agentsclimarketplace

Bug first tdd

Skill Johnny-Martinez/fleet-of-one-free/skills/bug-first-tdd

Free starter kit for running AI coding agents with proof gates, status badges, and lane discipline. MIT.

Install
npx -y skills add Johnny-Martinez/fleet-of-one-free --skill bug-first-tdd

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

One thing to look at

  • 0 stars0 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.

What its author says it does

Copied from the file, not written here

Reproduce a bug before fixing it, encode the expected behavior in a failing test, then make the smallest safe change.

SKILL.md

1.1 KB, as published. Nobody here has run it

Bug-First TDD

Use this skill for any bug, regression, broken workflow, failing test, or "fix this" request.

Loop

  1. Reproduce the bug with the smallest exact input or workflow.
  2. Write a failing test for the correct behavior.
  3. Run the test and confirm it fails for the expected reason.
  4. Make the smallest code change that turns the test green.
  5. Run the targeted test and the nearest surrounding suite.
  6. Verify the affected workflow outside the test if users touch it.
  7. Report what is fixed and what remains unverified.

Guardrails

  • Do not weaken a test to pass broken code.
  • Do not fix a guessed cause before reproducing the symptom.
  • Do not mix unrelated refactors into a bug fix.
  • Do not call it done until the proof matches the original failure.

Minimal Report

🟢 **DONE**

Reproduced: `<command/input>` failed with `<error>`.
Test: `<test file>` now covers expected behavior.
Fix: `<short change>`.
Verified: `<targeted test>` and `<workflow proof>`.

Gives 1 of the 12 instructions most tdd skills give

Counted across 439 of the 443 authors here whose files we hold, read 2026-08-06

  • write minimal code to pass the testin 302 of 439, across 218 files
  • write a failing test firstin 176 of 439, across 112 files
  • refactor code only after tests passin 171 of 439, across 101 files
  • watch the test fail before writing codein 142 of 439, across 93 files
  • test one behavior per testin 106 of 439, across 44 files
  • refactor code while keeping tests greenin 99 of 439, across 86 files
  • delete code written before testsin 98 of 439, across 54 files
  • run tests after each refactor stepin 85 of 439, across 54 files
  • Use real code instead of mocks unless unavoidablein 64 of 439, across 21 files
  • confirm the test fails for the right reasonhere, and in 64 of 439, across 60 files
  • reproduce bugs with a test before fixingin 53 of 439, across 36 files
  • write tests before implementationin 48 of 439, across 39 files

Said here and by no other author read

  • reproduce the bug with the smallest exact input
  • verify the affected workflow outside tests
  • report what is fixed and what remains unverified

Grouped from the skills themselves: near-identical wordings counted once, and counted by distinct author, so one author publishing three of these counts once.

Keep looking

Skills are one crate of 328,083. Ordering is by how many stacks a row turns up in, so the top of any crate is what has actually been picked rather than what has the most stars.