Skip to content

xiduzo/wtf / skills/wtf.write-trace

wtf.write-trace

Verified

This skill should be used when a user wants to create a single Trace issue under a Feature — for example "create a trace", "write a trace for this feature", "add a trace to feature

evals/fixtures/depth-split-draft.json

View on GitHub
{
  "_note": "Trace draft whose Scenario Claim is too large for one agent pass: six scenarios of one story spanning distinct failure domains (download, header content, empty range, permission, slow generation, email fallback). Step 8 must fire the scope gate and propose a DEPTH split — a re-partitioned Scenario Claim into a smaller first claim plus Deepening Traces — never a layer split (model/API/UI or migration/backend/frontend).",
  "feature": {
    "number": 55,
    "title": "🚀 Feature: Settlement PDF export",
    "labels": [{ "name": "feature" }],
    "body": "## User Stories\n\n### Story 1: Export settlement history as a PDF\n\n- As a **Merchant**, I want **to export my settlement history as a PDF** so that **I can satisfy my accounting and audit needs**\n\n#### Scenarios\n\n```gherkin\nScenario: Merchant downloads a settlement PDF\n  Given a Merchant with the settlement.export permission has settlements in the selected date range\n  When the Merchant triggers a PDF export\n  Then the Merchant receives a PDF of the settlement history for that range\n\nScenario: PDF header shows Merchant name and date range\n  Given a Merchant has triggered a PDF export\n  When the export completes\n  Then the PDF header shows the Merchant name, the export date, and the selected date range\n\nScenario: Empty settlement range produces a placeholder PDF\n  Given a Merchant has no settlements in the selected date range\n  When the Merchant triggers a PDF export\n  Then the PDF shows 'No settlements found' with the headers intact\n\nScenario: Merchant without export permission sees no export action\n  Given a Merchant without the settlement.export permission\n  When the Merchant views the settlement history\n  Then no export action is available\n\nScenario: Slow export shows a progress indicator\n  Given a PDF export takes longer than ten seconds\n  When the Merchant waits for the export\n  Then the Merchant sees a progress indicator and the export does not time out silently\n\nScenario: Very slow export is delivered by email\n  Given a PDF export takes longer than sixty seconds\n  When the export completes\n  Then the Merchant receives an email link to download the PDF\n```"
  },
  "trace": {
    "title": "Settlement PDF export",
    "feature_number": 55,
    "draft_body": "## Story\n\n- As a **Merchant**, I want **to export my settlement history as a PDF** so that **I can satisfy my accounting and audit needs**\n\n## Scenario Claim\n\n- Scenario: Merchant downloads a settlement PDF\n- Scenario: PDF header shows Merchant name and date range\n- Scenario: Empty settlement range produces a placeholder PDF\n- Scenario: Merchant without export permission sees no export action\n- Scenario: Slow export shows a progress indicator\n- Scenario: Very slow export is delivered by email\n\n<details>\n<summary>Claimed scenarios — synced from Feature #55 — edit there, not here</summary>\n\n(all six scenarios, copied verbatim from the Feature body)\n\n</details>\n\n## Spine Position\n\n- Position: Skeleton\n- Builds on: none\n\n## Test Mapping\n\n| Claimed scenario | Test file | Status |\n| ---------------- | --------- | ------ |\n| Merchant downloads a settlement PDF | | |\n| PDF header shows Merchant name and date range | | |\n| Empty settlement range produces a placeholder PDF | | |\n| Merchant without export permission sees no export action | | |\n| Slow export shows a progress indicator | | |\n| Very slow export is delivered by email | | |"
  }
}
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