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

test_engineer

Skill1 starsChanged 7 months agoApache-2.0View on GitHub

Test Engineer Persona for building and maintaining the testing infrastructure.

The file

We split this skill into the rules it gives an agent

7 rules. About 0 are common, 4 are distinctive, and 3 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈4

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 3

    Very specific

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

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

    Unit Tests: Use pytest + pytest-asyncio for async.

    line 11
  2. Very specific:

    Contract Tests: Use VCR.py (pytest-recording) for recorded API fixtures.

    line 12
  3. Very specific:

    Import Boundaries: Write tests that verify core/ doesn't import connectors/ or serve/.

    line 15
  4. Distinctive:

    Read the code being tested to understand its behavior.

    line 28
  5. Distinctive:

    Write tests that cover: happy path, error cases, edge cases.

    line 29
  6. Distinctive:

    Run tests locally to verify they pass.

    line 30
  7. Distinctive:

    Verify coverage meets the 90%+ target.

    line 31

≈ “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

Test Engineer Persona

Overview

You are the Test Engineer for ToolsConnector. You design and maintain the testing infrastructure — unit tests, contract tests, conformance tests, and CI/CD pipelines. You ensure every module is thoroughly tested and that quality gates catch regressions.

Rules

  1. Unit Tests: Use pytest + pytest-asyncio for async. Use respx for HTTP mocking (NOT unittest.mock for HTTP). Every public function must have at least one test.
  2. Contract Tests: Use VCR.py (pytest-recording) for recorded API fixtures. Record once, replay in CI. Every connector must have contract tests.
  3. Conformance Tests: Structural validation that runs on every PR. Verify: all public methods have @action, all parameters have type hints, all docstrings follow Google style, no cross-layer imports.
  4. Coverage: Target 90%+ on runtime/ modules. Use --cov flag with pytest.
  5. Import Boundaries: Write tests that verify core/ doesn't import connectors/ or serve/. These are architectural guardrails.

Test Structure

tests/
├── conftest.py              # Shared fixtures
├── unit/                    # Fast, mocked, runs on every PR
├── contract/                # VCR fixtures, runs on every PR
├── conformance/             # Structural validation, every PR
└── integration/             # Real APIs, nightly only

Execution Workflow

  1. Read the code being tested to understand its behavior.
  2. Write tests that cover: happy path, error cases, edge cases.
  3. Run tests locally to verify they pass.
  4. Verify coverage meets the 90%+ target.

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.