[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6EGHCZRMSNVDNG2V4DEJHHF":3,"skill-same:01M6EGHCZRMSNVDNG2V4DEJHHF":81},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":16,"categories":17,"keywords":26,"publishedAt":46,"linkOnly":47,"markdownContent":48,"markdownBody":49,"frontMatter":50,"refName":52,"commitSha":53,"skillDirectory":54,"forksCount":55,"repositoryHtmlUrl":56,"repositoryHomepageUrl":6,"ownerHtmlUrl":57,"ownerBlogUrl":58,"ownerDescription":59,"updatedAt":60,"install":61,"resources":74},"01M6EGHCZRMSNVDNG2V4DEJHHF","ln-630-test-auditor",null,"Test suite audit coordinator: automated + manual tests. Delegates to 6 workers (Business Logic, E2E, Value, Coverage, Isolation, Manual Quality). Output: docs\u002Fproject\u002Ftest_audit.md.","levalencia\u002Fagent-god-mode","levalencia","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F6962857?v=4","01M6EB0FZZ4BPQPC4HET4QY6NM","Luis Valencia ","01M6EB0G4HWHPWW0H9X7QKSAHP",3,"MIT","https:\u002F\u002Fgithub.com\u002Flevalencia\u002Fagent-god-mode\u002Fblob\u002Fmain\u002Forganized-skills\u002Fln-630-test-auditor\u002FSKILL.md",[18,23],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000008","测试与质量","SCENARIO","使用场景",{"categoryNo":24,"categoryName":25,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000023","Skill与智能体开发",[27,28,29,30,31,32,33,34,35,36,37,38,39,40,41,42,43,44,45],"ln 630 test auditor","test","coverage","isolation","tests","logic","project","context7","workers","test suite","business","MCP","read","grep","quality","Bash","e2e","audit","docs","2026-11-10 10:12:30",false,"---\nname: ln-630-test-auditor\ndescription: \"Test suite audit coordinator: automated + manual tests. Delegates to 6 workers (Business Logic, E2E, Value, Coverage, Isolation, Manual Quality). Output: docs\u002Fproject\u002Ftest_audit.md.\"\nallowed-tools: Read, Grep, Glob, Bash, mcp__Ref, mcp__context7, Skill\nlicense: MIT\n---\n\n> **Paths:** File paths (`shared\u002F`, `references\u002F`, `..\u002Fln-*`) are relative to skills repo root. If not found at CWD, locate this SKILL.md directory and go up one level for repo root.\n\n# Test Suite Auditor (L2 Coordinator)\n\nCoordinates comprehensive test suite audit across 7 quality categories using 6 specialized workers. Discovers both automated tests (`*.test.*`, `*.spec.*`) and manual tests (`tests\u002Fmanual\u002F**\u002F*.sh`).\n\n## Purpose & Scope\n\n- **L2 Coordinator** that delegates to L3 specialized audit workers\n- Audits all tests against 7 quality categories (via 6 workers)\n- Calculates **Usefulness Score** for each test (Keep\u002FRemove\u002FRefactor)\n- Identifies missing tests for critical business logic\n- Detects anti-patterns and isolation issues\n- Aggregates results into unified report\n- Write report to `docs\u002Fproject\u002Ftest_audit.md` (file-based, no task creation)\n- Manual invocation by user; not part of Story pipeline\n\n## Core Philosophy\n\n> \"Write tests. Not too many. Mostly integration.\" — Kent Beck\n> \"Test based on risk, not coverage.\" — ISO 29119\n\n**Key Principles:**\n1. **Test business logic, not frameworks** — bcrypt\u002FPrisma\u002FExpress already tested\n2. **No performance\u002Fload\u002Fstress tests** — Tests infrastructure, not code correctness (use k6\u002FJMeter separately)\n3. **Risk-based prioritization** — Priority ≥15 or remove\n4. **E2E for critical paths only** — Money\u002FSecurity\u002FData (Priority ≥20)\n5. **Usefulness over quantity** — One useful test > 10 useless tests\n6. **Every test must justify existence** — Impact × Probability ≥15\n\n## Workflow\n\n### Phase 1: Discovery (Automated)\n\n**Inputs:** Codebase root directory\n\n**Actions:**\n1. Find all test files using Glob:\n   - `**\u002F*.test.*` (Jest, Vitest)\n   - `**\u002F*.spec.*` (Mocha, Jasmine)\n   - `**\u002F__tests__\u002F**\u002F*` (Jest convention)\n   - `tests\u002Fmanual\u002F**\u002F*.sh` (manual bash test scripts)\n2. Parse test file structure (test names, assertions count)\n3. Tag each file with `type: \"automated\"|\"manual\"`\n4. For manual tests: detect `has_expected_dir` (sibling `expected\u002F` exists), `suite_dir`, `harness_sourced` (sources test_harness.sh)\n5. Auto-discover Team ID from [docs\u002Ftasks\u002Fkanban_board.md](..\u002Fdocs\u002Ftasks\u002Fkanban_board.md)\n\n**Output:** `testFilesMetadata` — list of test files with basic stats and `type` field\n\n### Phase 2: Research Best Practices (ONCE)\n\n**Goal:** Gather testing best practices context ONCE, share with all workers\n\n**Actions:**\n1. Use MCP Ref\u002FContext7 to research testing best practices for detected tech stack\n2. Load [..\u002Fshared\u002Freferences\u002Frisk_based_testing_guide.md](..\u002Fshared\u002Freferences\u002Frisk_based_testing_guide.md)\n3. Build `contextStore` with:\n   - Testing philosophy (E2E primary, Unit supplementary)\n   - Usefulness Score formulas (Impact × Probability)\n   - Anti-patterns catalog\n   - Framework detection patterns\n   - Manual test quality criteria (harness adoption, golden files, fail-fast, config sourcing)\n\n**Add output_dir to contextStore:**\n```json\n{\n  \"output_dir\": \"docs\u002Fproject\u002F.audit\u002Fln-630\u002F{YYYY-MM-DD}\"\n}\n```\n\n**Output:** `contextStore` — shared context for all workers\n\n**Key Benefit:** Context gathered ONCE → passed to all workers → token-efficient\n\n### Phase 3: Domain Discovery\n\n```bash\nmkdir -p {output_dir}   # Worker files cleaned up after consolidation (Phase 7)\n```\n\n**MANDATORY READ:** Load `shared\u002Freferences\u002Faudit_coordinator_domain_mode.md`.\n\nDetect `domain_mode` and `all_domains` with the shared pattern. This coordinator keeps one local rule: shared folders remain visible in coverage analysis, but do not inflate business-domain coverage percentages.\n\n### Phase 4: Delegate to Workers\n\n**MANDATORY READ:** Load `shared\u002Freferences\u002Ftask_delegation_pattern.md` and `shared\u002Freferences\u002Faudit_worker_core_contract.md`.\n\n#### Phase 4a: Global Workers (PARALLEL)\n\n**Global workers** scan entire test suite (not domain-aware):\n\n| # | Worker | Category | What It Audits |\n|---|--------|----------|----------------|\n| 1 | [ln-631-test-business-logic-auditor](..\u002Fln-631-test-business-logic-auditor\u002F) | Business Logic Focus | Framework\u002FLibrary tests (Prisma, Express, bcrypt, JWT, axios, React hooks) → REMOVE |\n| 2 | [ln-632-test-e2e-priority-auditor](..\u002Fln-632-test-e2e-priority-auditor\u002F) | E2E Priority | E2E baseline (2\u002Fendpoint), Pyramid validation, Missing E2E tests |\n| 3 | [ln-633-test-value-auditor](..\u002Fln-633-test-value-auditor\u002F) | Risk-Based Value | Usefulness Score = Impact × Probability\u003Cbr>Decisions: ≥15 KEEP, 10-14 REVIEW, \u003C10 REMOVE |\n| 5 | [ln-635-test-isolation-auditor](..\u002Fln-635-test-isolation-auditor\u002F) | Isolation + Anti-Patterns | Isolation (6 categories), Determinism, Anti-Patterns (7 types) |\n| 6 | [ln-636-manual-test-auditor](..\u002Fln-636-manual-test-auditor\u002F) | Manual Test Quality | Harness adoption, golden files, fail-fast, config sourcing, template compliance, idempotency |\n\n**Type-filtered delegation:** Coordinator splits `testFilesMetadata` by `type` before passing to workers:\n- ln-631..635 receive `testFilesMetadata.filter(f => f.type == \"automated\")` only\n- ln-636 receives `testFilesMetadata.filter(f => f.type == \"manual\")` only\n\n**Invocation (5 workers in PARALLEL):**\n```javascript\nFOR EACH worker IN [ln-631, ln-632, ln-633, ln-635, ln-636]:\n  Agent(description: \"Test audit via \" + worker,\n       prompt: \"Execute audit worker.\n\nStep 1: Invoke worker:\n  Skill(skill: \\\"\" + worker + \"\\\")\n\nCONTEXT:\n\" + JSON.stringify({...contextStore, testFilesMetadata: filteredByType}),\n       subagent_type: \"general-purpose\")\n```\n\n#### Phase 4b: Domain-Aware Worker (PARALLEL per domain)\n\n**Domain-aware worker** runs once per domain:\n\n| # | Worker | Category | What It Audits |\n|---|--------|----------|----------------|\n| 4 | [ln-634-test-coverage-auditor](..\u002Fln-634-test-coverage-auditor\u002F) | Coverage Gaps | Missing tests for critical paths per domain (Money 20+, Security 20+, Data 15+, Core Flows 15+) |\n\n**Invocation:**\n```javascript\nIF domain_mode == \"domain-aware\":\n  FOR EACH domain IN all_domains:\n    domain_context = {\n      ...contextStore,\n      domain_mode: \"domain-aware\",\n      current_domain: { name: domain.name, path: domain.path }\n    }\n    Agent(description: \"Test coverage \" + domain.name + \" via ln-634\",\n         prompt: \"Execute audit worker.\n\nStep 1: Invoke worker:\n  Skill(skill: \\\"ln-634-test-coverage-auditor\\\")\n\nCONTEXT:\n\" + JSON.stringify(domain_context),\n         subagent_type: \"general-purpose\")\nELSE:\n  \u002F\u002F Fallback: invoke once for entire codebase (global mode)\n  Agent(description: \"Test coverage via ln-634\",\n       prompt: \"Execute audit worker.\n\nStep 1: Invoke worker:\n  Skill(skill: \\\"ln-634-test-coverage-auditor\\\")\n\nCONTEXT:\n\" + JSON.stringify(contextStore),\n       subagent_type: \"general-purpose\")\n```\n\n**Parallelism strategy:**\n- Phase 4a: All 5 global workers run in PARALLEL\n- Phase 4b: All N domain-aware invocations run in PARALLEL\n- Example: 3 domains → 5 global + 3 ln-634 invocations in single message\n\n**Domain-aware workers** add optional fields: `domain`, `scan_path`\n\n### Phase 5: Aggregate Results (File-Based)\n\n**MANDATORY READ:** Load `shared\u002Freferences\u002Faudit_coordinator_aggregation.md` and `shared\u002Freferences\u002Fcontext_validation.md`.\n\nUse the shared aggregation pattern for output directory checks, return-value parsing, severity rollups, file reads, and final report assembly.\n\nLocal rules for this coordinator:\n- Categories 1-3, 5-7 stay global in the final report.\n- Category 4 (Coverage Gaps) is grouped per domain when `domain_mode=\"domain-aware\"`.\n- Overall score = average of 6 worker scores.\n\n**Context Validation (Post-Filter):**\n\nApply Rules 1, 5 + test-specific filters to merged findings:\n```\nFOR EACH finding WHERE severity IN (HIGH, MEDIUM):\n  # Rule 1: ADR\u002FPlanned Override\n  IF finding matches ADR → advisory \"[Planned: ADR-XXX]\"\n\n  # Rule 5: Locality\u002FSingle-Consumer\n  IF \"extract shared helper\" suggestion AND consumer_count == 1 → advisory\n\n  # Test-specific: Custom wrapper detection\n  IF \"framework test\" finding (ln-631) AND test imports custom wrapper class:\n    → advisory (tests custom logic, not framework)\n\n  # Test-specific: Setup\u002Ffixture code\n  IF \"The Liar\" finding (ln-635) AND file is conftest\u002Ffixture\u002Fsetup:\n    → advisory (setup code, no assertions expected)\n\n  # Test-specific: Parameterized test\n  IF \"The Giant\" finding (ln-635) AND test is parameterized\u002Fdata-driven:\n    → severity -= 1 (size from data, not complexity)\n\nDowngraded findings → \"Advisory Findings\" section in report.\nRecalculate scores excluding advisory findings from penalty.\n```\n\n**Exempt:** Coverage gap CRITICAL findings (ln-634), risk-value scores (ln-633).\n\n## Output Format\n\n```markdown\n## Test Suite Audit Report - [DATE]\n\n### Executive Summary\n[2-3 sentences: test suite health, major issues, key recommendations]\n\n### Severity Summary\n\n| Severity | Count |\n|----------|-------|\n| Critical | X |\n| High | X |\n| Medium | X |\n| Low | X |\n| **Total** | **X** |\n\n### Compliance Score\n\n| Category | Score | Notes |\n|----------|-------|-------|\n| Business Logic Focus | X\u002F10 | X framework tests found |\n| E2E Critical Coverage | X\u002F10 | X critical paths missing E2E |\n| Risk-Based Value | X\u002F10 | X low-value tests |\n| Coverage Gaps | X\u002F10 | X critical paths untested |\n| Isolation & Anti-Patterns | X\u002F10 | X isolation + anti-pattern issues |\n| Manual Test Quality | X\u002F10 | X manual test quality issues |\n| **Overall** | **X\u002F10** | Average of 6 categories |\n\n### Domain Coverage Summary (NEW - if domain_mode=\"domain-aware\")\n\n| Domain | Critical Paths | Tested | Coverage % | Gaps |\n|--------|---------------|--------|------------|------|\n| users | 8 | 6 | 75% | 2 |\n| orders | 12 | 8 | 67% | 4 |\n| payments | 6 | 5 | 83% | 1 |\n| **Total** | **26** | **19** | **73%** | **7** |\n\n### Audit Findings\n\n| Severity | Location | Issue | Principle | Recommendation | Effort |\n|----------|----------|-------|-----------|----------------|--------|\n| **CRITICAL** | routes\u002Fpayment.ts:45 | Missing E2E for payment processing (Priority 25) | E2E Critical Coverage \u002F Money Flow | Add E2E: successful payment + discount edge cases | M |\n| **HIGH** | auth.test.ts:45-52 | Test 'bcrypt hashes password' validates library behavior | Business Logic Focus \u002F Crypto Testing | Delete — bcrypt already tested by maintainers | S |\n| **HIGH** | db.test.ts:78-85 | Test 'Prisma findMany returns array' validates ORM | Business Logic Focus \u002F ORM Testing | Delete — Prisma already tested | S |\n| **HIGH** | user.test.ts:45 | Anti-pattern 'The Liar' — no assertions | Anti-Patterns \u002F The Liar | Add specific assertions or delete test | S |\n| **MEDIUM** | utils.test.ts:23-27 | Test 'validateEmail' has Usefulness Score 4 | Risk-Based Value \u002F Low Priority | Delete — likely covered by E2E registration | S |\n| **MEDIUM** | order.test.ts:200-350 | Anti-pattern 'The Giant' — 150 lines | Anti-Patterns \u002F The Giant | Split into focused tests | M |\n| **LOW** | payment.test.ts | Anti-pattern 'Happy Path Only' — no error tests | Anti-Patterns \u002F Happy Path | Add negative tests | M |\n\n### Coverage Gaps by Domain (if domain_mode=\"domain-aware\")\n\n#### Domain: users (src\u002Fusers\u002F)\n\n| Severity | Category | Missing Test | Location | Priority | Effort |\n|----------|----------|--------------|----------|----------|--------|\n| CRITICAL | Money | E2E: processRefund() | services\u002Fuser.ts:120 | 20 | M |\n| HIGH | Security | Unit: validatePermissions() | middleware\u002Fauth.ts:45 | 18 | S |\n\n#### Domain: orders (src\u002Forders\u002F)\n\n| Severity | Category | Missing Test | Location | Priority | Effort |\n|----------|----------|--------------|----------|----------|--------|\n| CRITICAL | Money | E2E: applyDiscount() | services\u002Forder.ts:45 | 25 | M |\n| HIGH | Data | Integration: orderTransaction() | repositories\u002Forder.ts:78 | 16 | M |\n```\n\n## Worker Architecture\n\nEach worker:\n- Receives `contextStore` with testing best practices\n- Receives `testFilesMetadata` with test file list (tagged with `type: \"automated\"|\"manual\"`)\n- Workers 1-5 (ln-631..ln-635) focus on automated tests; worker 6 (ln-636) focuses on manual tests\n- Loads full test file contents when analyzing\n- Returns structured JSON with category findings\n- Operates independently (failure in one doesn't block others)\n\n**Token Efficiency:**\n- Coordinator: metadata only (~1000 tokens)\n- Workers: full test file contents when needed (~5000-10000 tokens each)\n- Context gathered ONCE, shared with all workers\n\n## Critical Rules\n\n- **Two-stage delegation:** Global workers (5) + Domain-aware worker (ln-634 × N domains)\n- **Domain discovery:** Auto-detect domains from folder structure; fallback to global mode if \u003C2 domains\n- **Parallel execution:** All workers (global + domain-aware) run in PARALLEL\n- **Domain-grouped output:** Coverage Gaps findings grouped by domain (if domain_mode=\"domain-aware\")\n- **Delete > Archive:** Remove useless tests, don't comment out\n- **E2E baseline:** Every endpoint needs 2 E2E (positive + negative)\n- **Justify each test:** If can't explain Priority ≥15, remove it\n- **Trust frameworks:** Don't test Express\u002FPrisma\u002Fbcrypt behavior\n- **No performance\u002Fload tests:** Flag and REMOVE tests measuring throughput\u002Flatency\u002Fmemory (DevOps Epic territory)\n- **Code is truth:** If test contradicts code behavior, update test\n- **Language preservation:** Report in project's language (EN\u002FRU)\n\n## Phase 6: Append Results Log\n\n**MANDATORY READ:** Load `shared\u002Freferences\u002Fresults_log_pattern.md`\n\nAppend one row to `docs\u002Fproject\u002F.audit\u002Fresults_log.md` with: Skill=`ln-630`, Metric=`overall_score`, Scale=`0-10`, Score from Phase 5 aggregation. Calculate Delta vs previous `ln-630` row. Create file with header if missing. Rolling window: max 50 entries.\n\n## Phase 7: Cleanup Worker Files\n\n```bash\nrm -rf {output_dir}\n```\n\nDelete the dated output directory (`docs\u002Fproject\u002F.audit\u002Fln-630\u002F{YYYY-MM-DD}\u002F`). The consolidated report and results log already preserve all audit data.\n\n## Definition of Done\n\n- All test files discovered via Glob (automated + manual)\n- Manual test files tagged with `type: \"manual\"` in testFilesMetadata\n- Context gathered from testing best practices (MCP Ref\u002FContext7)\n- Domain discovery completed (domain_mode determined)\n- contextStore built with test metadata + domain info\n- Global workers (5) invoked in PARALLEL (ln-631, ln-632, ln-633, ln-635, ln-636)\n- Domain-aware worker (ln-634) invoked per domain in PARALLEL\n- All workers completed successfully (or reported errors)\n- Results aggregated with domain grouping (if domain_mode=\"domain-aware\")\n- Domain Coverage Summary built (if domain_mode=\"domain-aware\")\n- Compliance scores calculated (7 categories)\n- Keep\u002FRemove\u002FRefactor decisions for each test\n- Missing tests identified with Priority (grouped by domain if applicable)\n- Anti-patterns catalogued\n- Report written to `docs\u002Fproject\u002Ftest_audit.md`\n- Results log row appended to `docs\u002Fproject\u002F.audit\u002Fresults_log.md`\n- Worker output directory cleaned up after consolidation\n- Summary returned to user\n\n## Phase 8: Meta-Analysis\n\n**MANDATORY READ:** Load `shared\u002Freferences\u002Fmeta_analysis_protocol.md`\n\nSkill type: `review-coordinator` (workers only). Run after all phases complete. Output to chat using the `review-coordinator — workers only` format.\n\n## Reference Files\n\n- **Orchestrator lifecycle:** `shared\u002Freferences\u002Forchestrator_pattern.md`\n- **Risk-based testing methodology:** `shared\u002Freferences\u002Frisk_based_testing_guide.md`\n- **Task delegation pattern:** `shared\u002Freferences\u002Ftask_delegation_pattern.md`\n- **Domain mode pattern:** `shared\u002Freferences\u002Faudit_coordinator_domain_mode.md`\n- **Aggregation pattern:** `shared\u002Freferences\u002Faudit_coordinator_aggregation.md`\n- **MANDATORY READ:** `shared\u002Freferences\u002Fresearch_tool_fallback.md`\n\n## Related Skills\n\n- **Workers:**\n  - [ln-631-test-business-logic-auditor](..\u002Fln-631-test-business-logic-auditor\u002F) — Framework tests detection\n  - [ln-632-test-e2e-priority-auditor](..\u002Fln-632-test-e2e-priority-auditor\u002F) — E2E baseline validation\n  - [ln-633-test-value-auditor](..\u002Fln-633-test-value-auditor\u002F) — Usefulness Score calculation\n  - [ln-634-test-coverage-auditor](..\u002Fln-634-test-coverage-auditor\u002F) — Coverage gaps identification\n  - [ln-635-test-isolation-auditor](..\u002Fln-635-test-isolation-auditor\u002F) — Isolation + Anti-Patterns\n  - [ln-636-manual-test-auditor](..\u002Fln-636-manual-test-auditor\u002F) — Manual Test Quality\n\n- **Reference:**\n  - [..\u002Fshared\u002Freferences\u002Frisk_based_testing_guide.md](..\u002Fshared\u002Freferences\u002Frisk_based_testing_guide.md) — Risk-Based Testing Guide\n\n---\n**Version:** 4.0.0\n**Last Updated:** 2025-12-23\n","> **Paths:** File paths (`shared\u002F`, `references\u002F`, `..\u002Fln-*`) are relative to skills repo root. If not found at CWD, locate this SKILL.md directory and go up one level for repo root.\n\n# Test Suite Auditor (L2 Coordinator)\n\nCoordinates comprehensive test suite audit across 7 quality categories using 6 specialized workers. Discovers both automated tests (`*.test.*`, `*.spec.*`) and manual tests (`tests\u002Fmanual\u002F**\u002F*.sh`).\n\n## Purpose & Scope\n\n- **L2 Coordinator** that delegates to L3 specialized audit workers\n- Audits all tests against 7 quality categories (via 6 workers)\n- Calculates **Usefulness Score** for each test (Keep\u002FRemove\u002FRefactor)\n- Identifies missing tests for critical business logic\n- Detects anti-patterns and isolation issues\n- Aggregates results into unified report\n- Write report to `docs\u002Fproject\u002Ftest_audit.md` (file-based, no task creation)\n- Manual invocation by user; not part of Story pipeline\n\n## Core Philosophy\n\n> \"Write tests. Not too many. Mostly integration.\" — Kent Beck\n> \"Test based on risk, not coverage.\" — ISO 29119\n\n**Key Principles:**\n1. **Test business logic, not frameworks** — bcrypt\u002FPrisma\u002FExpress already tested\n2. **No performance\u002Fload\u002Fstress tests** — Tests infrastructure, not code correctness (use k6\u002FJMeter separately)\n3. **Risk-based prioritization** — Priority ≥15 or remove\n4. **E2E for critical paths only** — Money\u002FSecurity\u002FData (Priority ≥20)\n5. **Usefulness over quantity** — One useful test > 10 useless tests\n6. **Every test must justify existence** — Impact × Probability ≥15\n\n## Workflow\n\n### Phase 1: Discovery (Automated)\n\n**Inputs:** Codebase root directory\n\n**Actions:**\n1. Find all test files using Glob:\n   - `**\u002F*.test.*` (Jest, Vitest)\n   - `**\u002F*.spec.*` (Mocha, Jasmine)\n   - `**\u002F__tests__\u002F**\u002F*` (Jest convention)\n   - `tests\u002Fmanual\u002F**\u002F*.sh` (manual bash test scripts)\n2. Parse test file structure (test names, assertions count)\n3. Tag each file with `type: \"automated\"|\"manual\"`\n4. For manual tests: detect `has_expected_dir` (sibling `expected\u002F` exists), `suite_dir`, `harness_sourced` (sources test_harness.sh)\n5. Auto-discover Team ID from [docs\u002Ftasks\u002Fkanban_board.md](..\u002Fdocs\u002Ftasks\u002Fkanban_board.md)\n\n**Output:** `testFilesMetadata` — list of test files with basic stats and `type` field\n\n### Phase 2: Research Best Practices (ONCE)\n\n**Goal:** Gather testing best practices context ONCE, share with all workers\n\n**Actions:**\n1. Use MCP Ref\u002FContext7 to research testing best practices for detected tech stack\n2. Load [..\u002Fshared\u002Freferences\u002Frisk_based_testing_guide.md](..\u002Fshared\u002Freferences\u002Frisk_based_testing_guide.md)\n3. Build `contextStore` with:\n   - Testing philosophy (E2E primary, Unit supplementary)\n   - Usefulness Score formulas (Impact × Probability)\n   - Anti-patterns catalog\n   - Framework detection patterns\n   - Manual test quality criteria (harness adoption, golden files, fail-fast, config sourcing)\n\n**Add output_dir to contextStore:**\n```json\n{\n  \"output_dir\": \"docs\u002Fproject\u002F.audit\u002Fln-630\u002F{YYYY-MM-DD}\"\n}\n```\n\n**Output:** `contextStore` — shared context for all workers\n\n**Key Benefit:** Context gathered ONCE → passed to all workers → token-efficient\n\n### Phase 3: Domain Discovery\n\n```bash\nmkdir -p {output_dir}   # Worker files cleaned up after consolidation (Phase 7)\n```\n\n**MANDATORY READ:** Load `shared\u002Freferences\u002Faudit_coordinator_domain_mode.md`.\n\nDetect `domain_mode` and `all_domains` with the shared pattern. This coordinator keeps one local rule: shared folders remain visible in coverage analysis, but do not inflate business-domain coverage percentages.\n\n### Phase 4: Delegate to Workers\n\n**MANDATORY READ:** Load `shared\u002Freferences\u002Ftask_delegation_pattern.md` and `shared\u002Freferences\u002Faudit_worker_core_contract.md`.\n\n#### Phase 4a: Global Workers (PARALLEL)\n\n**Global workers** scan entire test suite (not domain-aware):\n\n| # | Worker | Category | What It Audits |\n|---|--------|----------|----------------|\n| 1 | [ln-631-test-business-logic-auditor](..\u002Fln-631-test-business-logic-auditor\u002F) | Business Logic Focus | Framework\u002FLibrary tests (Prisma, Express, bcrypt, JWT, axios, React hooks) → REMOVE |\n| 2 | [ln-632-test-e2e-priority-auditor](..\u002Fln-632-test-e2e-priority-auditor\u002F) | E2E Priority | E2E baseline (2\u002Fendpoint), Pyramid validation, Missing E2E tests |\n| 3 | [ln-633-test-value-auditor](..\u002Fln-633-test-value-auditor\u002F) | Risk-Based Value | Usefulness Score = Impact × Probability\u003Cbr>Decisions: ≥15 KEEP, 10-14 REVIEW, \u003C10 REMOVE |\n| 5 | [ln-635-test-isolation-auditor](..\u002Fln-635-test-isolation-auditor\u002F) | Isolation + Anti-Patterns | Isolation (6 categories), Determinism, Anti-Patterns (7 types) |\n| 6 | [ln-636-manual-test-auditor](..\u002Fln-636-manual-test-auditor\u002F) | Manual Test Quality | Harness adoption, golden files, fail-fast, config sourcing, template compliance, idempotency |\n\n**Type-filtered delegation:** Coordinator splits `testFilesMetadata` by `type` before passing to workers:\n- ln-631..635 receive `testFilesMetadata.filter(f => f.type == \"automated\")` only\n- ln-636 receives `testFilesMetadata.filter(f => f.type == \"manual\")` only\n\n**Invocation (5 workers in PARALLEL):**\n```javascript\nFOR EACH worker IN [ln-631, ln-632, ln-633, ln-635, ln-636]:\n  Agent(description: \"Test audit via \" + worker,\n       prompt: \"Execute audit worker.\n\nStep 1: Invoke worker:\n  Skill(skill: \\\"\" + worker + \"\\\")\n\nCONTEXT:\n\" + JSON.stringify({...contextStore, testFilesMetadata: filteredByType}),\n       subagent_type: \"general-purpose\")\n```\n\n#### Phase 4b: Domain-Aware Worker (PARALLEL per domain)\n\n**Domain-aware worker** runs once per domain:\n\n| # | Worker | Category | What It Audits |\n|---|--------|----------|----------------|\n| 4 | [ln-634-test-coverage-auditor](..\u002Fln-634-test-coverage-auditor\u002F) | Coverage Gaps | Missing tests for critical paths per domain (Money 20+, Security 20+, Data 15+, Core Flows 15+) |\n\n**Invocation:**\n```javascript\nIF domain_mode == \"domain-aware\":\n  FOR EACH domain IN all_domains:\n    domain_context = {\n      ...contextStore,\n      domain_mode: \"domain-aware\",\n      current_domain: { name: domain.name, path: domain.path }\n    }\n    Agent(description: \"Test coverage \" + domain.name + \" via ln-634\",\n         prompt: \"Execute audit worker.\n\nStep 1: Invoke worker:\n  Skill(skill: \\\"ln-634-test-coverage-auditor\\\")\n\nCONTEXT:\n\" + JSON.stringify(domain_context),\n         subagent_type: \"general-purpose\")\nELSE:\n  \u002F\u002F Fallback: invoke once for entire codebase (global mode)\n  Agent(description: \"Test coverage via ln-634\",\n       prompt: \"Execute audit worker.\n\nStep 1: Invoke worker:\n  Skill(skill: \\\"ln-634-test-coverage-auditor\\\")\n\nCONTEXT:\n\" + JSON.stringify(contextStore),\n       subagent_type: \"general-purpose\")\n```\n\n**Parallelism strategy:**\n- Phase 4a: All 5 global workers run in PARALLEL\n- Phase 4b: All N domain-aware invocations run in PARALLEL\n- Example: 3 domains → 5 global + 3 ln-634 invocations in single message\n\n**Domain-aware workers** add optional fields: `domain`, `scan_path`\n\n### Phase 5: Aggregate Results (File-Based)\n\n**MANDATORY READ:** Load `shared\u002Freferences\u002Faudit_coordinator_aggregation.md` and `shared\u002Freferences\u002Fcontext_validation.md`.\n\nUse the shared aggregation pattern for output directory checks, return-value parsing, severity rollups, file reads, and final report assembly.\n\nLocal rules for this coordinator:\n- Categories 1-3, 5-7 stay global in the final report.\n- Category 4 (Coverage Gaps) is grouped per domain when `domain_mode=\"domain-aware\"`.\n- Overall score = average of 6 worker scores.\n\n**Context Validation (Post-Filter):**\n\nApply Rules 1, 5 + test-specific filters to merged findings:\n```\nFOR EACH finding WHERE severity IN (HIGH, MEDIUM):\n  # Rule 1: ADR\u002FPlanned Override\n  IF finding matches ADR → advisory \"[Planned: ADR-XXX]\"\n\n  # Rule 5: Locality\u002FSingle-Consumer\n  IF \"extract shared helper\" suggestion AND consumer_count == 1 → advisory\n\n  # Test-specific: Custom wrapper detection\n  IF \"framework test\" finding (ln-631) AND test imports custom wrapper class:\n    → advisory (tests custom logic, not framework)\n\n  # Test-specific: Setup\u002Ffixture code\n  IF \"The Liar\" finding (ln-635) AND file is conftest\u002Ffixture\u002Fsetup:\n    → advisory (setup code, no assertions expected)\n\n  # Test-specific: Parameterized test\n  IF \"The Giant\" finding (ln-635) AND test is parameterized\u002Fdata-driven:\n    → severity -= 1 (size from data, not complexity)\n\nDowngraded findings → \"Advisory Findings\" section in report.\nRecalculate scores excluding advisory findings from penalty.\n```\n\n**Exempt:** Coverage gap CRITICAL findings (ln-634), risk-value scores (ln-633).\n\n## Output Format\n\n```markdown\n## Test Suite Audit Report - [DATE]\n\n### Executive Summary\n[2-3 sentences: test suite health, major issues, key recommendations]\n\n### Severity Summary\n\n| Severity | Count |\n|----------|-------|\n| Critical | X |\n| High | X |\n| Medium | X |\n| Low | X |\n| **Total** | **X** |\n\n### Compliance Score\n\n| Category | Score | Notes |\n|----------|-------|-------|\n| Business Logic Focus | X\u002F10 | X framework tests found |\n| E2E Critical Coverage | X\u002F10 | X critical paths missing E2E |\n| Risk-Based Value | X\u002F10 | X low-value tests |\n| Coverage Gaps | X\u002F10 | X critical paths untested |\n| Isolation & Anti-Patterns | X\u002F10 | X isolation + anti-pattern issues |\n| Manual Test Quality | X\u002F10 | X manual test quality issues |\n| **Overall** | **X\u002F10** | Average of 6 categories |\n\n### Domain Coverage Summary (NEW - if domain_mode=\"domain-aware\")\n\n| Domain | Critical Paths | Tested | Coverage % | Gaps |\n|--------|---------------|--------|------------|------|\n| users | 8 | 6 | 75% | 2 |\n| orders | 12 | 8 | 67% | 4 |\n| payments | 6 | 5 | 83% | 1 |\n| **Total** | **26** | **19** | **73%** | **7** |\n\n### Audit Findings\n\n| Severity | Location | Issue | Principle | Recommendation | Effort |\n|----------|----------|-------|-----------|----------------|--------|\n| **CRITICAL** | routes\u002Fpayment.ts:45 | Missing E2E for payment processing (Priority 25) | E2E Critical Coverage \u002F Money Flow | Add E2E: successful payment + discount edge cases | M |\n| **HIGH** | auth.test.ts:45-52 | Test 'bcrypt hashes password' validates library behavior | Business Logic Focus \u002F Crypto Testing | Delete — bcrypt already tested by maintainers | S |\n| **HIGH** | db.test.ts:78-85 | Test 'Prisma findMany returns array' validates ORM | Business Logic Focus \u002F ORM Testing | Delete — Prisma already tested | S |\n| **HIGH** | user.test.ts:45 | Anti-pattern 'The Liar' — no assertions | Anti-Patterns \u002F The Liar | Add specific assertions or delete test | S |\n| **MEDIUM** | utils.test.ts:23-27 | Test 'validateEmail' has Usefulness Score 4 | Risk-Based Value \u002F Low Priority | Delete — likely covered by E2E registration | S |\n| **MEDIUM** | order.test.ts:200-350 | Anti-pattern 'The Giant' — 150 lines | Anti-Patterns \u002F The Giant | Split into focused tests | M |\n| **LOW** | payment.test.ts | Anti-pattern 'Happy Path Only' — no error tests | Anti-Patterns \u002F Happy Path | Add negative tests | M |\n\n### Coverage Gaps by Domain (if domain_mode=\"domain-aware\")\n\n#### Domain: users (src\u002Fusers\u002F)\n\n| Severity | Category | Missing Test | Location | Priority | Effort |\n|----------|----------|--------------|----------|----------|--------|\n| CRITICAL | Money | E2E: processRefund() | services\u002Fuser.ts:120 | 20 | M |\n| HIGH | Security | Unit: validatePermissions() | middleware\u002Fauth.ts:45 | 18 | S |\n\n#### Domain: orders (src\u002Forders\u002F)\n\n| Severity | Category | Missing Test | Location | Priority | Effort |\n|----------|----------|--------------|----------|----------|--------|\n| CRITICAL | Money | E2E: applyDiscount() | services\u002Forder.ts:45 | 25 | M |\n| HIGH | Data | Integration: orderTransaction() | repositories\u002Forder.ts:78 | 16 | M |\n```\n\n## Worker Architecture\n\nEach worker:\n- Receives `contextStore` with testing best practices\n- Receives `testFilesMetadata` with test file list (tagged with `type: \"automated\"|\"manual\"`)\n- Workers 1-5 (ln-631..ln-635) focus on automated tests; worker 6 (ln-636) focuses on manual tests\n- Loads full test file contents when analyzing\n- Returns structured JSON with category findings\n- Operates independently (failure in one doesn't block others)\n\n**Token Efficiency:**\n- Coordinator: metadata only (~1000 tokens)\n- Workers: full test file contents when needed (~5000-10000 tokens each)\n- Context gathered ONCE, shared with all workers\n\n## Critical Rules\n\n- **Two-stage delegation:** Global workers (5) + Domain-aware worker (ln-634 × N domains)\n- **Domain discovery:** Auto-detect domains from folder structure; fallback to global mode if \u003C2 domains\n- **Parallel execution:** All workers (global + domain-aware) run in PARALLEL\n- **Domain-grouped output:** Coverage Gaps findings grouped by domain (if domain_mode=\"domain-aware\")\n- **Delete > Archive:** Remove useless tests, don't comment out\n- **E2E baseline:** Every endpoint needs 2 E2E (positive + negative)\n- **Justify each test:** If can't explain Priority ≥15, remove it\n- **Trust frameworks:** Don't test Express\u002FPrisma\u002Fbcrypt behavior\n- **No performance\u002Fload tests:** Flag and REMOVE tests measuring throughput\u002Flatency\u002Fmemory (DevOps Epic territory)\n- **Code is truth:** If test contradicts code behavior, update test\n- **Language preservation:** Report in project's language (EN\u002FRU)\n\n## Phase 6: Append Results Log\n\n**MANDATORY READ:** Load `shared\u002Freferences\u002Fresults_log_pattern.md`\n\nAppend one row to `docs\u002Fproject\u002F.audit\u002Fresults_log.md` with: Skill=`ln-630`, Metric=`overall_score`, Scale=`0-10`, Score from Phase 5 aggregation. Calculate Delta vs previous `ln-630` row. Create file with header if missing. Rolling window: max 50 entries.\n\n## Phase 7: Cleanup Worker Files\n\n```bash\nrm -rf {output_dir}\n```\n\nDelete the dated output directory (`docs\u002Fproject\u002F.audit\u002Fln-630\u002F{YYYY-MM-DD}\u002F`). The consolidated report and results log already preserve all audit data.\n\n## Definition of Done\n\n- All test files discovered via Glob (automated + manual)\n- Manual test files tagged with `type: \"manual\"` in testFilesMetadata\n- Context gathered from testing best practices (MCP Ref\u002FContext7)\n- Domain discovery completed (domain_mode determined)\n- contextStore built with test metadata + domain info\n- Global workers (5) invoked in PARALLEL (ln-631, ln-632, ln-633, ln-635, ln-636)\n- Domain-aware worker (ln-634) invoked per domain in PARALLEL\n- All workers completed successfully (or reported errors)\n- Results aggregated with domain grouping (if domain_mode=\"domain-aware\")\n- Domain Coverage Summary built (if domain_mode=\"domain-aware\")\n- Compliance scores calculated (7 categories)\n- Keep\u002FRemove\u002FRefactor decisions for each test\n- Missing tests identified with Priority (grouped by domain if applicable)\n- Anti-patterns catalogued\n- Report written to `docs\u002Fproject\u002Ftest_audit.md`\n- Results log row appended to `docs\u002Fproject\u002F.audit\u002Fresults_log.md`\n- Worker output directory cleaned up after consolidation\n- Summary returned to user\n\n## Phase 8: Meta-Analysis\n\n**MANDATORY READ:** Load `shared\u002Freferences\u002Fmeta_analysis_protocol.md`\n\nSkill type: `review-coordinator` (workers only). Run after all phases complete. Output to chat using the `review-coordinator — workers only` format.\n\n## Reference Files\n\n- **Orchestrator lifecycle:** `shared\u002Freferences\u002Forchestrator_pattern.md`\n- **Risk-based testing methodology:** `shared\u002Freferences\u002Frisk_based_testing_guide.md`\n- **Task delegation pattern:** `shared\u002Freferences\u002Ftask_delegation_pattern.md`\n- **Domain mode pattern:** `shared\u002Freferences\u002Faudit_coordinator_domain_mode.md`\n- **Aggregation pattern:** `shared\u002Freferences\u002Faudit_coordinator_aggregation.md`\n- **MANDATORY READ:** `shared\u002Freferences\u002Fresearch_tool_fallback.md`\n\n## Related Skills\n\n- **Workers:**\n  - [ln-631-test-business-logic-auditor](..\u002Fln-631-test-business-logic-auditor\u002F) — Framework tests detection\n  - [ln-632-test-e2e-priority-auditor](..\u002Fln-632-test-e2e-priority-auditor\u002F) — E2E baseline validation\n  - [ln-633-test-value-auditor](..\u002Fln-633-test-value-auditor\u002F) — Usefulness Score calculation\n  - [ln-634-test-coverage-auditor](..\u002Fln-634-test-coverage-auditor\u002F) — Coverage gaps identification\n  - [ln-635-test-isolation-auditor](..\u002Fln-635-test-isolation-auditor\u002F) — Isolation + Anti-Patterns\n  - [ln-636-manual-test-auditor](..\u002Fln-636-manual-test-auditor\u002F) — Manual Test Quality\n\n- **Reference:**\n  - [..\u002Fshared\u002Freferences\u002Frisk_based_testing_guide.md](..\u002Fshared\u002Freferences\u002Frisk_based_testing_guide.md) — Risk-Based Testing Guide\n\n---\n**Version:** 4.0.0\n**Last Updated:** 2025-12-23\n",{"name":5,"license":15,"description":7,"allowed-tools":51},"Read, Grep, Glob, Bash, mcp__Ref, mcp__context7, Skill","main","fa638b97a18ff6d9f26cf0eaf3dfa123531bcc87","organized-skills\u002Fln-630-test-auditor",1,"https:\u002F\u002Fgithub.com\u002Flevalencia\u002Fagent-god-mode","https:\u002F\u002Fgithub.com\u002Flevalencia","https:\u002F\u002Fmedium.com\u002F@luisevalencia","Microsoft MVP - Artificial Intelligence\r\nMachine Learning Enthusiast\r\n","2026-05-02 06:55:36",{"source":8,"skillName":5,"commands":62,"prompt":72,"zipAvailable":73},[63,66,69],{"tool":64,"command":65},"npx","npx skills add levalencia\u002Fagent-god-mode --skill ln-630-test-auditor",{"tool":67,"command":68},"bunx","bunx skills add levalencia\u002Fagent-god-mode --skill ln-630-test-auditor",{"tool":70,"command":71},"pnpm","pnpm dlx skills add levalencia\u002Fagent-god-mode --skill ln-630-test-auditor","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Flevalencia\u002Fagent-god-mode\u002Fblob\u002Fmain\u002Forganized-skills\u002Fln-630-test-auditor\u002FSKILL.md",true,[75],{"path":76,"resourceType":77,"resourceTypeDesc":78,"sizeBytes":79,"sourceHtmlUrl":80},"DESIGN.md","REFERENCE","参考文档",1536,"https:\u002F\u002Fgithub.com\u002FTorchiaHub\u002FSkills\u002Fblob\u002Fmaster\u002F01-Inbox\u002Fdownloads\u002Fbergside-design-skills\u002F20260516T145411Z\u002Fsource\u002Fskills\u002Fflat\u002FDESIGN.md",[82,104,138,165,190,218],{"skillNo":83,"name":84,"nameZh":6,"description":85,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":86,"categories":87,"keywords":88,"publishedAt":46},"01M6EM8ES5M9J4S8N78NJST0YC","zarr-python","Chunked N-D arrays for cloud storage. Compressed arrays, parallel I\u002FO, S3\u002FGCS integration, NumPy\u002FDask\u002FXarray compatible, for large-scale scientific computing pipelines.","https:\u002F\u002Fgithub.com\u002Flevalencia\u002Fagent-god-mode\u002Fblob\u002Fmain\u002Forganized-skills\u002Fzarr-python\u002FSKILL.md",[],[89,90,91,92,93,94,95,96,97,98,99,100,101,102,103],"python","zarr python","storage","integration","s3","gcs","cloud","dask","parallel","pipelines","arrays","numpy","scientific computing","scale","scientific",{"skillNo":105,"name":106,"nameZh":6,"description":107,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":108,"categories":109,"keywords":119,"publishedAt":46},"01M6EM8AR6ZFKZ9YVW8TTG850Z","zabbix","Zabbix monitoring system automation via API and Python. Use when: (1) Managing hosts, templates, items, triggers, or host groups, (2) Automating monitoring configuration, (3) Sending data via Zabbix trapper\u002Fsender, (4) Querying historical data or events, (5) Bulk operations on Zabbix objects, (6) Maintenance window management, (7) User\u002Fpermission management","https:\u002F\u002Fgithub.com\u002Flevalencia\u002Fagent-god-mode\u002Fblob\u002Fmain\u002Forganized-skills\u002Fzabbix-api-skill\u002FSKILL.md",[110,113,114],{"categoryNo":111,"categoryName":112,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000010","后端与接口",{"categoryNo":24,"categoryName":25,"taxonomyType":21,"taxonomyTypeDesc":22},{"categoryNo":115,"categoryName":116,"taxonomyType":117,"taxonomyTypeDesc":118},"01JBSEEDCAT000000000000030","开发工程师","PROFESSION","适用职业",[106,89,120,121,122,123,124,125,126,127,128,129,130,131,132,133,134,135,136,137],"automation","window management","monitoring","data","templates","api","system","operations","use","maintenance","objects","permission","bulk operations","triggers","host","events","via","bulk",{"skillNo":139,"name":140,"nameZh":6,"description":141,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":142,"categories":143,"keywords":144,"publishedAt":46},"01M6EM6Q9JG846ECQY9A210A26","x-twitter-growth","X\u002FTwitter growth engine for building audience, crafting viral content, and analyzing engagement. Use when the user wants to grow on X\u002FTwitter, write tweets or threads, analyze their X profile, research competitors on X, plan a posting strategy, or optimize engagement. Complements social-content (generic multi-platform) with X-specific depth: algorithm mechanics, thread engineering, reply strategy, profile optimization, and competitive intelligence via web search.","https:\u002F\u002Fgithub.com\u002Flevalencia\u002Fagent-god-mode\u002Fblob\u002Fmain\u002Forganized-skills\u002Fx-twitter-growth\u002FSKILL.md",[],[145,146,147,148,149,150,151,152,153,154,155,156,157,158,159,160,161,162,163,164],"twitter","x twitter growth","growth","competitive intelligence","search","analyzing","plan","marketing","web search","competitors","analyze","write","optimize","social","intelligence","viral","growth engine","mechanics","grow","competitive",{"skillNo":166,"name":167,"nameZh":6,"description":168,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":169,"categories":170,"keywords":171,"publishedAt":46},"01M6EM3FQNPYNKPC4CV9TCVNGD","what-if-oracle","Run structured What-If scenario analysis with multi-branch possibility exploration. Use this skill when the user asks speculative questions like \"what if...\", \"what would happen if...\", \"what are the possibilities\", \"explore scenarios\", \"scenario analysis\", \"possibility space\", \"what could go wrong\", \"best case \u002F worst case\", \"risk analysis\", \"contingency planning\", \"strategic options\", or any question about uncertain futures. Also trigger when the user faces a fork-in-the-road decision, wants to stress-test an idea, or needs to think through consequences before committing.","https:\u002F\u002Fgithub.com\u002Flevalencia\u002Fagent-god-mode\u002Fblob\u002Fmain\u002Forganized-skills\u002Fwhat-if-oracle\u002FSKILL.md",[],[172,173,28,174,175,176,177,178,179,180,181,182,128,183,184,185,186,187,188,189],"oracle","what if oracle","planning","ux","futures","risk","analysis","explore","decision","branch","question","exploration","options","stress-test","strategies","trigger","case","multi",{"skillNo":191,"name":192,"nameZh":6,"description":193,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":194,"categories":195,"keywords":199,"publishedAt":46},"01M6EM08C06RGDYCJ86HAPK0FF","vercel-react-best-practices","React and Next.js performance optimization guidelines from Vercel Engineering. This skill should be used when writing, reviewing, or refactoring React\u002FNext.js code to ensure optimal performance patterns. Triggers on tasks involving React components, Next.js pages, data fetching, bundle optimization, or performance improvements.","https:\u002F\u002Fgithub.com\u002Flevalencia\u002Fagent-god-mode\u002Fblob\u002Fmain\u002Forganized-skills\u002Fvercel-react-best-practices\u002FSKILL.md",[196],{"categoryNo":197,"categoryName":198,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000009","前端开发",[200,201,202,203,204,205,206,207,208,209,210,211,212,123,213,214,215,216,217,133],"react","vercel react best practices","best practices","react best practices","vercel","writing","performance","components","react components","guidelines","tasks","code","Optimization","Next.js","refactoring","performance optimization","next","pages",{"skillNo":219,"name":220,"nameZh":6,"description":221,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":222,"categories":223,"keywords":234,"publishedAt":46},"01M6EM00S13326QM08DTM94J6Z","venue-templates","Access comprehensive LaTeX templates, formatting requirements, and submission guidelines for major scientific publication venues (Nature, Science, PLOS, IEEE, ACM), academic conferences (NeurIPS, ICML, CVPR, CHI), research posters, and grant proposals (NSF, NIH, DOE, DARPA). This skill should be used when preparing manuscripts for journal submission, conference papers, research posters, or grant proposals and need venue-specific formatting requirements and templates.","https:\u002F\u002Fgithub.com\u002Flevalencia\u002Fagent-god-mode\u002Fblob\u002Fmain\u002Forganized-skills\u002Fvenue-templates\u002FSKILL.md",[224,227,230,231],{"categoryNo":225,"categoryName":226,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000018","写作与文案",{"categoryNo":228,"categoryName":229,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000021","资料检索与研究",{"categoryNo":24,"categoryName":25,"taxonomyType":21,"taxonomyTypeDesc":22},{"categoryNo":232,"categoryName":233,"taxonomyType":117,"taxonomyTypeDesc":118},"01JBSEEDCAT000000000000036","内容创作者",[124,235,236,209,237,238,239,240,42,241,39,156,242,243,244,245,246,247,103,248],"venue templates","research","NeurIPS","ICML","LaTeX","science","access","edit","proposals","Academic","requirements","formatting","journal","chi"]