foreman-tdd
Stack-agnostic test-driven development loop for a single Foreman issue. Implements one vertical slice with strict red-green-refactor (one test at a time, never horizontal slicing) using the foreman-test wrapper, saves completion evidence, then emits a machine-readable FOREMAN-SUMMARY block Foreman parses.
npx skills add VisionForge-OU/foreman --skill foreman-tdd --agent claude-code
Same command for any agent — swap --agent for codex, cursor, copilot.
Weekly change comes from our own snapshots, not the repository page — it measures attention, not adoption.
# foreman-tdd (Adapted from mattpocock/skills `tdd` — see NOTICE. Made stack-agnostic: test, lint and typecheck commands are injected by Foreman from `config.yaml`, not hard-coded to npm/Husky. Removed interactive "confirm with the user / get user approval" steps — those become escalation triggers. Added the FOREMAN-SUMMARY output block.) ## Inputs (injected by Foreman in the prompt) - The full **issue file** (`ISS-NNN.md`) — its Goal, Acceptance criteria, Out of scope, `prd_refs`, and its `acceptance_check` (a runnable check Foreman re-runs independently — your slice is not done until it passes). This is your slice definition. - The **commands** for the project (`test`, `lint`, `typecheck`) — but you run tests through the **`foreman-test`** wrapper (see below), never the raw runner. - The target repo conventions (`CONTEXT.md`, relevant ADRs). - The **evidence directory** (`runs/<id>/evidence/`) you MUST populate before claiming done. - On a retry, the **failing output** from the previous attempt. You run headless in a git worktree on the issue's branch, cwd set to that worktree. Implement the slice and stop. Do not ask for confirmation. ## The foreman-test wrapper (use it exclusiv
- Inputs (injected by Foreman in the prompt)
- The foreman-test wrapper (use it exclusively)
- You may NOT write Foreman-owned state
- Philosophy
- Anti-pattern: horizontal slices
- Workflow
- 1. Plan from the issue
- 2. Tracer bullet
- 3. Incremental loop
- 4. Refactor (only while GREEN)
- 5. Verify, save evidence, and summarise
- Required output: FOREMAN-SUMMARY
What does the foreman-tdd skill do?
Stack-agnostic test-driven development loop for a single Foreman issue. Implements one vertical slice with strict red-green-refactor (one test at a time, never horizontal slicing) using the foreman-test wrapper, saves completion evidence, then emits a machine-readable FOREMAN-SUMMARY block Foreman parses.
How do I install it?
Run `npx skills add VisionForge-OU/foreman --skill foreman-tdd --agent claude-code` — it drops the skill into your project so the agent can pick it up. Swap the --agent value for codex, cursor or copilot if you use one of those.
Where does this skill come from?
From VisionForge-OU/foreman, a repository with 421 stars. We read it straight from the repository tree rather than a submitted listing, so what you see here is what is actually published.
Is a popular skill a good skill?
Not necessarily. Stars measure attention, not adoption — a repository can trend for a week and be abandoned. That is why we show the weekly change from our own snapshots next to the total, instead of a single flattering number.