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.

shared-references/lifecycle-labels.md

View on GitHub
# Lifecycle Labels

Shared label semantics and gate templates for any skill that reads or writes lifecycle labels on a Trace or Feature issue. Legacy Task issues carry the same labels with the same meanings.

## Label semantics

| Label | Meaning | Set by |
|---|---|---|
| `designed` | Design coverage produced (Design Reference / Handoff written) | `wtf.design-trace`, `wtf.design-feature` |
| `implemented` | Code complete. All claimed Gherkin scenarios pass. | `wtf.implement-trace` |
| `verified` | QA verified against the Scenario Claim — exactly the claimed scenarios | `wtf.verify-trace` |
| `merged` | PR merged into its base branch (closes the issue) | GitHub on PR merge |

## Canonical flow

The recommended end-to-end flow:

```
write-trace → design-trace → implement-trace → verify-trace → create-pr
```

Render this flow string verbatim inside gate prompts. The user is trained to recognize it.

## Read labels

```bash
gh issue view <issue_number> --json labels --jq '.labels[].name'
```

## Gate template — absent label (consumer skills)

Use when a skill that consumes a lifecycle stage finds the expected label **absent**:

> If `<label>` is **absent**, warn the user that the trace has not been `<verb>` yet and that the recommended flow is **write-trace → design-trace → implement-trace → verify-trace → create-pr**. Then apply `./questioning-style.md` and ask the question — header `<header>`:
>
> - **Run `<recommended-skill>`** → invoke that skill, passing the issue number in as context (default)
> - **Skip** → continue without it

| Consumer | Checked label | Recommended skill | Header |
|---|---|---|---|
| `wtf.implement-trace` | `designed` | `wtf.design-trace` | `Design check` |
| `wtf.verify-trace` | `implemented` | `wtf.implement-trace` | `Implement first?` |
| `wtf.create-pr` | `verified` | `wtf.verify-trace` | `Verify first?` |

If the label is present, continue silently. Do not announce.

## Gate template — present label (producer overwrite)

Use when a skill that **writes** a lifecycle output finds the label already present (re-run scenario):

> If `<label>` is **present**, ask "This `<issue type>` already has a `<label>` label. Continuing will overwrite the existing `<output>`. How would you like to proceed?" — header `Already <label>`:
>
> - **<Re-run verb> it** → overwrite the existing `<output>` and continue
> - **Exit** → leave the existing `<output>` as-is and exit immediately

| Producer | Checked label | Output | Re-run verb |
|---|---|---|---|
| `wtf.design-trace` | `designed` | Design Reference | Redesign |
| `wtf.design-feature` | `designed` | Design Handoff | Redesign |

## Mark transition (write side)

After you produce the output, set the lifecycle label:

```bash
gh issue edit <issue_number> --add-label "<label>"
```

This call is **mandatory**. The consuming skill's gate depends on it. In sub-agent contexts the label call is non-skippable per `./subagent-protocol.md` rule 4.

`wtf.verify-trace` also ticks the Trace's entry in the Feature's Trace Plan when it sets `verified`.
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