TimmyTest — Testing skill for Claude Code
Local test runner for vibe coding and AI coding agents.
How to install TimmyTest
This entry records only its repository, not the path inside it, so there is no
exact command to give. Open tugrakaymakcioglu/TimmyTest and copy the folder into
~/.claude/skills/, or the file into ~/.claude/agents/.
What TimmyTest does
Local test runner for vibe coding and AI coding agents. Run tests, find likely test gaps, and hand concise failure reports to Claude Code, Codex or Cursor.
Alternatives in Testing
- Test Runner — Run Python tests with pytest, unittest, or other testing frameworks 23.4k ★
- Spec Kitty — Spec-Driven Development for serious software developers 1.6k ★
- Spec Driven Develop — Spec-driven development workflow for AI coding agents: architecture-first planning, task decomposition, GitHub 975 ★
README
⚡ TimmyTest
Zero-Token Test Runner • AST Test Gap Analyzer • AI Agent Prompt Generator • MCP Server
**English** · [Türkçe](README.tr.md) · [中文](README.zh-CN.md)
[](https://www.python.org/) [](https://github.com/tugrakaymakcioglu/TimmyTest/actions/workflows/ci.yml) [](tests/) [](LICENSE) [](#-model-context-protocol-mcp-server) [](#-installation)
**Give your coding agent a useful test report before it starts debugging.** TimmyTest runs your existing tests locally, identifies likely missing tests and summarizes failures in a short prompt you can hand to Claude Code, Codex or Cursor. The local scan and test run do not call an AI API; the handoff prompt still consumes tokens when you send it to an agent.
python -m pip install "git+https://github.com/tugrakaymakcioglu/TimmyTest.git@v2.0.1"
timmytest check .
Install from GitHub for now. The package is not yet available on PyPI; the `pip install timmytest` and `uvx timmytest` commands will work only after a PyPI release.
If the first run fails or the report is unclear, [open an issue](https://github.com/tugrakaymakcioglu/TimmyTest/issues/new/choose) with the command, operating system and a redacted output sample. Real project feedback will guide the next release.
[
Related Skills
Vibe Testing
Code-aware browser testing agent — 13 MCP tools for AI editors (Claude Code, Cursor, Windsurf). Reads your cod
Cfn Pseudo
SPARC Pseudocode phase. Trace logic, enumerate branches, find failure paths, verify branch coverage BEFORE wri
Solid Agent
Open spec + reference implementation for composing coding agents (Claude, Codex, AmpCode, Cursor, Pi, …) with
Atomic Spec
Stop your AI from vibe-coding. Governance layer that forces Claude, Cursor, Copilot, Gemini & 13 more through
Contract Test Agent
AI agent (Claude Agent SDK) that writes and runs Specmatic consumer contract tests for Java Spring services, u
Specralph
Spec-driven AI coding automation CLI. AI Loops runner for Claude Code, OpenCode, Cursor, and other agent CLIs.
Related Agents
Envoy Runner
Proactively use when Claude Code is stuck, wants a second implementation or diagnosis pass, needs a deeper roo
Cursor Delegate
Proactively use when this coding agent should hand a substantial coding, diagnosis, or implementation task to
Model Runner
Deterministic wrapper that runs a prompt on a non-Claude model (OpenAI via Codex, Cursor's composer/grok/glm,