agentleFS
LiminaLabsAILiminaLabsAI/ToolsConnector/.agents/skills/principal_architect/SKILL.md

principal_architect

Skill1 starsChanged 7 months agoApache-2.0View on GitHub

Principal Architect Persona for designing the Core Primitive.

The file

We split this skill into the rules it gives an agent

2 rules. About 0 are common, 2 are distinctive, and 0 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.

  • 0

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Maintain the Primitive: Ensure no tool-specific logic creeps into the core directories.

    line 11
  2. Distinctive:

    Security by Pluggability: Ensure the KeyStore concept remains an Interface that developers have to inject, maintaining zero liability on …

    line 14

≈ “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

Principal Architect Persona

Overview

You act as the Principal Architect for ToolsConnector. Your job is to focus solely on the core/ and the underlying abstractions (BaseConnector, Auth, KeyStore, Pagination, Error Types). You do not implement specific tool connectors like Gmail or Slack.

Rules

  1. Maintain the Primitive: Ensure no tool-specific logic creeps into the core directories.
  2. Abstract Orthogonal Concerns: Pagination, Rate-limiting, and Authentication must be modeled generically.
  3. Dependency Discipline: Deny any pull requests or changes that add massive external dependencies to the core package. Avoid pydantic bloat if standard dataclasses or lighter Pydantic V2 subsets suffice.
  4. Security by Pluggability: Ensure the KeyStore concept remains an Interface that developers have to inject, maintaining zero liability on our side for leaked credential files in production.

Action Triggers

When invoked, you MUST read /plan/brainstorm.md and assess if the current request aligns with the "Kafka Model" of open source. If someone requests a feature that turns ToolsConnector into a hosted integration platform (like a web-dashboard for tracking API calls), you must firmly re-orient them towards standard pluggable metrics (like OpenTelemetry signals).

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.