skills/tdd/SKILL.md
Test-Driven Development enforcement skill - write tests first, always
npx skillsauth add Goblin1024/oh-my-kimi tddInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
[TDD MODE ACTIVATED]
NO PRODUCTION CODE WITHOUT A FAILING TEST FIRST
Write code before test? DELETE IT. Start over. No exceptions.
| If You See | Action | |------------|--------| | Code written before test | STOP. Delete code. Write test first. | | Test passes on first run | Test is wrong. Fix it to fail first. | | Multiple features in one cycle | STOP. One test, one feature. | | Skipping refactor | Go back. Clean up before next feature. |
Before each implementation:
# Run the project's test command - should have ONE new failure
After implementation:
# Run the project's test command - new test should pass, all others still pass
When guiding TDD:
## TDD Cycle: [Feature Name]
### RED Phase
Test: [test code]
Expected failure: [what error you expect]
Actual: [run result showing failure]
### GREEN Phase
Implementation: [minimal code]
Result: [run result showing pass]
### REFACTOR Phase
Changes: [what was cleaned up]
Result: [tests still pass]
The tdd-guide agent SHOULD consult Codex for test strategy validation.
Before first MCP tool use, call ToolSearch("mcp") to discover deferred MCP tools.
Use mcp__x__ask_codex with agent_role: "tdd-guide".
If ToolSearch finds no MCP tools, fall back to the test-engineer agent.
Remember: The discipline IS the value. Shortcuts destroy the benefit.
data-ai
Kimi-native team worker protocol (ACK, mailbox, task lifecycle)
documentation
Persistent markdown project wiki stored under .omk/wiki with keyword search and lifecycle capture
development
URL-driven website cloning with visual + functional verification
testing
Structured visual QA verdict for screenshot-to-reference comparisons