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/contradiction-spec.json
View on GitHub{
"_note": "The Feature declares 'Merchant' as the sole actor and holds the canonical story scenarios. Trace #10's Scenario Claim names 'Admin user' scenarios that do not exist in the Feature's canonical set, and its synced scenario copy uses the 'Admin user' actor. Step 2b (contradiction scan) should surface this actor mismatch between the Feature's canonical scenarios and Trace #10's claim.",
"feature": {
"number": 62,
"title": "Feature: Settlement retry management",
"labels": [{"name": "feature"}],
"body": "## Goal\nMerchants can view failed settlements and trigger manual retries from their dashboard.\n\n## Acceptance Criteria\n- [ ] Merchants can see failed settlements with reason codes in their settlement list\n- [ ] Merchants can request a retry for a permanently-failed settlement\n- [ ] A retried settlement is re-queued and its status changes to 'pending'\n\n## User Stories\n### Story: Merchant retries a failed settlement\nAs a Merchant, I want to retry a permanently-failed settlement, so that I receive my funds.\n\n```gherkin\nScenario: Merchant triggers a settlement retry\n Given a Merchant views a permanently-failed settlement\n When the Merchant submits a retry request for settlement #S-123\n Then the SettlementRetryRequested event is emitted\n And the settlement status changes to 'pending'\n\nScenario: Merchant cannot retry a settlement in 'pending' status\n Given a Merchant views a settlement in 'pending' status\n When the Merchant attempts to submit a retry\n Then the retry action is rejected\n```\n\n## Domain Events\n- `SettlementRetryRequested` — emitted when a Merchant requests a retry\n\n## Bounded Context\nSettlement domain. Merchant actor. No operator or admin access paths in this feature.\n\n## Trace Plan\n1. [ ] ☄️ #10 Skeleton — settlement retry endpoint (claims: \"Admin user triggers a settlement retry\", \"Admin user cannot retry a settlement in 'pending' status\")"
},
"traces": [
{
"number": 10,
"title": "Trace: Skeleton — settlement retry endpoint",
"labels": [{"name": "trace"}],
"body": "## Story\nAs a Merchant, I want to retry a permanently-failed settlement, so that I receive my funds.\n\n## Scenario Claim\n- Admin user triggers a settlement retry\n- Admin user cannot retry a settlement in 'pending' status\n\n## Spine Position\nSkeleton — first pass, builds on nothing.\n\n<details>\n<summary>Synced from Feature #62 — edit there, not here</summary>\n\n```gherkin\nScenario: Admin user triggers a settlement retry\n Given an Admin user has access to the settlement management panel\n When the Admin user submits a retry request for settlement #S-123\n Then the SettlementRetryRequested event is emitted\n And the settlement status changes to 'pending'\n\nScenario: Admin user cannot retry a settlement in 'pending' status\n Given an Admin user views a settlement in 'pending' status\n When the Admin user attempts to submit a retry\n Then the retry action is rejected\n```\n\n</details>"
}
]
}
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 |