one exists

    line 20
  4. Very specific:

    Run dotnet build in dotnet/src/LightningEnable.Mcp/

    line 23
  5. Distinctive:

    Verify no build errors

    line 24
  6. Very specific:

    Check .github/workflows/publish-mcp.yml is up to date

    line 27
  7. Very specific:

    Verify secrets are configured: NUGET_API_KEY, PYPI_API_TOKEN, DOCKERHUB_USERNAME, DOCKERHUB_TOKEN

    line 28

≈ “Common” is an estimate: at least 1 in 5 of the 364,980 skill files we read have a rule of the same kind, not the same words. “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

Prepare the MCP package for a new release. Use $ARGUMENTS for the new version number (e.g., 1.5.0).

Steps

  1. Bump version in BOTH files (CRITICAL — must be simultaneous):
    • dotnet/src/LightningEnable.Mcp/LightningEnable.Mcp.csproj — update <Version>
    • python/lightning-enable-mcp/pyproject.toml — update version
    • dotnet/src/LightningEnable.Mcp/Services/UserAgent.cs — update FallbackVersion (UserAgentTests fails on drift)
    • These MUST match. CI/CD publishes both from the same version.
  2. Validate server.json:
    • Check description field is ≤100 characters (enforced by MCP Registry and CI)
    • Update version field if present (CI auto-updates via jq, but good to keep in sync)
  3. Update changelog if one exists
  4. Build verification:
    • Run dotnet build in dotnet/src/LightningEnable.Mcp/
    • Verify no build errors
  5. Review CI/CD:
    • Check .github/workflows/publish-mcp.yml is up to date
    • Verify secrets are configured: NUGET_API_KEY, PYPI_API_TOKEN, DOCKERHUB_USERNAME, DOCKERHUB_TOKEN

Publishing targets (all automated on push to main):

  • NuGet: https://www.nuget.org/packages/LightningEnable.Mcp
  • PyPI: https://pypi.org/project/lightning-enable-mcp
  • Docker Hub: https://hub.docker.com/r/refinedelement/lightning-enable-mcp
  • MCP Registry: https://registry.modelcontextprotocol.io

Output

Report the version bump, validation results, and build status. Remind the user to push to main to trigger CI/CD.

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.