[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6EGESGQD10J8DC381CMY2FG":3,"skill-same:01M6EGESGQD10J8DC381CMY2FG":86},{"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":23,"publishedAt":42,"linkOnly":43,"markdownContent":44,"markdownBody":45,"frontMatter":46,"refName":47,"commitSha":48,"skillDirectory":49,"forksCount":50,"repositoryHtmlUrl":51,"repositoryHomepageUrl":6,"ownerHtmlUrl":52,"ownerBlogUrl":53,"ownerDescription":54,"updatedAt":55,"install":56,"resources":69},"01M6EGESGQD10J8DC381CMY2FG","ln-510-quality-coordinator",null,"Coordinates code quality: ln-511 metrics, ln-512 cleanup, inline agent review (Codex + Gemini), ln-513 regression, ln-514 log analysis. Returns quality_verdict + aggregated results.","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-510-quality-coordinator\u002FSKILL.md",[18],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000023","Skill与智能体开发","SCENARIO","使用场景",[24,25,26,27,28,29,30,31,32,33,34,35,36,37,38,39,40,41],"quality","ln 510 quality coordinator","codex","code quality","cleanup","code","metrics","analysis","regression","review","returns","results","log analysis","log","coordinates","agent review","verdict","gemini","2026-11-10 10:12:30",false,"---\nname: ln-510-quality-coordinator\ndescription: \"Coordinates code quality: ln-511 metrics, ln-512 cleanup, inline agent review (Codex + Gemini), ln-513 regression, ln-514 log analysis. Returns quality_verdict + aggregated results.\"\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# Quality Coordinator\n\nSequential coordinator for code quality pipeline. Invokes workers (ln-511 → ln-512 → ln-513 → ln-514), runs inline agent review in parallel with Phases 5-8, merges all results, and returns quality_verdict.\n\n## Inputs\n\n| Input | Required | Source | Description |\n|-------|----------|--------|-------------|\n| `storyId` | Yes | args, git branch, kanban, user | Story to process |\n\n**Resolution:** Story Resolution Chain.\n**Status filter:** To Review\n\n## Purpose & Scope\n- Invoke ln-511-code-quality-checker (metrics, MCP Ref, static analysis)\n- Invoke ln-512-tech-debt-cleaner (auto-fix safe findings from ln-511)\n- Run inline agent review (Codex + Gemini in parallel on cleaned code)\n- Run Criteria Validation (Story dependencies, AC-Task Coverage, DB Creation Principle)\n- Run linters from tech_stack.md\n- Invoke ln-513-regression-checker (test suite after all changes)\n- Invoke ln-514-test-log-analyzer (classify errors, assess log quality)\n- Return quality_verdict + aggregated results\n- Calculate quality_verdict per normalization matrix + `references\u002Fgate_levels.md`\n\n## When to Use\n- **Invoked by ln-500-story-quality-gate** Phase 2\n- All implementation tasks in Story status = Done\n\n## Workflow\n\n### Phase 0: Resolve Inputs\n\n**MANDATORY READ:** Load `shared\u002Freferences\u002Finput_resolution_pattern.md`\n\n1. **Resolve storyId:** Run Story Resolution Chain per guide (status filter: [To Review]).\n\n### Phase 1: Discovery\n\n1) Auto-discover team\u002Fconfig from `docs\u002Ftasks\u002Fkanban_board.md`\n2) Load Story + task metadata from Linear (no full descriptions)\n3) **Collect git scope** (sets `changed_files[]` for ln-511 via coordinator context):\n   **MANDATORY READ:** Load `shared\u002Freferences\u002Fgit_scope_detection.md`\n   Run algorithm from guide → build `changed_files[]`\n\n**Fast-track mode:** When invoked with `--fast-track` flag (readiness 10\u002F10), run Phase 2 with `--skip-mcp-ref` (metrics + static only, no MCP Ref), skip Phase 3 (ln-512), Phase 4 (agent review). Run Phase 5 (criteria), Phase 6 (linters), Phase 7 (ln-513), Phase 8 (ln-514).\n\n### Phase 2: Code Quality (delegate to ln-511 — ALWAYS runs)\n\n> **MANDATORY STEP:** ln-511 invocation required in ALL modes.\n> **Full gate:** ln-511 runs everything (metrics + MCP Ref + static analysis).\n> **Fast-track:** ln-511 runs with `--skip-mcp-ref` (metrics + static analysis only — catches complexity, DRY, dead code without expensive MCP Ref calls).\n\n1) **Invoke ln-511-code-quality-checker** via Skill tool\n   - Full: ln-511 runs code metrics, MCP Ref validation (OPT\u002FBP\u002FPERF), static analysis\n   - Fast-track: ln-511 runs code metrics + static analysis only (skips OPT-, BP-, PERF- MCP Ref checks)\n   - Returns verdict (PASS\u002FCONCERNS\u002FISSUES_FOUND) + code_quality_score + issues list\n2) **If ln-511 returns ISSUES_FOUND** -> aggregate issues, continue (ln-500 decides action)\n\n**Invocation:**\n```\n# Full gate:\nSkill(skill: \"ln-511-code-quality-checker\", args: \"{storyId}\")\n# Fast-track:\nSkill(skill: \"ln-511-code-quality-checker\", args: \"{storyId} --skip-mcp-ref\")\n```\n\n### Phase 3: Tech Debt Cleanup (delegate to ln-512 — SKIP if --fast-track)\n\n> **MANDATORY STEP (full gate):** ln-512 invocation required. Safe auto-fixes only (confidence >=90%).\n> **Fast-track:** SKIP this phase.\n\n1) **Invoke ln-512-tech-debt-cleaner** via Skill tool\n   - ln-512 consumes findings from ln-511 output (passed via coordinator context)\n   - Filters to auto-fixable categories (unused imports, dead code, deprecated aliases)\n   - Applies safe fixes, verifies build integrity, creates commit\n2) **If ln-512 returns BUILD_FAILED** -> all changes reverted, aggregate issue, continue\n\n**Invocation:**\n```\nSkill(skill: \"ln-512-tech-debt-cleaner\", args: \"{storyId}\")\n```\n\n### Phase 4: Agent Review Launch (SKIP if --fast-track)\n\n> **MANDATORY STEP (full gate):** Launches agents in background, results merged in Phase 9.\n> **Fast-track:** SKIP this phase.\n\n**MANDATORY READ:** Load `shared\u002Freferences\u002Fagent_review_workflow.md`, `shared\u002Freferences\u002Fagent_delegation_pattern.md`\n\n4a) **Health Check** (per shared workflow \"Step: Health Check\"):\n    - Read `docs\u002Fenvironment_state.json` → exclude agents with `disabled: true`\n    - Run `python shared\u002Fagents\u002Fagent_runner.py --health-check` for remaining agents\n    - If 0 agents → agent review SKIPPED, go to Phase 5\n4b) **Get references:** `get_issue(storyId)` + `list_issues(parent=storyId, status=Done)` (exclude test tasks)\n4c) **Build prompt:** Assemble from `shared\u002Fagents\u002Fprompt_templates\u002Freview_base.md` + `modes\u002Fcode.md` (per shared workflow \"Step: Build Prompt\"), replace `{story_ref}`, `{task_refs}`. Save to `.agent-review\u002F{identifier}_codereview_prompt.md`\n4d) **Launch BOTH agents** as background tasks (per shared workflow) + **Load Review Memory**\n    → Continue to Phase 5 (Criteria Validation), Phase 6 (Linters), Phase 7 (Regression), Phase 8 (Log Analysis) while agents work\n\n### Phase 5: Criteria Validation\n\n**MANDATORY READ:** Load `references\u002Fcriteria_validation.md`\n\n| Check | Description | Fail Action |\n|-------|-------------|-------------|\n| #1 Story Dependencies | No forward deps within Epic | [DEP-] issue |\n| #2 AC-Task Coverage | STRONG\u002FWEAK\u002FMISSING scoring | [COV-]\u002F[BUG-] issue |\n| #3 DB Creation Principle | Schema scope matches Story | [DB-] issue |\n\n### Phase 6: Linters\n**MANDATORY READ:** `shared\u002Freferences\u002Fci_tool_detection.md` (Discovery Hierarchy + Command Registry)\n\n1) Detect lint\u002Ftypecheck commands per ci_tool_detection.md discovery hierarchy\n2) Run all detected checks (timeouts per guide: 2min linters, 5min typecheck)\n3) **If any check fails** -> aggregate issues, continue\n\n### Phase 7: Regression Tests (delegate to ln-513)\n\n1) **Invoke ln-513-regression-checker** via Skill tool\n   - Runs full test suite, reports PASS\u002FFAIL\n   - Runs AFTER ln-512 changes to verify nothing broke\n2) **If regression FAIL** -> aggregate issues, continue\n\n**Invocation:**\n```\nSkill(skill: \"ln-513-regression-checker\", args: \"{storyId}\")\n```\n\n### Phase 8: Test Log Analysis (delegate to ln-514 — runs after ln-513)\n\n1) **Invoke ln-514-test-log-analyzer** via Skill tool with context instructions\n   - Only Real Bugs affect quality verdict; log quality issues are informational\n2) **If ln-514 returns REAL_BUGS_FOUND** -> aggregate issues, continue\n3) **If ln-514 returns NO_LOG_SOURCES** -> status ignored, continue\n4) Post ln-514 report as Linear comment on story\n\n**Invocation:**\n```\nSkill(skill: \"ln-514-test-log-analyzer\", args: \"review logs since test run start, expected errors from negative test cases\")\n```\n\n### Phase 9: Agent Merge (runs after Phase 8, when agent results arrive — SKIP if --fast-track or agents SKIPPED)\n\n**MANDATORY READ:** Load `shared\u002Freferences\u002Fagent_review_workflow.md` (Critical Verification + Debate), `shared\u002Freferences\u002Fagent_review_memory.md`\n\n9a) **Wait for agent results** — read result files as they arrive (process-as-arrive pattern)\n9b) **Critical Verification + Debate** per shared workflow — Claude evaluates each suggestion on merits\n9c) **Merge accepted suggestions** into issues list (SEC-, PERF-, MNT-, ARCH-, BP-, OPT-)\n    - If `area=security` or `area=correctness` → escalate aggregate to CONCERNS\n9d) **Save review summary** to `.agent-review\u002Freview_history.md`\n\n### Phase 10: Calculate Verdict + Return Results\n\n**MANDATORY READ:** Load `references\u002Fgate_levels.md`\n\n#### Step 10.1: Normalize Component Results\n\nMap each component status to FAIL\u002FCONCERN\u002Fignored using this matrix:\n\n| Component | Status | Maps To | Penalty |\n|-----------|--------|---------|---------|\n| quality_check | PASS | -- | 0 |\n| quality_check | CONCERNS | CONCERN | -10 |\n| quality_check | ISSUES_FOUND | FAIL | -20 |\n| criteria_validation | PASS | -- | 0 |\n| criteria_validation | CONCERNS | CONCERN | -10 |\n| criteria_validation | FAIL | FAIL | -20 |\n| linters | PASS | -- | 0 |\n| linters | FAIL | FAIL | -20 |\n| regression | PASS | -- | 0 |\n| regression | FAIL | FAIL | -20 |\n| tech_debt_cleanup | CLEANED | -- | 0 |\n| tech_debt_cleanup | NOTHING_TO_CLEAN | -- | 0 |\n| tech_debt_cleanup | BUILD_FAILED | FAIL | -20 |\n| tech_debt_cleanup | SKIPPED | ignored | 0 |\n| agent_review | CODE_ACCEPTABLE | -- | 0 |\n| agent_review | SUGGESTIONS (security\u002Fcorrectness) | CONCERN | -10 |\n| agent_review | SKIPPED | ignored | 0 |\n| log_analysis | CLEAN | -- | 0 |\n| log_analysis | WARNINGS_ONLY | -- | 0 |\n| log_analysis | REAL_BUGS_FOUND | FAIL | -20 |\n| log_analysis | SKIPPED \u002F NO_LOG_SOURCES | ignored | 0 |\n\n#### Step 10.2: Calculate Quality Verdict\n\n```\nfail_count = count of components mapped to FAIL\nconcern_count = count of components mapped to CONCERN\nquality_score = 100 - (20 * fail_count) - (10 * concern_count)\n\n# Fast-fail override: any FAIL -> verdict is FAIL regardless of score\nIF fail_count > 0:\n  quality_verdict = FAIL\nELSE IF quality_score >= 90:\n  quality_verdict = PASS\nELSE IF quality_score >= 70:\n  quality_verdict = CONCERNS\nELSE:\n  quality_verdict = FAIL\n```\n\n#### Step 10.3: Return Results\n\n```yaml\nquality_verdict: PASS | CONCERNS | FAIL\nquality_score: {0-100}\nfail_count: {N}\nconcern_count: {N}\nignored_components: [tech_debt_cleanup, agent_review]  # only if SKIPPED\nquality_check: PASS | CONCERNS | ISSUES_FOUND\ncode_quality_score: {0-100}\nagent_review: CODE_ACCEPTABLE | SUGGESTIONS | SKIPPED\ncriteria_validation: PASS | CONCERNS | FAIL\nlinters: PASS | FAIL\ntech_debt_cleanup: CLEANED | NOTHING_TO_CLEAN | BUILD_FAILED | SKIPPED\nregression: PASS | FAIL\nlog_analysis: CLEAN | WARNINGS_ONLY | REAL_BUGS_FOUND | SKIPPED\nissues:\n  - {id: \"SEC-001\", severity: high, finding: \"...\", source: \"ln-511\"}\n  - {id: \"OPT-001\", severity: medium, finding: \"...\", source: \"agent-review\"}\n  - {id: \"DEP-001\", severity: medium, finding: \"...\", source: \"criteria\"}\n  - {id: \"LINT-001\", severity: low, finding: \"...\", source: \"linters\"}\n```\n\n**TodoWrite format (mandatory):**\n```\n- Invoke ln-511-code-quality-checker (in_progress)\n- Invoke ln-512-tech-debt-cleaner (pending)\n- Launch agent review (background) (pending)\n- Criteria Validation (Story deps, AC coverage, DB schema) (pending)\n- Run linters from tech_stack.md (pending)\n- Invoke ln-513-regression-checker (pending)\n- Invoke ln-514-test-log-analyzer (pending)\n- Merge agent review results (pending)\n- Calculate quality_verdict + return results (pending)\n```\n\n## Worker Invocation (MANDATORY)\n\n| Phase | Worker | Context |\n|-------|--------|---------|\n| 2 | ln-511-code-quality-checker | Shared (Skill tool) — code metrics, MCP Ref, static analysis |\n| 3 | ln-512-tech-debt-cleaner | Shared (Skill tool) — auto-fix safe findings from ln-511 |\n| 4 | Inline agent review (Codex + Gemini) | Background — launched after ln-512, merged in Phase 9 |\n| 7 | ln-513-regression-checker | Shared (Skill tool) — full test suite after all changes |\n| 8 | ln-514-test-log-analyzer | Shared (Skill tool) — error classification + log quality after ln-513 |\n\n**All workers:** Invoke via Skill tool — workers see coordinator context. Agent review runs inline (no Skill delegation).\n\n**Anti-Patterns:**\n- Running mypy, ruff, pytest directly instead of invoking ln-511\u002Fln-513\n- Skipping agent health check or not launching agents in Phase 4\n- Auto-fixing code directly instead of invoking ln-512\n- Marking steps as completed without invoking the actual skill\n- Skipping verdict calculation or returning raw results without quality_verdict\n\n## Critical Rules\n- Always calculate quality_verdict per normalization matrix + gate_levels.md. Final gate_verdict is ln-500's responsibility (includes tests, NFR, waivers)\n- Single source of truth: rely on Linear metadata for tasks\n- Language preservation in comments (EN\u002FRU)\n- Do not create tasks or change statuses; ln-500 decides next actions\n\n## Definition of Done\n- ln-511 invoked (ALWAYS — full or `--skip-mcp-ref` in fast-track), code quality score returned\n- ln-512 invoked (or skipped if --fast-track), tech debt cleanup results returned\n- Agent review executed inline (or skipped if --fast-track), results merged in Phase 9\n- Criteria Validation completed (3 checks)\n- Linters executed\n- ln-513 invoked, regression results returned\n- ln-514 invoked, log analysis results returned (or SKIPPED\u002FNO_LOG_SOURCES)\n- quality_verdict calculated + aggregated results returned\n\n## Phase 11: Meta-Analysis\n\n**MANDATORY READ:** Load `shared\u002Freferences\u002Fmeta_analysis_protocol.md`\n\nSkill type: `review-coordinator` (with agents). Run after all phases complete. Output to chat using the `review-coordinator — with agents` format.\n\n## Reference Files\n- Criteria Validation: `references\u002Fcriteria_validation.md`\n- Gate levels: `references\u002Fgate_levels.md`\n- Workers: `..\u002Fln-511-code-quality-checker\u002FSKILL.md`, `..\u002Fln-512-tech-debt-cleaner\u002FSKILL.md`, `..\u002Fln-513-regression-checker\u002FSKILL.md`, `..\u002Fln-514-test-log-analyzer\u002FSKILL.md`\n- Agent review workflow: `shared\u002Freferences\u002Fagent_review_workflow.md`\n- Agent delegation pattern: `shared\u002Freferences\u002Fagent_delegation_pattern.md`\n- Agent review memory: `shared\u002Freferences\u002Fagent_review_memory.md`\n- Review templates: `shared\u002Fagents\u002Fprompt_templates\u002Freview_base.md` + `modes\u002Fcode.md`\n- Caller: `..\u002Fln-500-story-quality-gate\u002FSKILL.md`\n- Test planning (separate coordinator): `..\u002Fln-520-test-planner\u002FSKILL.md`\n- Tech stack\u002Flinters: `docs\u002Fproject\u002Ftech_stack.md`\n\n---\n**Version:** 7.0.0\n**Last Updated:** 2026-02-09\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# Quality Coordinator\n\nSequential coordinator for code quality pipeline. Invokes workers (ln-511 → ln-512 → ln-513 → ln-514), runs inline agent review in parallel with Phases 5-8, merges all results, and returns quality_verdict.\n\n## Inputs\n\n| Input | Required | Source | Description |\n|-------|----------|--------|-------------|\n| `storyId` | Yes | args, git branch, kanban, user | Story to process |\n\n**Resolution:** Story Resolution Chain.\n**Status filter:** To Review\n\n## Purpose & Scope\n- Invoke ln-511-code-quality-checker (metrics, MCP Ref, static analysis)\n- Invoke ln-512-tech-debt-cleaner (auto-fix safe findings from ln-511)\n- Run inline agent review (Codex + Gemini in parallel on cleaned code)\n- Run Criteria Validation (Story dependencies, AC-Task Coverage, DB Creation Principle)\n- Run linters from tech_stack.md\n- Invoke ln-513-regression-checker (test suite after all changes)\n- Invoke ln-514-test-log-analyzer (classify errors, assess log quality)\n- Return quality_verdict + aggregated results\n- Calculate quality_verdict per normalization matrix + `references\u002Fgate_levels.md`\n\n## When to Use\n- **Invoked by ln-500-story-quality-gate** Phase 2\n- All implementation tasks in Story status = Done\n\n## Workflow\n\n### Phase 0: Resolve Inputs\n\n**MANDATORY READ:** Load `shared\u002Freferences\u002Finput_resolution_pattern.md`\n\n1. **Resolve storyId:** Run Story Resolution Chain per guide (status filter: [To Review]).\n\n### Phase 1: Discovery\n\n1) Auto-discover team\u002Fconfig from `docs\u002Ftasks\u002Fkanban_board.md`\n2) Load Story + task metadata from Linear (no full descriptions)\n3) **Collect git scope** (sets `changed_files[]` for ln-511 via coordinator context):\n   **MANDATORY READ:** Load `shared\u002Freferences\u002Fgit_scope_detection.md`\n   Run algorithm from guide → build `changed_files[]`\n\n**Fast-track mode:** When invoked with `--fast-track` flag (readiness 10\u002F10), run Phase 2 with `--skip-mcp-ref` (metrics + static only, no MCP Ref), skip Phase 3 (ln-512), Phase 4 (agent review). Run Phase 5 (criteria), Phase 6 (linters), Phase 7 (ln-513), Phase 8 (ln-514).\n\n### Phase 2: Code Quality (delegate to ln-511 — ALWAYS runs)\n\n> **MANDATORY STEP:** ln-511 invocation required in ALL modes.\n> **Full gate:** ln-511 runs everything (metrics + MCP Ref + static analysis).\n> **Fast-track:** ln-511 runs with `--skip-mcp-ref` (metrics + static analysis only — catches complexity, DRY, dead code without expensive MCP Ref calls).\n\n1) **Invoke ln-511-code-quality-checker** via Skill tool\n   - Full: ln-511 runs code metrics, MCP Ref validation (OPT\u002FBP\u002FPERF), static analysis\n   - Fast-track: ln-511 runs code metrics + static analysis only (skips OPT-, BP-, PERF- MCP Ref checks)\n   - Returns verdict (PASS\u002FCONCERNS\u002FISSUES_FOUND) + code_quality_score + issues list\n2) **If ln-511 returns ISSUES_FOUND** -> aggregate issues, continue (ln-500 decides action)\n\n**Invocation:**\n```\n# Full gate:\nSkill(skill: \"ln-511-code-quality-checker\", args: \"{storyId}\")\n# Fast-track:\nSkill(skill: \"ln-511-code-quality-checker\", args: \"{storyId} --skip-mcp-ref\")\n```\n\n### Phase 3: Tech Debt Cleanup (delegate to ln-512 — SKIP if --fast-track)\n\n> **MANDATORY STEP (full gate):** ln-512 invocation required. Safe auto-fixes only (confidence >=90%).\n> **Fast-track:** SKIP this phase.\n\n1) **Invoke ln-512-tech-debt-cleaner** via Skill tool\n   - ln-512 consumes findings from ln-511 output (passed via coordinator context)\n   - Filters to auto-fixable categories (unused imports, dead code, deprecated aliases)\n   - Applies safe fixes, verifies build integrity, creates commit\n2) **If ln-512 returns BUILD_FAILED** -> all changes reverted, aggregate issue, continue\n\n**Invocation:**\n```\nSkill(skill: \"ln-512-tech-debt-cleaner\", args: \"{storyId}\")\n```\n\n### Phase 4: Agent Review Launch (SKIP if --fast-track)\n\n> **MANDATORY STEP (full gate):** Launches agents in background, results merged in Phase 9.\n> **Fast-track:** SKIP this phase.\n\n**MANDATORY READ:** Load `shared\u002Freferences\u002Fagent_review_workflow.md`, `shared\u002Freferences\u002Fagent_delegation_pattern.md`\n\n4a) **Health Check** (per shared workflow \"Step: Health Check\"):\n    - Read `docs\u002Fenvironment_state.json` → exclude agents with `disabled: true`\n    - Run `python shared\u002Fagents\u002Fagent_runner.py --health-check` for remaining agents\n    - If 0 agents → agent review SKIPPED, go to Phase 5\n4b) **Get references:** `get_issue(storyId)` + `list_issues(parent=storyId, status=Done)` (exclude test tasks)\n4c) **Build prompt:** Assemble from `shared\u002Fagents\u002Fprompt_templates\u002Freview_base.md` + `modes\u002Fcode.md` (per shared workflow \"Step: Build Prompt\"), replace `{story_ref}`, `{task_refs}`. Save to `.agent-review\u002F{identifier}_codereview_prompt.md`\n4d) **Launch BOTH agents** as background tasks (per shared workflow) + **Load Review Memory**\n    → Continue to Phase 5 (Criteria Validation), Phase 6 (Linters), Phase 7 (Regression), Phase 8 (Log Analysis) while agents work\n\n### Phase 5: Criteria Validation\n\n**MANDATORY READ:** Load `references\u002Fcriteria_validation.md`\n\n| Check | Description | Fail Action |\n|-------|-------------|-------------|\n| #1 Story Dependencies | No forward deps within Epic | [DEP-] issue |\n| #2 AC-Task Coverage | STRONG\u002FWEAK\u002FMISSING scoring | [COV-]\u002F[BUG-] issue |\n| #3 DB Creation Principle | Schema scope matches Story | [DB-] issue |\n\n### Phase 6: Linters\n**MANDATORY READ:** `shared\u002Freferences\u002Fci_tool_detection.md` (Discovery Hierarchy + Command Registry)\n\n1) Detect lint\u002Ftypecheck commands per ci_tool_detection.md discovery hierarchy\n2) Run all detected checks (timeouts per guide: 2min linters, 5min typecheck)\n3) **If any check fails** -> aggregate issues, continue\n\n### Phase 7: Regression Tests (delegate to ln-513)\n\n1) **Invoke ln-513-regression-checker** via Skill tool\n   - Runs full test suite, reports PASS\u002FFAIL\n   - Runs AFTER ln-512 changes to verify nothing broke\n2) **If regression FAIL** -> aggregate issues, continue\n\n**Invocation:**\n```\nSkill(skill: \"ln-513-regression-checker\", args: \"{storyId}\")\n```\n\n### Phase 8: Test Log Analysis (delegate to ln-514 — runs after ln-513)\n\n1) **Invoke ln-514-test-log-analyzer** via Skill tool with context instructions\n   - Only Real Bugs affect quality verdict; log quality issues are informational\n2) **If ln-514 returns REAL_BUGS_FOUND** -> aggregate issues, continue\n3) **If ln-514 returns NO_LOG_SOURCES** -> status ignored, continue\n4) Post ln-514 report as Linear comment on story\n\n**Invocation:**\n```\nSkill(skill: \"ln-514-test-log-analyzer\", args: \"review logs since test run start, expected errors from negative test cases\")\n```\n\n### Phase 9: Agent Merge (runs after Phase 8, when agent results arrive — SKIP if --fast-track or agents SKIPPED)\n\n**MANDATORY READ:** Load `shared\u002Freferences\u002Fagent_review_workflow.md` (Critical Verification + Debate), `shared\u002Freferences\u002Fagent_review_memory.md`\n\n9a) **Wait for agent results** — read result files as they arrive (process-as-arrive pattern)\n9b) **Critical Verification + Debate** per shared workflow — Claude evaluates each suggestion on merits\n9c) **Merge accepted suggestions** into issues list (SEC-, PERF-, MNT-, ARCH-, BP-, OPT-)\n    - If `area=security` or `area=correctness` → escalate aggregate to CONCERNS\n9d) **Save review summary** to `.agent-review\u002Freview_history.md`\n\n### Phase 10: Calculate Verdict + Return Results\n\n**MANDATORY READ:** Load `references\u002Fgate_levels.md`\n\n#### Step 10.1: Normalize Component Results\n\nMap each component status to FAIL\u002FCONCERN\u002Fignored using this matrix:\n\n| Component | Status | Maps To | Penalty |\n|-----------|--------|---------|---------|\n| quality_check | PASS | -- | 0 |\n| quality_check | CONCERNS | CONCERN | -10 |\n| quality_check | ISSUES_FOUND | FAIL | -20 |\n| criteria_validation | PASS | -- | 0 |\n| criteria_validation | CONCERNS | CONCERN | -10 |\n| criteria_validation | FAIL | FAIL | -20 |\n| linters | PASS | -- | 0 |\n| linters | FAIL | FAIL | -20 |\n| regression | PASS | -- | 0 |\n| regression | FAIL | FAIL | -20 |\n| tech_debt_cleanup | CLEANED | -- | 0 |\n| tech_debt_cleanup | NOTHING_TO_CLEAN | -- | 0 |\n| tech_debt_cleanup | BUILD_FAILED | FAIL | -20 |\n| tech_debt_cleanup | SKIPPED | ignored | 0 |\n| agent_review | CODE_ACCEPTABLE | -- | 0 |\n| agent_review | SUGGESTIONS (security\u002Fcorrectness) | CONCERN | -10 |\n| agent_review | SKIPPED | ignored | 0 |\n| log_analysis | CLEAN | -- | 0 |\n| log_analysis | WARNINGS_ONLY | -- | 0 |\n| log_analysis | REAL_BUGS_FOUND | FAIL | -20 |\n| log_analysis | SKIPPED \u002F NO_LOG_SOURCES | ignored | 0 |\n\n#### Step 10.2: Calculate Quality Verdict\n\n```\nfail_count = count of components mapped to FAIL\nconcern_count = count of components mapped to CONCERN\nquality_score = 100 - (20 * fail_count) - (10 * concern_count)\n\n# Fast-fail override: any FAIL -> verdict is FAIL regardless of score\nIF fail_count > 0:\n  quality_verdict = FAIL\nELSE IF quality_score >= 90:\n  quality_verdict = PASS\nELSE IF quality_score >= 70:\n  quality_verdict = CONCERNS\nELSE:\n  quality_verdict = FAIL\n```\n\n#### Step 10.3: Return Results\n\n```yaml\nquality_verdict: PASS | CONCERNS | FAIL\nquality_score: {0-100}\nfail_count: {N}\nconcern_count: {N}\nignored_components: [tech_debt_cleanup, agent_review]  # only if SKIPPED\nquality_check: PASS | CONCERNS | ISSUES_FOUND\ncode_quality_score: {0-100}\nagent_review: CODE_ACCEPTABLE | SUGGESTIONS | SKIPPED\ncriteria_validation: PASS | CONCERNS | FAIL\nlinters: PASS | FAIL\ntech_debt_cleanup: CLEANED | NOTHING_TO_CLEAN | BUILD_FAILED | SKIPPED\nregression: PASS | FAIL\nlog_analysis: CLEAN | WARNINGS_ONLY | REAL_BUGS_FOUND | SKIPPED\nissues:\n  - {id: \"SEC-001\", severity: high, finding: \"...\", source: \"ln-511\"}\n  - {id: \"OPT-001\", severity: medium, finding: \"...\", source: \"agent-review\"}\n  - {id: \"DEP-001\", severity: medium, finding: \"...\", source: \"criteria\"}\n  - {id: \"LINT-001\", severity: low, finding: \"...\", source: \"linters\"}\n```\n\n**TodoWrite format (mandatory):**\n```\n- Invoke ln-511-code-quality-checker (in_progress)\n- Invoke ln-512-tech-debt-cleaner (pending)\n- Launch agent review (background) (pending)\n- Criteria Validation (Story deps, AC coverage, DB schema) (pending)\n- Run linters from tech_stack.md (pending)\n- Invoke ln-513-regression-checker (pending)\n- Invoke ln-514-test-log-analyzer (pending)\n- Merge agent review results (pending)\n- Calculate quality_verdict + return results (pending)\n```\n\n## Worker Invocation (MANDATORY)\n\n| Phase | Worker | Context |\n|-------|--------|---------|\n| 2 | ln-511-code-quality-checker | Shared (Skill tool) — code metrics, MCP Ref, static analysis |\n| 3 | ln-512-tech-debt-cleaner | Shared (Skill tool) — auto-fix safe findings from ln-511 |\n| 4 | Inline agent review (Codex + Gemini) | Background — launched after ln-512, merged in Phase 9 |\n| 7 | ln-513-regression-checker | Shared (Skill tool) — full test suite after all changes |\n| 8 | ln-514-test-log-analyzer | Shared (Skill tool) — error classification + log quality after ln-513 |\n\n**All workers:** Invoke via Skill tool — workers see coordinator context. Agent review runs inline (no Skill delegation).\n\n**Anti-Patterns:**\n- Running mypy, ruff, pytest directly instead of invoking ln-511\u002Fln-513\n- Skipping agent health check or not launching agents in Phase 4\n- Auto-fixing code directly instead of invoking ln-512\n- Marking steps as completed without invoking the actual skill\n- Skipping verdict calculation or returning raw results without quality_verdict\n\n## Critical Rules\n- Always calculate quality_verdict per normalization matrix + gate_levels.md. Final gate_verdict is ln-500's responsibility (includes tests, NFR, waivers)\n- Single source of truth: rely on Linear metadata for tasks\n- Language preservation in comments (EN\u002FRU)\n- Do not create tasks or change statuses; ln-500 decides next actions\n\n## Definition of Done\n- ln-511 invoked (ALWAYS — full or `--skip-mcp-ref` in fast-track), code quality score returned\n- ln-512 invoked (or skipped if --fast-track), tech debt cleanup results returned\n- Agent review executed inline (or skipped if --fast-track), results merged in Phase 9\n- Criteria Validation completed (3 checks)\n- Linters executed\n- ln-513 invoked, regression results returned\n- ln-514 invoked, log analysis results returned (or SKIPPED\u002FNO_LOG_SOURCES)\n- quality_verdict calculated + aggregated results returned\n\n## Phase 11: Meta-Analysis\n\n**MANDATORY READ:** Load `shared\u002Freferences\u002Fmeta_analysis_protocol.md`\n\nSkill type: `review-coordinator` (with agents). Run after all phases complete. Output to chat using the `review-coordinator — with agents` format.\n\n## Reference Files\n- Criteria Validation: `references\u002Fcriteria_validation.md`\n- Gate levels: `references\u002Fgate_levels.md`\n- Workers: `..\u002Fln-511-code-quality-checker\u002FSKILL.md`, `..\u002Fln-512-tech-debt-cleaner\u002FSKILL.md`, `..\u002Fln-513-regression-checker\u002FSKILL.md`, `..\u002Fln-514-test-log-analyzer\u002FSKILL.md`\n- Agent review workflow: `shared\u002Freferences\u002Fagent_review_workflow.md`\n- Agent delegation pattern: `shared\u002Freferences\u002Fagent_delegation_pattern.md`\n- Agent review memory: `shared\u002Freferences\u002Fagent_review_memory.md`\n- Review templates: `shared\u002Fagents\u002Fprompt_templates\u002Freview_base.md` + `modes\u002Fcode.md`\n- Caller: `..\u002Fln-500-story-quality-gate\u002FSKILL.md`\n- Test planning (separate coordinator): `..\u002Fln-520-test-planner\u002FSKILL.md`\n- Tech stack\u002Flinters: `docs\u002Fproject\u002Ftech_stack.md`\n\n---\n**Version:** 7.0.0\n**Last Updated:** 2026-02-09\n",{"name":5,"license":15,"description":7},"main","fa638b97a18ff6d9f26cf0eaf3dfa123531bcc87","organized-skills\u002Fln-510-quality-coordinator",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":57,"prompt":67,"zipAvailable":68},[58,61,64],{"tool":59,"command":60},"npx","npx skills add levalencia\u002Fagent-god-mode --skill ln-510-quality-coordinator",{"tool":62,"command":63},"bunx","bunx skills add levalencia\u002Fagent-god-mode --skill ln-510-quality-coordinator",{"tool":65,"command":66},"pnpm","pnpm dlx skills add levalencia\u002Fagent-god-mode --skill ln-510-quality-coordinator","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Flevalencia\u002Fagent-god-mode\u002Fblob\u002Fmain\u002Forganized-skills\u002Fln-510-quality-coordinator\u002FSKILL.md",true,[70,76,82],{"path":71,"resourceType":72,"resourceTypeDesc":73,"sizeBytes":74,"sourceHtmlUrl":75},"customize.toml","OTHER","其他",1718,"https:\u002F\u002Fgithub.com\u002FdevelopAgent\u002Fbmad-start\u002Fblob\u002Fmain\u002F.roo\u002Fskills\u002Fbmad-cis-agent-innovation-strategist\u002Fcustomize.toml",{"path":77,"resourceType":78,"resourceTypeDesc":79,"sizeBytes":80,"sourceHtmlUrl":81},"references\u002Fcriteria_validation.md","REFERENCE","参考文档",6148,"https:\u002F\u002Fgithub.com\u002Flevalencia\u002Fagent-god-mode\u002Fblob\u002Fmain\u002Forganized-skills\u002Fln-510-quality-coordinator\u002Freferences\u002Fcriteria_validation.md",{"path":83,"resourceType":78,"resourceTypeDesc":79,"sizeBytes":84,"sourceHtmlUrl":85},"references\u002Fgate_levels.md",2925,"https:\u002F\u002Fgithub.com\u002Flevalencia\u002Fagent-god-mode\u002Fblob\u002Fmain\u002Forganized-skills\u002Fln-510-quality-coordinator\u002Freferences\u002Fgate_levels.md",[87,109,143,170,195,222],{"skillNo":88,"name":89,"nameZh":6,"description":90,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":91,"categories":92,"keywords":93,"publishedAt":42},"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",[],[94,95,96,97,98,99,100,101,102,103,104,105,106,107,108],"python","zarr python","storage","integration","s3","gcs","cloud","dask","parallel","pipelines","arrays","numpy","scientific computing","scale","scientific",{"skillNo":110,"name":111,"nameZh":6,"description":112,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":113,"categories":114,"keywords":124,"publishedAt":42},"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",[115,118,119],{"categoryNo":116,"categoryName":117,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000010","后端与接口",{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},{"categoryNo":120,"categoryName":121,"taxonomyType":122,"taxonomyTypeDesc":123},"01JBSEEDCAT000000000000030","开发工程师","PROFESSION","适用职业",[111,94,125,126,127,128,129,130,131,132,133,134,135,136,137,138,139,140,141,142],"automation","window management","monitoring","data","templates","api","system","operations","use","maintenance","objects","permission","bulk operations","triggers","host","events","via","bulk",{"skillNo":144,"name":145,"nameZh":6,"description":146,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":147,"categories":148,"keywords":149,"publishedAt":42},"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",[],[150,151,152,153,154,155,156,157,158,159,160,161,162,163,164,165,166,167,168,169],"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":171,"name":172,"nameZh":6,"description":173,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":174,"categories":175,"keywords":176,"publishedAt":42},"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",[],[177,178,179,180,181,182,183,31,184,185,186,187,133,188,189,190,191,192,193,194],"oracle","what if oracle","test","planning","ux","futures","risk","explore","decision","branch","question","exploration","options","stress-test","strategies","trigger","case","multi",{"skillNo":196,"name":197,"nameZh":6,"description":198,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":199,"categories":200,"keywords":204,"publishedAt":42},"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",[201],{"categoryNo":202,"categoryName":203,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000009","前端开发",[205,206,207,208,209,210,211,212,213,214,215,29,216,128,217,218,219,220,221,138],"react","vercel react best practices","best practices","react best practices","vercel","writing","performance","components","react components","guidelines","tasks","Optimization","Next.js","refactoring","performance optimization","next","pages",{"skillNo":223,"name":224,"nameZh":6,"description":225,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":226,"categories":227,"keywords":238,"publishedAt":42},"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",[228,231,234,235],{"categoryNo":229,"categoryName":230,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000018","写作与文案",{"categoryNo":232,"categoryName":233,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000021","资料检索与研究",{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},{"categoryNo":236,"categoryName":237,"taxonomyType":122,"taxonomyTypeDesc":123},"01JBSEEDCAT000000000000036","内容创作者",[129,239,240,214,241,242,243,244,245,246,247,161,248,249,250,251,252,253,108,254],"venue templates","research","NeurIPS","ICML","LaTeX","science","Bash","access","read","edit","proposals","Academic","requirements","formatting","journal","chi"]