Agent skill
setup
Set up or update TDD Guard for the current project. Detects the test framework, installs or updates the matching reporter, and configures or migrates its configuration to match the current specification.
Install this agent skill to your Project
npx add-skill https://github.com/nizos/tdd-guard/tree/main/plugin/skills/setup
SKILL.md
TDD Guard Setup
Set up TDD Guard for the current project. Your goal is to:
- Identify the test framework(s) used in this project
- Install the matching TDD Guard reporter, or update it if already present
- Configure the reporter, or migrate an existing configuration to match the current specification
Reporter packages
| Framework | Reporter package | Registry |
|---|---|---|
| Vitest | tdd-guard-vitest | npm |
| Jest | tdd-guard-jest | npm |
| Storybook | tdd-guard-storybook | npm |
| pytest | tdd-guard-pytest | PyPI |
| PHPUnit | tdd-guard/phpunit | Packagist |
| Go | github.com/nizos/tdd-guard/reporters/go/cmd/tdd-guard-go | go install |
| Rust | tdd-guard-rust | crates.io |
| RSpec | tdd-guard-rspec | RubyGems |
Reporter configuration
All reporters write test results to .claude/tdd-guard/data/test.json relative to the project root.
Vitest — Add the reporter entry to the reporters array with projectRoot in the options object.
reporters: [
'default',
['tdd-guard-vitest', { projectRoot: '/absolute/path/to/project' }],
]
Jest — Add reporter entry to the reporters array with projectRoot option.
reporters: [
'default',
['tdd-guard-jest', { projectRoot: '/absolute/path/to/project' }],
]
Storybook — Construct StorybookReporter in .storybook/test-runner.ts and wire it into the postVisit hook.
// .storybook/test-runner.ts
import { StorybookReporter } from 'tdd-guard-storybook'
const reporter = new StorybookReporter({
projectRoot: '/absolute/path/to/project',
})
module.exports = {
async postVisit(page, context) {
await reporter.onStoryResult(context)
},
}
process.on('exit', () => {
reporter.onComplete()
})
pytest — Set tdd_guard_project_root in pytest config (pyproject.toml, pytest.ini, or setup.cfg).
[tool.pytest.ini_options]
tdd_guard_project_root = "/absolute/path/to/project"
PHPUnit — Add extension (PHPUnit 10+) or listener (PHPUnit 9.x) to phpunit.xml with project root path.
<!-- PHPUnit 10+ -->
<extensions>
<bootstrap class="TddGuard\PHPUnit\TddGuardExtension">
<parameter name="projectRoot" value="/absolute/path/to/project"/>
</bootstrap>
</extensions>
<!-- PHPUnit 9.x -->
<listeners>
<listener class="TddGuard\PHPUnit\TddGuardListener">
<arguments>
<string>/absolute/path/to/project</string>
</arguments>
</listener>
</listeners>
Go — Add a test target using the piped command below. Update an existing Makefile, Taskfile, or similar build system if one exists.
go test -json ./... 2>&1 | tdd-guard-go -project-root /absolute/path/to/project
Rust — Add a test target using the piped command below. Update an existing Makefile, Taskfile, or similar build system if one exists.
cargo nextest run 2>&1 | tdd-guard-rust --project-root /absolute/path/to/project --passthrough
RSpec — Add the formatter to .rspec and set TDD_GUARD_PROJECT_ROOT environment variable to the absolute project root path.
--format TddGuardRspec::Formatter
export TDD_GUARD_PROJECT_ROOT="/absolute/path/to/project"
Guidelines
Your scope is limited to installing, updating, configuring, and migrating a TDD Guard reporter. Do not make changes beyond that.
- Always use absolute paths when configuring the project root in reporters.
- Do not install, update, or modify test frameworks, build tools, or any other project dependencies. Only install or update the TDD Guard reporter itself.
- Do not modify existing test configuration beyond the TDD Guard reporter entry. Migrate any drifted reporter configuration to match the current specification, preserving the user's project root value and leaving unrelated entries untouched. If the existing configuration cannot be migrated without guessing — for example, because it is wrapped in user-defined code or intermingled with custom logic — inform the user and let them decide.
- If a TDD Guard reporter is already installed and its configuration matches this skill's specification, inform the user that everything is up to date and stop.
- If multiple frameworks are detected, ask the user which to configure.
- If something goes wrong or is unclear, inform the user rather than attempting to fix it. Do not install additional packages or make extra changes to resolve issues.
After setup
Once complete, inform the user of what was done and that:
- TDD Guard validates changes against TDD principles
- They can type
tdd-guard off/tdd-guard onto toggle it mid-session - They can customize validation rules by editing
.claude/tdd-guard/data/instructions.md - More help and configuration options are available at https://github.com/nizos/tdd-guard
Recommended Agent Skills
Expand your agent's capabilities with these related and highly-rated skills.
verl-rl-training
Provides guidance for training LLMs with reinforcement learning using verl (Volcano Engine RL). Use when implementing RLHF, GRPO, PPO, or other RL algorithms for LLM post-training at scale with flexible infrastructure backends.
openrlhf-training
High-performance RLHF framework with Ray+vLLM acceleration. Use for PPO, GRPO, RLOO, DPO training of large models (7B-70B+). Built on Ray, vLLM, ZeRO-3. 2× faster than DeepSpeedChat with distributed architecture and GPU resource sharing.
gguf-quantization
GGUF format and llama.cpp quantization for efficient CPU/GPU inference. Use when deploying models on consumer hardware, Apple Silicon, or when needing flexible quantization from 2-8 bit without GPU requirements.
Claude Code Guide
Master guide for using Claude Code effectively. Includes configuration templates, prompting strategies "Thinking" keywords, debugging techniques, and best practices for interacting with the agent.
qdrant-vector-search
High-performance vector similarity search engine for RAG and semantic search. Use when building production RAG systems requiring fast nearest neighbor search, hybrid search with filtering, or scalable vector storage with Rust-powered performance.
behavioral-modes
AI operational modes (brainstorm, implement, debug, review, teach, ship, orchestrate). Use to adapt behavior based on task type.
Didn't find tool you were looking for?