Skip to content

xiduzo/wtf / skills/wtf.setup

wtf.setup

Verified

This skill should be used when a user wants to set up WTF in a repository or check that the environment is ready for it — for example "set up wtf", "is wtf ready", "install wtf templates", or "a new dev joined, set them up". Verifies the GitHub CLI and its auth, installs the required gh extensions and the issue and PR templates, configures issue classification, planning, feature scope, and delivery mode, and registers the hooks. Run once per repo when onboarding, or when a contributor joins the project.

references/TRACE.md

View on GitHub
---
name: Trace
about: One pass over the Feature's Spine — implements one story's Scenario Claim end-to-end
title: "☄️ Trace: "
labels: trace
assignees: ""
---

# ☄️ Trace: {{title}}

---

## Story

<!-- 👤 Copied verbatim from the parent Feature. Do not re-derive it. Do not reword it. -->

- As a **_, I want _** so that \_\_\_

---

## Scenario Claim

<!-- The names of the scenarios this Trace implements. The claims of one story's Traces cover all its scenarios, with no overlap. The Feature body is canonical — edit scenarios there. -->

- Scenario:

<details>
<summary>Claimed scenarios — synced from Feature #N — edit there, not here</summary>

```gherkin
Scenario:
  Given
  When
  Then
```

</details>

---

## Spine Position

<!-- Skeleton | Extension | Deepening. The Skeleton is Trace 1 and proves the Spine. An Extension adds a further story to the Spine. A Deepening claims further scenarios of a story already started. Name the Traces this one builds on. -->

- Position:
- Builds on: Trace #

---

## Impacted Areas

<!-- 👤 Developer — The files, modules, and components this Trace touches. The conflict graph schedules sibling Traces by this list. A Trace with no entries is serialized against every other Trace of its Feature. Refined by implement-trace once the Technical Approach names real paths. -->

- Backend:
- Frontend:
- Database:
- APIs:
- External systems:

---

## Contracts & Interfaces

<!-- 👤 Tech Lead — These are the spec. Implementation must match these exactly. -->

### Request

```json
{}
```

### Response

```json
{}
```

### Events / Side Effects

<!-- Describe any events emitted, webhooks triggered, or state changes. Write "None" when the Trace emits nothing. -->

- None

---

## Technical Approach

<!-- 👤 Developer — Filled by implement-trace at implementation time -->

- Architecture decisions:
- Data flow:
- Trade-offs:

### Aggregates & Invariants

<!-- Which Aggregates does this Trace modify? What business rules must hold after the change? -->

- Aggregates:
- Invariants:

---

## Observability

<!-- How do we verify this works in production? -->

- Logs:
- Metrics:
- Alerts:

---

## Design Reference

<!-- Optional. Filled by design-trace: Figma frames / component specs for the claimed scenarios. -->

## Definition of Done

- [ ] All claimed scenarios covered by tests
- [ ] Contracts match implementation
- [ ] Observability in place
- [ ] System releasable after merge
- [ ] Code reviewed
- [ ] Design reviewed (if UI)
- [ ] Documentation updated

---

## Test Mapping

| Claimed scenario | Test file | Status |
| ---------------- | --------- | ------ |
|                  |           |        |
reverse-engineer-anythingmorluto/reaReverse engineer native, managed, Electron/JavaScript, packaged, firmware, and browser targets with REA, and build agent environments (AgentEnv bundles) of web applications from a live instance or a capture, and of Linux desktop apps with a task from a request. Use shipped-artifact or requested runtime evidence to explain features, compare versions, decompile code, or guide a reconstruction. Skip REA for ordinary source-repository architecture analysis.Stars: 471kUpdated Claude CodeCodexVerifiedInstall
diagnosing-superpowersobra/superpowersUse when a superpowers session went wrong and your human partner wants to know why — repeated work, ignored plans, stumbles, poor results, a skill that didn't fire, "it took too long", "why is it so expensive", "what is it doing" — or wants to build a bug report for the superpowers maintainers, for the current session or a past one identified by id or path, on any harness.Stars: 322kUpdated Claude CodeCodexVerifiedInstall
dispatching-parallel-agentsobra/superpowersUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependenciesStars: 322kUpdated Claude CodeCodexVerifiedInstall
executing-plansobra/superpowersUse when executing an implementation plan in the current session as the implementer yourself — your human partner chose inline execution, or no subagent tool is availableStars: 322kUpdated Claude CodeCodexVerifiedInstall