Skip to content
Development
Skill

/test-writer

Generate comprehensive test suites for existing code

From plugin
pydantic-deepagents
1k14 skills
Install
$ npx -y skills add vstorm-co/pydantic-deepagents --skill test-writer --agent claude-code

How it fires

How this skill gets triggered: by you, by Claude, or both.

  • Fires itselfAuto-invocation. Claude auto-loads it when your prompt matches the work.Auto-invocation is when the right skill fires by itself at the right moment, driven by a FLOW.md router and a hook, instead of you invoking it by name. It is the difference between a skill being installed and a skill actually getting used.Read the full definition →
  • You can call itInvoke it directly when you want it.
  • Slash command/test-writer

Context preview

The summary Claude sees to decide when to auto-load this skill.

Generate comprehensive test suites for existing code

SKILL.md

test-writer.SKILL.md
name: test-writer
description: "Generate comprehensive test suites for existing code"
tags: [testing, code-quality]
version: "1.0.0"

Test Writer

Generate comprehensive tests for the target code.

Process

1. Read the source code to understand all public functions/methods 2. Identify the testing framework already used in the project (pytest, unittest, etc.) 3. Follow existing test patterns and conventions in the project 4. Write tests covering all categories below

Coverage Strategy

Happy Path

  • Normal inputs with expected outputs
  • All public methods/functions

Edge Cases

  • Empty inputs (empty string, empty list, None)
  • Boundary values (0, -1, max int)
  • Single element collections

Error Cases

  • Invalid input types
  • Missing required arguments
  • Network/IO failures (mock external calls)

Integration

  • Multiple functions working together
  • State changes across calls

Guidelines

  • One test function per behavior, not per method
  • Descriptive test names: `test_<what>_<condition>_<expected>`
  • Use fixtures for shared setup
  • Mock external dependencies (APIs, databases, filesystem)
  • Assert specific values, not just truthiness
  • Test both return values and side effects
Ships withpydantic-deepagents

Open-source, self-hosted Claude Code - a terminal AI assistant and the Python framework behind it. Tool-calling, sandboxed execution, multi-agent teams, skills, checkpoints, unlimited context - on Pydantic AI, any model.

Get the whole plugin
Stats
1,021
Stars
120
Forks
Active
Maintenance
Python
Language
MIT
License
4d ago
Last commit
8mo ago
Created

Repo: vstorm-co/pydantic-deepagents