TDD with integration tests
Drives test-first work through public interfaces: agrees the seams to test with the user, runs one red-green cycle per test, mocks only at system boundaries and leaves refactoring to review. Use when building a feature or fixing a bug test-first.
tdd- Author
- Matt Pocock
- Source
- mattpocock/skills/skills/engineering/tdd @ abeeaf9
- License
- MIT · Copyright (c) 2026 Matt Pocock
About this skill
What it does
A reference for the red-green loop that aims at tests worth keeping. Before any test, the agent names the seams, the public boundaries where behaviour can be observed without reaching inside, notes what each catches and misses, and has you confirm them. Each cycle is one seam, one failing test and the least code that passes. Refactoring is moved out of the loop to review.
Three anti-patterns are named: tests coupled to the implementation (mocked internals, private methods, checking the database instead of the interface), tautological tests whose expected value is computed the way the code computes it, and horizontal slicing, all tests first and all code after. It reads GLOSSARY.md, if present, for the domain's words, and respects ADRs.
Two helper files ship with it. tests.md sets good tests against bad ones in TypeScript: checkout through the public API, a user checked through getUser instead of SQL, a total compared with a literal rather than a recomputed sum. mocking.md limits mocks to system boundaries such as external APIs, time and randomness, and shows dependency injection and SDK-style clients with one function per external call.
When to use it, and when not
Use it for a feature or bug fix done test-first, with integration-style tests through real interfaces instead of a suite of mocks.
Skip it for throwaway code, which the author's Throwaway prototype leaves untested on purpose, and for covering existing code, where Unit test writer fits better.
How to run it
The install command below puts the whole folder in place. The agent picks it up by its description for test-first work; to call it yourself:
- Claude Code:
/tdd, or ask for the skill by name. - Codex:
$tdd. - Cursor: type
/in the Agent chat and picktdd.
Example: /tdd Add discount codes to checkout. Propose the seams first.
For interface questions it calls Deep module design, and it leaves refactoring to Code review against standards and spec; install both. Implement a spec runs it in each implementer subagent.
How it differs from similar skills
The other three TDD skills keep refactoring inside the cycle. Our Test-driven development adds a baseline run and a red/green report, the Superpowers version deletes code written before its test, and Addy Osmani's aims for mostly unit tests. Only this one agrees seams with you first and tests only there. Those three install into test-driven-development; this one goes into tdd and clashes with none of them.
Install
Run one command — it saves SKILL.md and the files it uses into your agent's skills folder. Claude Code and Codex pick up a new skill without a restart; if it does not show up, restart the agent.
curl -fsSL --create-dirs -o ~/.claude/skills/tdd/SKILL.md https://anymodel.org/en/skills/matt-pocock/tdd/SKILL.md -o ~/.claude/skills/tdd/LICENSE https://anymodel.org/en/skills/matt-pocock/tdd/LICENSE -o ~/.claude/skills/tdd/agents/openai.yaml https://anymodel.org/en/skills/matt-pocock/tdd/agents/openai.yaml -o ~/.claude/skills/tdd/mocking.md https://anymodel.org/en/skills/matt-pocock/tdd/mocking.md -o ~/.claude/skills/tdd/tests.md https://anymodel.org/en/skills/matt-pocock/tdd/tests.md
curl -fsSL --create-dirs -o ~/.agents/skills/tdd/SKILL.md https://anymodel.org/en/skills/matt-pocock/tdd/SKILL.md -o ~/.agents/skills/tdd/LICENSE https://anymodel.org/en/skills/matt-pocock/tdd/LICENSE -o ~/.agents/skills/tdd/agents/openai.yaml https://anymodel.org/en/skills/matt-pocock/tdd/agents/openai.yaml -o ~/.agents/skills/tdd/mocking.md https://anymodel.org/en/skills/matt-pocock/tdd/mocking.md -o ~/.agents/skills/tdd/tests.md https://anymodel.org/en/skills/matt-pocock/tdd/tests.md
foreach ($f in 'SKILL.md','LICENSE','agents/openai.yaml','mocking.md','tests.md') { $p = Join-Path "$HOME\.claude\skills\tdd" $f; New-Item -ItemType Directory -Force (Split-Path $p) | Out-Null; Invoke-WebRequest "https://anymodel.org/en/skills/matt-pocock/tdd/$f" -UseBasicParsing -OutFile $p }foreach ($f in 'SKILL.md','LICENSE','agents/openai.yaml','mocking.md','tests.md') { $p = Join-Path "$HOME\.agents\skills\tdd" $f; New-Item -ItemType Directory -Force (Split-Path $p) | Out-Null; Invoke-WebRequest "https://anymodel.org/en/skills/matt-pocock/tdd/$f" -UseBasicParsing -OutFile $p }Any other agent: save the file into its skills folder, or give it the link to the file: https://anymodel.org/en/skills/matt-pocock/tdd/SKILL.md
SKILL.md
Test-Driven Development
TDD is the red → green loop. This skill is the reference that makes that loop produce tests worth keeping: what a good test is, where tests go, the anti-patterns, and the rules of the loop. Every section applies on every cycle: consult them before and during the loop, not after.
When exploring the codebase, read GLOSSARY.md (if it exists) so test names and interface vocabulary match the project's domain language, and respect ADRs in the area you're touching.
What a good test is
Tests verify behavior through public interfaces, not implementation details. Code can change entirely; tests shouldn't. A good test reads like a specification: "user can checkout with valid cart" tells you exactly what capability exists, and it survives refactors because it doesn't care about internal structure.
See tests.md for examples and mocking.md for mocking guidelines.
Seams: where tests go
A seam is the public boundary you test at: the interface where you observe behavior without reaching inside. Tests live at seams, never against internals.
Test only at pre-agreed seams. Before writing any test, write down the seams under test and confirm them with the user. No test is written at an unconfirmed seam. You can't test everything, so agreeing the seams up front is how testing effort lands on the critical paths and complex logic instead of every edge case.
Ask: "What's the public interface, and which seams should we test?" Give each proposed seam a one-line note on what it catches and what it misses.
When the shape of that interface is itself in question (how deep the module is, where the seam belongs, what the interface should expose), call the Skill tool with "codebase-design" for the vocabulary. It is the shared source of the module, interface, depth, seam, adapter, leverage and locality terms, and it is a reference to consult, not a session to run.
Anti-patterns
- Implementation-coupled: mocks internal collaborators, tests private methods, or verifies through a side channel (querying the database instead of using the interface). The tell: the test breaks when you refactor but behavior hasn't changed.
- Tautological: the assertion recomputes the expected value the way the code does (
expect(add(a, b)).toBe(a + b), a snapshot derived by hand the same way, a constant asserted equal to itself), so it passes by construction and can never disagree with the code. Expected values must come from an independent source of truth: a known-good literal, a worked example, the spec. - Horizontal slicing: writing all tests first, then all implementation. Bulk tests verify imagined behavior: you test the shape of things rather than user-facing behavior, the tests go insensitive to real changes, and you commit to test structure before understanding the implementation. Work in vertical slices instead: one test → one implementation → repeat, each test a tracer bullet that responds to what the last cycle taught you.
Rules of the loop
- Red before green. Write the failing test first, then only enough code to pass it. Don't anticipate future tests or add speculative features.
- One slice at a time. One seam, one test, one minimal implementation per cycle.
- Refactoring is not part of the loop. It belongs to the review stage (see the
code-reviewskill), not the red → green implementation cycle.
Connect through AnyModel API
This skill runs on whatever model your agent uses. Point Claude Code, Codex or Cursor at AnyModel to run it on Claude, GPT, Gemini and more with one key — pay per token, no subscription.
AnyModel