New: 98,000+ skills indexed from GitHub repos with 100+ stars · every skill safety-checkedBrowse top skillsTop skills
Esc to closeBrowse all skills
Submit a skillBrowse skills
Submit a skillBrowse skills

Agent skill

Aidd TDD

by paralleldrive in paralleldrive/aidd

Systematic test-driven development with proper test isolation.

MITAuto-check passedTesting & QA

Install Aidd TDD

skills CLI
$ npx skills add paralleldrive/aidd --skill aidd-tdd -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install paralleldrive/aidd aidd-tdd --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/paralleldrive/aidd.git skills-src && mkdir -p .claude/skills && cp -r skills-src/ai/skills/aidd-tdd .claude/skills/aidd-tdd && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
aidd-tdd
GitHub stars
384
Token cost
~1.2k tokens
SKILL.md length
693 words
Files
2
Skills in repo
35
Repo updated
First seen
Licence
MIT

At a glance

Systematic test-driven development with proper test isolation.

  • Works in 7 steps: If the user has not specified a test… → If the calling API is unspecified,… → Write a test. Run the test runner and… → …
  • Implementing code changes
  • SKILL.md covers assert, Process, Describe/Test Wrappers and Default Test Utils
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Aidd TDD is an agent skill from paralleldrive/aidd. Systematic test-driven development with proper test isolation. Use when implementing code changes, writing tests, or when TDD process guidance is needed.

Its SKILL.md is about 1.2k tokens, which your agent loads only when the skill is triggered. The skill folder holds 1 other file (for example `README.md`).

It sits in Testing & QA, covering Test-driven development. The repository describes itself as: The standard framework for AI Driven Development. The licence is MIT.

When your agent uses it

  • Implementing code changes
  • TDD process guidance is needed

Example prompts

  • “/aidd-tdd”

Workflow steps

7 steps, taken from the first numbered list in SKILL.md.

  1. If the user has not specified a test framework or technology stack, ask them before implementing.
  2. If the calling API is unspecified, propose a calling API that serves the functional requirements and creates an optimal developer…
  3. Write a test. Run the test runner and watch the test fail.
  4. Implement the code to make the test pass. Implement ONLY the code needed to make the test pass.
  5. Run the test runner: fail => fix bug; pass => continue
  6. Get approval from the user before moving on.
  7. Repeat the TDD iteration process for the next functional requirement.

What it can do on your machine

Read from SKILL.md and the folder at commit 9a7c8e3. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    No scripts in the folder and no shell commands in SKILL.md.

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Aidd TDD loads about 1.2k tokens when it runs. Until then it costs about 41 tokens; SKILL.md has 693 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~41
When it runs · the whole SKILL.md, loaded when a task matches
~1.2k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from paralleldrive/aidd at commit 9a7c8e3, republished under its MIT licence (© paralleldrive). 693 words, ~1,219 tokens.

Download SKILL.mdSave it as .claude/skills/aidd-tdd/SKILL.md (or your agent's skills folder). This skill also uses 1 other file; get the full folder from GitHub.
name
aidd-tdd
description
Systematic test-driven development with proper test isolation. Use when implementing code changes, writing tests, or when TDD process guidance is needed.

TDD Engineer

Act as a top-tier software engineer with serious TDD discipline to systematically implement software using the TDD process.

assert

type assert = ({ given: string, should: string, actual: any, expected: any }) { given and should must clearly state the functional requirements from an acceptance perspective, and should avoid describing literal values. Tests must demonstrate locality: The test should not rely on external state or other tests.

Ensure that the test answers these 5 questions { 1. What is the unit under test? (test should be in a named describe block) 2. What is the expected behavior? ($given and $should arguments are adequate) 3. What is the actual output? (the unit under test was exercised by the test) 4. What is the expected output? ($expected and/or $should are adequate) 5. How can we find the bug? (implicitly answered if the above questions are answered correctly) }

Tests must be:

  • Readable - Answer the 5 questions.
  • Isolated/Integrated
    • Units under test should be isolated from each other
    • Tests should be isolated from each other with no shared mutable state.
    • For integration tests, test integration with the real system.
  • Thorough - Test expected/very likely edge cases
  • Explicit - Everything you need to know to understand the test should be part of the test itself. If you need to produce the same data structure many times for many test cases, create a factory function and invoke it from the individual tests, rather than sharing mutable fixtures between tests. }

Process

For each unit of code, create a test suite, one requirement at a time:

  1. If the user has not specified a test framework or technology stack, ask them before implementing.
  2. If the calling API is unspecified, propose a calling API that serves the functional requirements and creates an optimal developer experience.
  3. Write a test. Run the test runner and watch the test fail.
  4. Implement the code to make the test pass. Implement ONLY the code needed to make the test pass.
  5. Run the test runner: fail => fix bug; pass => continue
  6. Get approval from the user before moving on.
  7. Repeat the TDD iteration process for the next functional requirement.

Describe/Test Wrappers

In most testing frameworks, there is a describe function and possibly a nested test or it wrapper.

Use the string in the describe function to name the unit under test.

Use the string in the test function to offer a brief category for the test, e.g. "new account creation".

Because of conflicts with the assert function API and description, avoid the it wrapper entirely, if possible.

Show full SKILL.md (272 more words)Show less

Default Test Utils

For Vitest/Riteway tests:

  • Spies and stubs: vi.fn and vi.spyOn
    • Vitest ships tinyspy under the hood. Simple, fast, and no extra deps.
  • Module mocking: vi.mock with vi.importActual for partial mocks
    • Works cleanly with ESM. Avoid require.
  • Timers: vi.useFakeTimers and vi.setSystemTime
    • UI testing strategy:
    • Redux actions/selectors: Pure tests (no component rendering needed)
    • Side effects: must be isolated from UI, see /aidd-javascript-io-effects
    • Component rendering: Use riteway/render for markup verification
    • Browser interactions: Use Playwright to exercise real browser APIs
    • Never use @testing-library/react (redundant with above patterns)

Constraints { Unless directed otherwise, always colocate tests with the code they are testing. Carefully think through correct output. Avoid hallucination. This is very important to ensure software works as expected and that user safety is protected. Please do your best work. When testing app state logic, always use selectors to read from the state. NEVER read directly from state objects. Avoid writing tests for expected types/shapes. It would be redundant with type checks.

Mocking is a code smell. { mocks in unit tests => build both a mocked and an integration candidate; run /aidd-churn to compare total code impact; the winning approach must (1) lower or match the composite score AND (2) meaningfully exercise the functional requirement of the unit under test — not just verify mock calls. Cheaper substitutes (e.g. echo instead of a real LLM) are preferred when they satisfy both conditions. Mocks are only justified when real integration is (a) technically infeasible or (b) prohibitively expensive — meaning irrecoverable real-world side effects, physical infrastructure unavailable in CI, or per-run cost that makes the test suite economically non-viable. } }

State { testFramework = Riteway Library + Vitest libraryStack // e.g. React + Redux + Redux Saga }

© paralleldrive, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 1 other file in ai/skills/aidd-tdd of paralleldrive/aidd.

  • SKILL.md
  • README.md

Open the folder on GitHubat commit 9a7c8e3

Compare with similar skills

Aidd TDD next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Aidd TDD compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Aidd TDD this skillparalleldrive/aidd384—~1.2kAutomated safety check: PassMIT
TDDpietheinstrengholt/rssmonster56430 repos~906Automated safety check: PassMIT
TDD WorkflowhellangleZ/burn-in-cceverywhere-ralph11211 repos~2.4kAutomated safety check: PassNone
TDDsanity-io/sanity6.4k20 repos~1kAutomated safety check: PassMIT
Test Driven Developmentfarm-fe/farm5.6k51 repos~2.5kAutomated safety check: PassMIT
Tapd Story PipelineTencentBlueKing/bk-bcs840—~2.6kAutomated safety check: PassCustom licence

Similar skills

  • TDD

    pietheinstrengholt/rssmonster

    Test-driven development. An agent skill from pietheinstrengholt/rssmonster.

    564 GitHub starsUsed in 30 repos~906 tokens
    Testing & QAAuto-check passed

  • TDD Workflow

    hellangleZ/burn-in-cceverywhere-ralph

    A skill your agent uses when writing new features, fixing bugs, or refactoring code.

    112 GitHub starsUsed in 11 repos~2.4k tokens
    Testing & QAAuto-check passed

  • TDD

    sanity-io/sanity

    Official

    Test-driven development with red-green-refactor loop. An agent skill from sanity-io/sanity.

    6.4k GitHub starsUsed in 20 repos~1k tokens
    Testing & QAAuto-check passed

  • Test Driven Development

    farm-fe/farm

    A skill your agent uses when implementing any feature or bugfix, before writing implementation code

    5.6k GitHub starsUsed in 51 repos~2.5k tokens
    Testing & QAAuto-check passed

  • Tapd Story Pipeline

    TencentBlueKing/bk-bcs

    单需求实现流水线——把一个 TAPD 需求从零推进到代码提交。自动串联技术澄清、 开发计划、任务拆分、TDD 实现、架构/安全校验、代码提交六个阶段。

    840 GitHub stars~2.6k tokensUpdated today
    Testing & QAAuto-check passed

  • Absolute Init

    maddhruv/absolute

    One-time setup for absolute: interview how you want it to behave (output style, autonomy, TDD strictness, spec dir, families) + detect the stack once, then write .absolute.config.json (project…

    218 GitHub starsUsed in 1 repo~3k tokens
    Testing & QAAuto-check passed

More from paralleldrive/aidd

All 35 skills in this repo

  • AIDD Skill Authoring Guide

    paralleldrive/aidd

    Guides creating, reviewing or refactoring AI-Driven Development skills so each one stays minimal, composable and named around a single clear function.

    384 GitHub stars~1.1k tokensUpdated 3 mo ago
    Auto-check passed

  • AIDD UI Layout Patterns

    paralleldrive/aidd

    Enforces a split of UI components into terminal and layout types, with layout components composing others through standard layout tokens, for cleaner structure and fewer re-renders.

    384 GitHub stars~562 tokensUpdated 3 mo ago
    Auto-check passed

  • Adobe Data ECS Plugin Rules

    paralleldrive/aidd

    Enforces @adobe/data/ecs practices when writing Database.Plugin definitions, including property order, plugin composition, services, components, resources and archetypes.

    384 GitHub stars~1.9k tokensUpdated 3 mo ago
    Auto-check passed

  • Error Causes Handling

    paralleldrive/aidd

    Has your agent throw and catch JavaScript and TypeScript errors with the error-causes library, using named causes, preserved originals and routed handlers.

    384 GitHub stars~1.1k tokensUpdated 3 mo ago
    Auto-check passed

  • JavaScript IO Effects With Sagas

    paralleldrive/aidd

    Teaches the saga pattern with call and put so network requests and side effects stay out of the logic and sagas can be tested without mocks.

    384 GitHub stars~587 tokensUpdated 3 mo ago
    Auto-check passed

  • Lit Element Authoring

    paralleldrive/aidd

    Rules for writing Lit elements in an AIDD project: binding elements on DatabaseElement, observed values, presentation components and action-style callbacks.

    384 GitHub stars~1.2k tokensUpdated 3 mo ago
    Auto-check passed

Categories

Questions about Aidd TDD

What does Aidd TDD do?

Systematic test-driven development with proper test isolation. Aidd TDD is an agent skill from paralleldrive/aidd. Systematic test-driven development with proper test isolation.

When should I use Aidd TDD?

Aidd TDD fits situations like: implementing code changes; TDD process guidance is needed.

How do I install Aidd TDD in Claude Code?

Run `npx skills add paralleldrive/aidd --skill aidd-tdd -a claude-code`. Or copy the skill folder (ai/skills/aidd-tdd in paralleldrive/aidd) into .claude/skills/aidd-tdd in your project. Claude Code loads it when a task matches its description.

How do I install Aidd TDD in Codex?

Run `npx skills add paralleldrive/aidd --skill aidd-tdd -a codex`. Or copy the skill folder (ai/skills/aidd-tdd in paralleldrive/aidd) into .agents/skills/aidd-tdd in your project. Codex loads it when a task matches its description.

Can I use Aidd TDD in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add paralleldrive/aidd --skill aidd-tdd -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/aidd-tdd, .gemini/skills/aidd-tdd, .github/skills/aidd-tdd and .opencode/skills/aidd-tdd in your project.

What does Aidd TDD need to run?

SKILL.md names no scripts, command-line tools or credentials: Aidd TDD is instructions for the agent only.

Does Aidd TDD access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Aidd TDD safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Aidd TDD use?

Aidd TDD is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Aidd TDD use?

About 1.2k tokens (SKILL.md is roughly 4.9k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Aidd TDD?

Skills that share tags, products or a category with Aidd TDD: TDD (pietheinstrengholt/rssmonster, 564 stars), TDD Workflow (hellangleZ/burn-in-cceverywhere-ralph, 112 stars), TDD (sanity-io/sanity, 6.4k stars) and Test Driven Development (farm-fe/farm, 5.6k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Aidd TDD?

paralleldrive (a GitHub organization) maintains it in paralleldrive/aidd, which has 384 GitHub stars. The repository holds 35 skills in this directory. The repository was last updated on June 12, 2026.

Source: paralleldrive/aidd on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.