xiduzo/wtf / skills/wtf.loop
wtf.loop
VerifiedThis skill should be used when a developer wants to autonomously execute all Traces under a fully-specified Epic or Feature — for example "go", "start building", "implement everything", "run the loop", "execute the feature", "build it all", "kick it off". Requires that the Epic/Feature/Trace tree is fully written before starting. Chains implement → verify → PR → re-aim for every Trace — spine-first within each Feature, parallel across Features — with targeted human-in-the-loop gates for contradictions, ambiguities, and every change to a Trace Plan's scenario set.
| File | Kind | Size |
|---|---|---|
| SKILL.md | skill md | 16.5 KB |
| evals/evals.json | config | 10.8 KB |
| evals/fixtures/contradiction-spec.json | config | 3.0 KB |
| evals/fixtures/diamond-file-conflict.json | config | 2.3 KB |
| evals/fixtures/external-blocker.json | config | 863 B |
| evals/fixtures/linear-chain.json | config | 3.4 KB |
| evals/fixtures/parallel-features.json | config | 1.6 KB |
| evals/fixtures/sibling-traces-parallel.json | config | 5.2 KB |
| evals/fixtures/trunk-delivery-close.json | config | 2.9 KB |
| references/pre-flight-validation.md | markdown | 6.9 KB |
| references/trace-execution.md | markdown | 14.2 KB |
evals/fixtures/trunk-delivery-close.json
View on GitHub{
"_note": "Trunk delivery: `.wtf/config.json` says delivery=trunk and the Feature declares no override. One Feature with two Traces: Skeleton #30 then Deepening #31, sharing files. Expected: no feature branch anywhere; #30's PR targets main; #31 stacks on trace/30-… (PR base trace/30-…, retargeted to main when #30 merges); #31 is the final plan entry, so its PR body carries `Closes #7`; step 5 opens no feature PR.",
"config": {
"_note": "contents of .wtf/config.json",
"classification": "labels",
"planning": "guided",
"feature_scope": "single-story",
"delivery": "trunk"
},
"remote_branches": [
"main"
],
"feature": {
"number": 7,
"title": "🚀 Feature: Settlement notifications",
"labels": [
"feature",
"designed"
],
"body": "## Bounded Context\nPayments\n\n## User Stories\n\n### Story 1: Merchant is notified when a settlement completes\n- As a Merchant, I want an email when a settlement completes so that I do not have to poll the dashboard.\n\n```gherkin\nScenario: Email sent for a completed settlement\n Given a Merchant has a pending settlement\n When the settlement completes\n Then the Merchant receives a settlement email\n\nScenario: No email for a settlement that fails\n Given a Merchant has a pending settlement\n When the settlement fails\n Then no settlement email is sent and the failure is logged\n```\n\n## Trace Plan\n1. [ ] ☄️ Skeleton — Merchant is notified when a settlement completes: email for one completed settlement (claims: \"Email sent for a completed settlement\") #30\n2. [ ] ☄️ Deepening — Merchant is notified when a settlement completes: failure path (claims: \"No email for a settlement that fails\") #31\n\n## Delivery Override\n- Mode:\n- Reason:\n\n## Impacted Areas\n- src/notifications/"
},
"nodes": [
{
"number": 30,
"title": "☄️ Trace: Skeleton — settlement email happy path",
"type": "trace",
"state": "OPEN",
"labels": [
"trace",
"designed"
],
"feature": 7,
"body": "## Spine Position\n- Position: Skeleton\n- Builds on: none\n\n## Impacted Areas\n- Backend: src/notifications/SettlementMailer.ts\n- Frontend: —\n- Database: —\n- APIs: —\n- External systems: SMTP relay"
},
{
"number": 31,
"title": "☄️ Trace: Deepening — no email on failed settlement",
"type": "trace",
"state": "OPEN",
"labels": [
"trace",
"designed"
],
"feature": 7,
"body": "## Spine Position\n- Position: Deepening\n- Builds on: Trace #30\n\n## Impacted Areas\n- Backend: src/notifications/SettlementMailer.ts\n- Frontend: —\n- Database: —\n- APIs: —\n- External systems: SMTP relay"
}
],
"edges": {
"30": {
"blocks": [
31
],
"blocked_by": []
},
"31": {
"blocks": [],
"blocked_by": [
30
]
}
},
"pull_requests": []
}
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| 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: 472k | Updated | Claude CodeCodex | Verified | Install |
| 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: 322k | Updated | Claude CodeCodex | Verified | Install |
| dispatching-parallel-agentsobra/superpowersUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| 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 available | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |