Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →visionforge-ou/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.
Passed 11 of 18 test cases with the skill, and 7 of 18 without it.
and 7 more in the full report
7 fixed7 passed either way6 still failing2 broke
Tokens, turns and time describe resource use, not a dollar price.
One of 7 test cases the skill fixed. Same model, same prompt, with and without the skill.
In a Node.js repository with `npm test` configured in package.json, which command should be executed to run the test suite during TDD iteration?
| Checked | Without skill | With skill |
|---|---|---|
| Selects foreman-test as the command runner for executing tests. | Missed | Passed |
The instructions your model reads when the skill loads.
(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.)
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.test, lint, typecheck) — but you run
tests through the foreman-test wrapper (see below), never the raw runner.CONTEXT.md, relevant ADRs).runs/<id>/evidence/) you MUST populate before
claiming done.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.
Run tests with foreman-test (on your PATH) instead of the raw test runner:
foreman-test — full suite, quiet output (counts + failures only), full log
on disk with greppable ERROR lines.foreman-test --fast — a deterministic per-worker random subsample for cheap
inner-loop runs. Use this while iterating; run the full foreman-test
before you finish. Foreman re-runs the full suite itself regardless.Wall-clock discipline: the wrapper prints elapsed time. Spend at most ~1 turn in 3 re-running tests; the rest goes to making changes. Don't loop on the runner.
verification.json, any issue file, and the canonical *.check/ artifacts are
Foreman's. A worktree hook will block (and surface) any attempt to write them —
test cases passed, vs 7 / 18 without
More skills from the same source and nearby in the registry, with their headline benchmark lift.