Behavior first
Practical bilingual skills that make AI coding agents more disciplined, testable, and useful in real engineering work.
npx -y skills add Rookage/agent-discipline --skill behavior-firstAssembled 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
Use when implementing features or fixing bugs with tests. Applies red-green-refactor, behavior-focused tests, public-interface testing, and small vertical slices. Trigger when the user says TDD, tests, implement with tests, make it stable, or fix with regression coverage.
SKILL.md
1.3 KB, as published. Nobody here has run it
Behavior First
中文核心：测行为，不拜实现。
Principles
- Test observable behavior through public interfaces.
- Avoid tests that depend on private implementation details.
- Work in vertical slices: one behavior, one test, one minimal implementation.
- Refactor only after tests are green.
Workflow
- Inspect existing test style and commands.
- Identify the public interface or user-visible behavior.
- Write one failing test for one behavior.
- Implement the smallest code needed to pass.
- Repeat for the next behavior.
- Refactor after green.
- Run relevant verification.
Test Quality
Good tests:
- read like specifications
- survive internal refactors
- fail when behavior breaks
Bad tests:
- mock internal collaborators unnecessarily
- assert private function shape
- pass while user behavior is broken
Output
End with:
- behavior implemented
- tests added or changed
- verification command and result
- known gaps, if any
Gives 2 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 firsthere, and in 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 greenhere, and in 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 reasonin 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
- avoid tests depending on private implementation details
- implement the smallest code needed to pass
- inspect existing test style and commands
- run relevant verification
Grouped from the skills themselves: near-identical wordings counted once, and counted by distinct author, so one author publishing three of these counts once.