xiduzo/wtf / skills/wtf.write-trace
wtf.write-trace
VerifiedThis skill should be used when a user wants to create a single Trace issue under a Feature β for example "create a trace", "write a trace for this feature", "add a trace to feature
| File | Kind | Size |
|---|---|---|
| SKILL.md | skill md | 13.3 KB |
| evals/evals.json | config | 4.8 KB |
| evals/fixtures/ambiguous-claim.json | config | 2.7 KB |
| evals/fixtures/claim-selection.json | config | 2.9 KB |
| evals/fixtures/depth-split-draft.json | config | 3.4 KB |
evals/fixtures/ambiguous-claim.json
View on GitHub{
"_note": "Vague request 'add a trace for settlement error handling' against a Feature whose story has four unclaimed scenarios and a Trace Plan that only covers the created Skeleton (#61). Step 2 must show the claim state and ask which scenario subset to claim β not invent a claim, not overlap the Skeleton's claim, not draft.",
"trace_request": "Add a trace for settlement error handling",
"feature": {
"number": 60,
"title": "π Feature: Settlement error handling",
"labels": [{ "name": "feature" }],
"body": "## Bounded Context\nSettlement domain. Merchant and Operator actors. Payment processor integration boundary.\n\n## User Stories\n\n### Story 1: Surface and recover failed settlements\n\n- As a **Merchant**, I want **failed settlements to be retried and surfaced** so that **I do not lose revenue silently**\n\n#### Acceptance Criteria\n\n- [ ] Failed settlements are retried up to 3 times before being marked as permanently failed\n- [ ] Merchants receive a notification when a settlement fails permanently\n- [ ] Operators can view and manually retry failed settlements\n\n#### Scenarios\n\n```gherkin\nScenario: Failed settlement is retried\n Given a settlement attempt has failed\n When the retry runs\n Then the settlement is attempted again and the Merchant balance stays consistent\n\nScenario: Settlement is marked permanently failed after three retries\n Given a settlement has failed three retry attempts\n When the last retry fails\n Then the settlement is marked as permanently failed\n\nScenario: Merchant is notified of a permanent settlement failure\n Given a settlement is marked as permanently failed\n When the SettlementPermanentlyFailed event is received\n Then the Merchant receives a failure notification\n\nScenario: Operator manually retries a failed settlement\n Given an Operator views a permanently failed settlement\n When the Operator requests a retry\n Then a SettlementRetryRequested event is emitted and the settlement is retried\n\nScenario: Duplicate operator retry is idempotent\n Given an Operator has already requested a retry for a settlement\n When the Operator requests a retry again\n Then no second SettlementRetryRequested event is emitted\n```\n\n## Domain Events\n\n- Emits: `SettlementFailed`, `SettlementPermanentlyFailed`, `SettlementRetryRequested`\n- Consumes: none\n\n## Trace Plan\n\n1. [x] βοΈ Skeleton β Surface and recover failed settlements: proves the retry path end-to-end (claims: \"Failed settlement is retried\") #61"
},
"traces": [
{
"number": 61,
"title": "βοΈ Trace: Skeleton β settlement retry path",
"labels": [{ "name": "trace" }, { "name": "verified" }],
"scenario_claim": ["Failed settlement is retried"]
}
]
}
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 β 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" β 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 β your human partner chose inline execution, or no subagent tool is available | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |