Skip to content

xiduzo/wtf / skills/wtf.create-pr

wtf.create-pr

Verified

This skill should be used when a developer wants to open a pull request for a completed trace branch — for example "create a PR", "open a pull request", "submit this for review", "make a PR for trace

evals/fixtures/stacked-trace-branch.json

View on GitHub
{
  "_note": "Stacked Trace branch. Deepening #12 builds on Extension #11 whose branch trace/11-settlement-export is still open on origin with an open PR. Delivery is staged and the feature branch is feature/5-payment-settlement. Expected: the PR base is trace/11-settlement-export (the stack base), not the feature branch; the body carries `Closes #12` and says the PR is stacked. The gh-stack extension is deliberately absent, so this eval exercises the no-native-stack fallback (wtf.setup installs it by default).",
  "branch": "trace/12-settlement-failures",
  "config": {
    "_note": "contents of .wtf/config.json",
    "classification": "labels",
    "delivery": "staged"
  },
  "gh_extensions": [
    "yahsan2/gh-sub-issue",
    "xiduzo/gh-issue-dependency"
  ],
  "remote_branches": [
    "main",
    "feature/5-payment-settlement",
    "trace/11-settlement-export",
    "trace/12-settlement-failures"
  ],
  "pull_requests": [
    {
      "number": 61,
      "title": "feat(settlements): export settled payments as CSV",
      "headRefName": "trace/11-settlement-export",
      "baseRefName": "feature/5-payment-settlement",
      "state": "OPEN",
      "body": "Closes #11"
    }
  ],
  "trace": {
    "number": 12,
    "title": "☄️ Trace: Deepening — settlement failures",
    "labels": [
      {
        "name": "trace"
      },
      {
        "name": "designed"
      },
      {
        "name": "implemented"
      },
      {
        "name": "verified"
      }
    ],
    "body": "## Story\n\n- As a **Merchant**, I want to see the settlement status of a payment so that I know when funds arrive.\n\n## Scenario Claim\n\n- Scenario: Status for a failed settlement\n\n<details>\n<summary>Claimed scenarios — synced from Feature #5 — edit there, not here</summary>\n\n```gherkin\nScenario: Status for a failed settlement\n  Given a Merchant has a failed settlement\n  When the Merchant opens the settlement list\n  Then the payment shows status 'failed' with a reason code\n```\n\n</details>\n\n## Spine Position\n\n- Position: Deepening\n- Builds on: Trace #11\n\n## Impacted Areas\n\n- Backend: src/settlements/status/StatusService.ts\n- Frontend: src/ui/SettlementList.tsx\n- Database: —\n- APIs: GET /settlements\n- External systems: —\n\n## Technical Approach\n\n- Architecture decisions: reuse the status projection the Skeleton added; map failure reason codes in StatusService\n- Data flow: settlement record → StatusService.failureReason → SettlementList badge\n- Trade-offs: reason codes are mapped in the service, not the UI, so the export Trace can reuse them\n\n## Definition of Done\n\n- [x] All claimed scenarios covered by tests\n- [x] Contracts match implementation\n- [x] Observability in place\n- [x] System releasable after merge\n- [ ] Code reviewed\n- [x] Design reviewed (if UI)\n- [x] Documentation updated"
  },
  "feature": {
    "number": 5,
    "title": "🚀 Feature: Payment settlement",
    "labels": [
      {
        "name": "feature"
      },
      {
        "name": "designed"
      }
    ],
    "body": "## Bounded Context\nPayments\n\n## User Stories\n\n### Story 1: Merchant sees settlement status\n- As a **Merchant**, I want to see the settlement status of a payment so that I know when funds arrive.\n\n#### Acceptance Criteria\n- [ ] Merchants can see the status of a settled payment\n- [ ] Merchants can see why a settlement failed\n\n```gherkin\nScenario: Status shown for a settled payment\n  Given a Merchant has a settled payment\n  When the Merchant opens the settlement list\n  Then the payment shows status 'settled'\n\nScenario: Status for a failed settlement\n  Given a Merchant has a failed settlement\n  When the Merchant opens the settlement list\n  Then the payment shows status 'failed' with a reason code\n```\n\n### Story 2: Merchant exports settlements\n- As a **Merchant**, I want to export my settlements so that I can reconcile them in my accounting tool.\n\n```gherkin\nScenario: Export settled payments as CSV\n  Given a Merchant has settled payments\n  When the Merchant exports the settlement list\n  Then a CSV file with one row per settlement downloads\n```\n\n## Trace Plan\n1. [x] ☄️ Skeleton — Merchant sees settlement status: status for one settled payment (claims: \"Status shown for a settled payment\") #10\n2. [ ] ☄️ Extension — Merchant exports settlements: CSV export on the Spine (claims: \"Export settled payments as CSV\") #11\n3. [ ] ☄️ Deepening — Merchant sees settlement status: failure modes (claims: \"Status for a failed settlement\") #12\n\n## Delivery Override\n- Mode:\n- Reason:"
  },
  "epic": {
    "number": 2,
    "title": "🎯 Epic: Settlement visibility",
    "body": "## Goal\nMerchants understand where their money is without contacting support."
  },
  "git_log": "c4d5e6f feat(settlements): show failure reason code on the settlement list\nb3c4d5e test(settlements): cover failed settlement status",
  "git_diff_stat": " src/settlements/status/StatusService.ts      | 18 ++++++++++++++++\n src/ui/SettlementList.tsx                     |  9 ++++++++\n tests/settlements/status.failed.test.ts       | 31 +++++++++++++++++++++++++++\n 3 files changed, 58 insertions(+)"
}
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: 472kUpdated 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