tdd
Use when the user requests test-driven development, red-green-refactor, integration tests, or a test-first bug fix.
Skill by minfengyuan
Chalk Labs
Need help deploying tdd?
Chalk Labs sets up agents like this inside real teams: connected to your tools, tested on your data, with a human in the loop where it matters.
Install
Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.
npx agentmarket install skill/minfengyuan-tdd
Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.
Get the weekly diff
The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.
About
Use cases: testing
Reviews
Write a reviewNo reviews yet. Installed it? Reviews come from verified installers only. How reviews work
Permissions
What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.
- Tools
- No tools found
- Secrets
- None asked for
- Install scripts
- None found
Network hosts it talks to 1
codeload.github.com· found in install command
Files it touches
~/.claude/skills/tdd
What's inside
- Skill name
tdd- Description
- Use when the user requests test-driven development, red-green-refactor, integration tests, or a test-first bug fix.
- License
- MIT
- Instructions
- 28 lines in SKILL.md · view on GitHub
Files (6)
- SKILL.md
- deep-modules.md
- interface-design.md
- mocking.md
- refactoring.md
- tests.md
SKILL.md (first lines)
# Test-Driven Development Use a test-first loop when it is part of the user's requested method or is the clearest way to specify a behavior. Tests should exercise public behavior and avoid coupling to implementation details. ## Loop 1. Identify the next observable behavior and write the smallest meaningful failing test. 2. Implement only enough to make that test pass. 3. Refactor after the behavior is green, keeping the test suite green. 4. Repeat for the important behaviors, prioritizing critical paths and meaningful failure modes rather than trying to test every edge case. Prefer vertical slices over writing a complete test suite before understanding the implementation. Use unit, integration, or end-to-end tests according to the boundary being specified. ## Planning and completion Use the project's vocabulary and conventions, inspect existing interfaces and tests, and preserve public behavior unless the request changes it. Confirm a product decision only when the interface or behavior is genuinely ambiguous; do not require a separate approval round for a clear task. Before claiming completion, run the relevant tests and report what behavior they cover. If the user did not request TDD and a low-risk change is adequately verified by a focused check, do not impose a full red-green workflow. ## Further resources - [Good and bad tests](tests.md) - [Interface design for testability](interface-design.md) - [When to mock](mocking.md) - [Refactor candidates](refactoring.md) - [Deep modules](deep-modules.md)
From minfengyuan/harness-knowledge-base, MIT.
More from minfengyuan/harness-knowledge-base
- 0.589score
tailscale-api
Hermes Agent
Tailscale REST API v2 (api.tailscale.com/api/v2) — devices, keys, ACL, DNS, webhooks, OAuth scopes.
SkillAFreshness: A★ 1Claude Code +9 - 0.587score
dev-mode
minfengyuan
Coordinate the project's seven specialized agents through planning, execution, review, debugging, and final acceptance for substantial software-development…
SkillAFreshness: A★ 1Claude Code +9 - 0.587score
conventional-branch-naming
minfengyuan
Generate one descriptive Git branch name from a task using Conventional Commits 1.0.0 types.
SkillAFreshness: A★ 1Claude Code +9 - 0.587score
clarifying-requirements
minfengyuan
Turn vague ideas or requirements into a shared, actionable brief through iterative questions and confirmation.
SkillAFreshness: A★ 1Claude Code +9 - 0.581score
tailscale-cli
minfengyuan
Complete tailscale CLI usage — all subcommands, flags, and common workflows (v1.96+)
SkillAFreshness: A★ 1Claude Code +9 - 0.552score
photo-illustration-styles
minfengyuan
Photo-to-illustration style transfer.
SkillBFreshness: B★ 1Claude Code +9 - 0.552score
optimize-astra-instructions
minfengyuan
Audit or revise Skills, AGENTS.md files, and agent task prompts specifically for GPT-6 Astra.
SkillBFreshness: B★ 1Claude Code +9 - 0.552score
progressive-disclosure-agents-md
minfengyuan
Design, review, or create progressive-disclosure and layered AGENTS.md instruction systems for agentic coding workflows.
SkillBFreshness: B★ 1Claude Code +9 - 0.549score
pi-coding-agent
minfengyuan
Guides agents using Pi coding-agent: install, authenticate, run, configure, automate, and extend the pi CLI.
SkillBFreshness: B★ 1Claude Code +9 - 0.548score
recipe-formatter
minfengyuan
将用户提供的菜谱文字或明确要求保存的菜谱整理为结构化 Obsidian 菜谱,自动分类并打标签。Use when the user wants recipe text formatted, normalized, tagged, or saved as a recipe note.
SkillBFreshness: B★ 1Claude Code +9 - 0.547score
plan-ceo-review
minfengyuan
Use when a user wants product-level review of a plan, especially to challenge scope, ambition, and user value before implementation
SkillBFreshness: B★ 1Claude Code +9 - 0.547score
conventional-commits
minfengyuan
Generate Conventional Commits 1.0.0 messages from staged git changes.
SkillBFreshness: B★ 1Claude Code +9
Signals
- Stars
- 1
- Forks
- 0
- Open issues
- 0
- Last commit (this folder)
- Sep 16, 2026 (1 month ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- MIT
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from minfengyuan
- 0.587score
dev-mode
minfengyuan
Coordinate the project's seven specialized agents through planning, execution, review, debugging, and final acceptance for substantial software-development…
SkillAFreshness: A★ 1Claude Code +9 - 0.587score
clarifying-requirements
minfengyuan
Turn vague ideas or requirements into a shared, actionable brief through iterative questions and confirmation.
SkillAFreshness: A★ 1Claude Code +9 - 0.587score
conventional-branch-naming
minfengyuan
Generate one descriptive Git branch name from a task using Conventional Commits 1.0.0 types.
SkillAFreshness: A★ 1Claude Code +9 - 0.581score
tailscale-cli
minfengyuan
Complete tailscale CLI usage — all subcommands, flags, and common workflows (v1.96+)
SkillAFreshness: A★ 1Claude Code +9 - 0.552score
photo-illustration-styles
minfengyuan
Photo-to-illustration style transfer.
SkillBFreshness: B★ 1Claude Code +9 - 0.552score
progressive-disclosure-agents-md
minfengyuan
Design, review, or create progressive-disclosure and layered AGENTS.md instruction systems for agentic coding workflows.
SkillBFreshness: B★ 1Claude Code +9
Done for you
Rather not set it up yourself?
Chalk Labs scopes, builds and runs agents for your team: the task audit, the eval harness, the integrations and the weekly ops report. Fixed scope, priced before we start.
See how we build AI agents →Read the case studies
Chalk Labs is a two-founder AI and growth studio. We build AI agents, CRMs and MVPs for Web3 and AI companies, and have shipped 50+ product and token launches.
- launches shipped
- 50+
- launches shipped
- media placements
- 500+
- media placements
- founders on every account
- 2
- founders on every account
Press we've placed: Forbes · CoinDesk · Decrypt · Cointelegraph · The Block
Rahil Jain, Co-founder, Chalk Labs. Ex-Goldman Sachs engineer. You talk to the person who builds it.
Get tdd running in your business
Tell us what you want to automate. A founder replies within one working day with a plan, not a pitch deck.
Cite this page
tdd skill. Agent Mart. https://agentmart.dev/skills/minfengyuan-tdd (last updated 2026-10-24)