Update to Zuora Coding Agent

{
  "name": "zuora-uat-run-feature",
  "description": "Internal worker — verify gate + execute-api + execute-ui for one feature",
  "included_files": [],
  "skill_md_contents": "---\nname: zuora-uat-run-feature\ndescription: Internal worker — verify gate + execute-api + execute-ui for one feature\n---\n\n# Run feature worker (internal)\n\n**Inputs:** `feature`, optional `tr_filter`, `verify` (`auto`|`true`|`false`), `environment`, `max_fix_retries`.\n\n## Startup (required, once per feature)\n\nEnsure a canonical verification manifest exists before any TR work:\n\n```bash\npython3 \"${CLAUDE_PLUGIN_ROOT}/references/uat-test/execution/scripts/uat_verification.py\" ensure-manifest \\\n  --git-root \"$GIT_ROOT\" \\\n  --feature \"<feature>\"\n# When tr_filter is set, append --tr N for each TR in scope\n```\n\nResolve scenario dir: `$UAT_ROOT/execution/tests/test_scenarios/test_<feature>/` (via `repo_paths.resolve_feature_scenario_dir`).\n\n## Per-TR verify decision\n\n| `verify` | Behavior |\n|----------|----------|\n| `false` | Execute directly; no fix/review |\n| `true` | Always run verify segment first |\n| `auto` | Run verify when mark missing, `verified: false`, or `artifact_revision` stale |\n\nCheck stale marks:\n\n```bash\npython3 \"${CLAUDE_PLUGIN_ROOT}/references/uat-test/execution/scripts/uat_verification.py\" should-verify \\\n  --scenario-dir \"<scenario_dir>\" --tr <n> --git-root \"$GIT_ROOT\" --feature \"<feature>\"\n```\n\nExit 0 → run verify; exit 1 → skip verify.\n\n## Per TR in scope\n\n1. **Verify gate** (when applicable) — `verify/SKILL.md`. On failure: skip execute for this TR.\n2. **Execute API** — `execute-api/SKILL.md`\n3. **Hybrid handoff (required after API pass)** — run:\n\n```bash\npython3 \"${CLAUDE_PLUGIN_ROOT}/references/uat-test/execution/scripts/hybrid_tr_prepare.py\" \\\n  --git-root \"$GIT_ROOT\" \\\n  --feature \"<feature>\" \\\n  --tr <n> \\\n  --environment \"<environment>\"\n```\n\n| `execute_ui` | Action |\n|--------------|--------|\n| `true` | **MUST** run `execute-ui/SKILL.md` using `variables`, `ui_steps_path`, and `debug_log` from script output. Do not return worker JSON until UI completes or retries are exhausted. |\n| `false` | Record skip reason in worker JSON (`execution.TRn.ui=skipped`, `execution.TRn.reason=<skip_reason>`). Call `record-ui-result` with `--status skipped --reason \"<skip_reason>\"`. |\n\n4. **Record UI outcome (required for hybrid TRs)** — after UI pass/fail/skip:\n\n```bash\npython3 \"${CLAUDE_PLUGIN_ROOT}/references/uat-test/execution/scripts/uat_verification.py\" record-ui-result \\\n  --scenario-dir \"<scenario_dir>\" \\\n  --tr <n> \\\n  --status passed|failed|skipped \\\n  --evidence \"<report_or_screenshot_path>\" \\\n  --summary \"<one-line outcome>\"\n```\n\n5. On verify pass during run: update mark (`verified: true`, `artifact_revision`)\n\n## Return contract (JSON only)\n\n```json\n{\n  \"feature\": \"<stem>\",\n  \"tr_filter\": [\"TR1\"],\n  \"status\": \"completed\",\n  \"artifacts\": {},\n  \"verification\": { \"TR1\": { \"verified\": true, \"artifact_revision\": \"abc123\" } },\n  \"execution\": {\n    \"TR1\": { \"api\": \"passed\", \"ui\": \"passed\", \"evidence\": \"execution/reports/tr1_account_page.md\" }\n  },\n  \"failures\": []\n}\n```\n\nReturn **only** this summary to the parent orchestrator.\n"
}