Test-Driven Development (superpowers)
Write the failing test first, watch it fail for the right reason, then make it pass. The red run is part of the proof.
proof: red-to-green blocks: test never failedblocks: tests written after the fact to match code
Source
https://github.com/obra/superpowers/blob/main/skills/test-driven-development/SKILL.mdChecked 2026-10-16. Read the original before installing.
By harness
| Harness | Status | How |
|---|---|---|
| Cursor | adapted | Copy SKILL.md body into .cursor/rules/<name>.mdc with alwaysApply: false and a description so the agent pulls it in. Untested as a rule. |
| Claude Code | native | Native skill. |
| Grok Build | native | Grok Build reads Claude Code skills from .claude/skills/ alongside .grok/skills/ (per docs.x.ai skills page). |
| Codex | untested | Paste the core checklist into AGENTS.md. Codex has no SKILL.md loader in the cited docs; untested. |
| AGENTS.md generic | untested | Paste the checklist section into AGENTS.md. Untested. |
By model family
| Claude | source |
| GPT | untested |
| Grok | untested |
| Gemini | untested |
Sponsor slot: your verification tool here, one sponsor per week. Details
Proof of the week
One verification pattern every week, adapted per harness and model. No spam.