Skip to content

mikeparcewski/wicked-garden / skills/build-guide

wicked-garden-build-guide

Verified

Discover how a repo builds and tests, and write its build/test guide (`.wicked/build-guide.json`, contract v1): the data the wicked-core floor interprets instead of hardcoding runners. Reads CI config first, then the manifests, then each runner's own --version and --help. Prefers structured results (JUnit; JSON lines and TAP are reserved in v1) and writes a text parser, learned from this repo's real output, only when none exists. Writes a deliberately failing mutation probe, validates with `wicked-core floor probe` (only the probe writes `verified`), and proposes the file as a PR or governed change, never silently. Use when: "build guide", "write the build/test guide", "how does this repo test", "onboard this repo's tests for the floor", "re-onboard the build guide", "the build guide is stale", the onboarding step of the wicked-garden-core setup action, or a wicked-crew onboarding run dispatched because the floor found no guide, a stale one, or a failed probe.

FileKindSize
SKILL.mdskill md13.7 KB
assets/seeds/cargo-libtest.jsonconfig2.6 KB
assets/seeds/pytest-short-summary.jsonconfig2.5 KB
assets/seeds/vitest-junit.jsonconfig2.0 KB
refs/contract-notes.mdmarkdown12.1 KB
refs/discover.mdmarkdown4.9 KB
refs/propose.mdmarkdown1.9 KB
refs/results.mdmarkdown7.0 KB

refs/propose.md

View on GitHub
# Propose the guide

The guide reaches the base only through review: the run's deliver gate inside wicked-crew, or a
PR otherwise. It is never a silent write and never a push to the default branch.

## Outside a wicked-crew run

1. Branch: `git switch -c wicked/build-guide` (or `wicked/build-guide-refresh`).
2. Stage only `.wicked/build-guide.json`. Commit message: `chore(floor): add build/test guide`
   (or `refresh`).
3. Show the user the guide and the probe table, and ask before opening the PR. Use your
   harness's question prompt where it has one; otherwise ask in plain text and wait.
4. Open the PR. Make it a draft when any probe failed or the probe was unavailable. Use the body
   below.

## Inside a wicked-crew run

Write `.wicked/build-guide.json` in the run's worktree and finish your unit. The deliver gate
shows the diff, and the operator approves it there. Ask nothing; a headless run has nobody to
answer. Put the same body in your unit output.

## PR body

```
## Build/test guide (.wicked/build-guide.json)

Derived from: <derivedFrom, one per line>
Runner: <verified.runnerVersion, which the probe recorded from the `version` piece>
Schema: <the `schema` field check.py printed>

### Probe results (`wicked-core floor probe`)
<probe.py's markdown table>
— or, when the probe was unavailable —
probe unavailable: the guide is unverified, so the floor will not use it for exclusion.
Rehearsal (unverified, not evidence): <per-check rehearse.py results>

### Notes
- Result kind: <junit|text …>, and why (for text: the runner has no structured output, or its
  structured ids do not round-trip)
- Known limits: <for example, multi failed: vitest rejects a repeated name pattern, so two base failures are not excluded>
- Attempts: <n of 3> per check
```

## No guide

Open nothing. Report *"no build/test guide: the floor will run this repo's checks exit-code
only"*, and give the reason.
finishing-a-development-branchobra/superpowersUse when implementation is complete, all tests pass, and you need to decide how to integrate the workStars: 322kUpdated Claude CodeCodexVerifiedInstall
systematic-debuggingobra/superpowersUse when encountering any bug, test failure, or unexpected behavior, before proposing fixesStars: 322kUpdated Claude CodeCodexVerifiedInstall
test-driven-developmentobra/superpowersUse when implementing any feature or bugfix, before writing implementation codeStars: 322kUpdated Claude CodeCodexVerifiedInstall
skill-creatoranthropics/skillsCreate new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, edit, or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy.Stars: 198kUpdated Claude CodeCodexVerifiedInstall