agentleFS
Sign inStart free
LiminaLabsAILiminaLabsAI/ToolsConnector/.agents/skills/connector_implementer/SKILL.md

connector_implementer

Skill1 starsChanged 7 months agoApache-2.0View on GitHub

Connector Implementer Persona for integrating new tools into the registry.

The file

We split this skill into the rules it gives an agent

6 rules. About 0 are common, 0 are distinctive, and 6 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈0

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 6

    Very specific

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

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

    Full Capability First: Do not build a "least common denominator." Expose the full power of the tool, but wrap it cleanly using the global …

    line 11
  2. Very specific:

    Auth Handling: Every connector must declare its valid auth_types and leverage the core Authentication protocols.

    line 12
  3. Very specific:

    If a tier-1 official, healthy SDK exists (e.g., google-api-python-client), wrap it.

    line 14
  4. Very specific:

    If no healthy SDK exists, use directly httpx or auto-generate via OpenAPI inside the connector boundary.

    line 15
  5. Very specific:

    When asked to create a Connector, create a directory in connectors/ with the tool's name.

    line 19
  6. Very specific:

    Add the connector to the pyproject.toml extra dependencies specifically for that tool.

    line 21

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 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

Connector Implementer Persona

Overview

You act as the primary implementer of individual tools (e.g., Gmail, Slack, Jira). Your job is to construct the Python classes that wrap these tools and expose them via the unified ToolsConnector interface.

Rules

  1. Full Capability First: Do not build a "least common denominator." Expose the full power of the tool, but wrap it cleanly using the global @action decorators and standard Python types.
  2. Auth Handling: Every connector must declare its valid auth_types and leverage the core Authentication protocols. DO NOT write raw OAuth callback HTTP servers inside the connector.
  3. Use the Right Underlayer:
    • If a tier-1 official, healthy SDK exists (e.g., google-api-python-client), wrap it.
    • If no healthy SDK exists, use directly httpx or auto-generate via OpenAPI inside the connector boundary.
  4. Typing and Docstrings: You MUST type everything. Docstrings MUST clearly explain constraints, as these docstrings will literally become the LLM function calling descriptions later.

Execution Workflow

  1. When asked to create a Connector, create a directory in connectors/ with the tool's name.
  2. Separate the logic into connector.py and types.py.
  3. Add the connector to the pyproject.toml extra dependencies specifically for that tool.
  4. Review the /plan/brainstorm.md file for deeper philosophy when in doubt.

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