[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M75M8MKXR3VZTPYWAW13TPZP":3,"skill-same:01M75M8MKXR3VZTPYWAW13TPZP":70},{"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":18,"publishedAt":19,"linkOnly":20,"markdownContent":21,"markdownBody":22,"frontMatter":23,"refName":47,"commitSha":48,"skillDirectory":49,"forksCount":50,"repositoryHtmlUrl":51,"repositoryHomepageUrl":6,"ownerHtmlUrl":52,"ownerBlogUrl":53,"ownerDescription":54,"updatedAt":55,"install":56,"resources":69},"01M75M8MKXR3VZTPYWAW13TPZP","review-orchestrator",null,"Get multiple perspectives on your work — coordinate reviews across cognitive modes","javimosch\u002Fopen-claw-skills","javimosch","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F12900508?v=4","01M6D3F2AS6PV75ET9PZ1QGP8J","Javier Leandro Arancibia","01M75B8NCTAJG9WH5YNZH7C3D8",0,"MIT","https:\u002F\u002Fgithub.com\u002Fjavimosch\u002Fopen-claw-skills\u002Fblob\u002Fmain\u002Fskills\u002Fleegitw\u002Freview-orchestrator\u002FSKILL.md",[],[],"2026-11-12 13:55:43",false,"---\nname: review-orchestrator\nversion: 1.5.0\ndescription: Get multiple perspectives on your work — coordinate reviews across cognitive modes\nauthor: Live Neon \u003Ccontact@liveneon.dev>\nhomepage: https:\u002F\u002Fgithub.com\u002Flive-neon\u002Fskills\u002Ftree\u002Fmain\u002Fagentic\u002Freview-orchestrator\nrepository: leegitw\u002Freview-orchestrator\nlicense: MIT\ntags: [agentic, review, orchestration, multi-perspective, code-review, quality, twin-review, feedback]\nlayer: review\nstatus: active\nalias: ro\nmetadata:\n  openclaw:\n    requires:\n      config:\n        - .openclaw\u002Freview-orchestrator.yaml\n        - .claude\u002Freview-orchestrator.yaml\n      workspace:\n        - docs\u002Freviews\u002F\n---\n\n# review-orchestrator (審査)\n\nUnified skill for selecting review types, spawning multi-perspective and cognitive review agents,\nand managing quality gates. Consolidates 5 granular skills into a single review system.\n\n**Trigger**: レビュー要求 (review requested)\n\n**Source skills**: twin-review, cognitive-review, review-selector, staged-quality-gate, prompt-normalizer\n\n## Installation\n\n```bash\nopenclaw install leegitw\u002Freview-orchestrator\n```\n\n**Dependencies**:\n- `leegitw\u002Ffailure-memory` (for context)\n- `leegitw\u002Fcontext-verifier` (for file verification)\n\n```bash\n# Install with dependencies\nopenclaw install leegitw\u002Fcontext-verifier\nopenclaw install leegitw\u002Ffailure-memory\nopenclaw install leegitw\u002Freview-orchestrator\n```\n\n**Standalone usage**: Review orchestration works independently for multi-perspective reviews.\nIntegration with failure-memory enables automatic observation recording from review findings.\n\n**Data handling**: This skill operates within your agent's trust boundary. When triggered,\nit uses your agent's configured model for multi-perspective review orchestration. No external APIs\nor third-party services are called. Review results are written to `docs\u002Freviews\u002F` in your workspace.\n\n## What This Solves\n\nOne perspective has blind spots. This skill coordinates multiple review perspectives to catch what single-pass review misses:\n\n1. **Twin review** — technical and creative perspectives for balance\n2. **Cognitive modes** — analyzer (\"what conflicts\"), architect (\"how to restructure\"), implementer (\"how to implement\")\n\n**The insight**: N=2 catches more than N=1. Different perspectives see different things. Coordinate them systematically.\n\n> **Note**: \"Cognitive modes\" are review perspectives with different analytical focus, not\n> external API calls. Mode names (analyzer, architect, implementer) describe the review\n> approach, not specific AI models or services.\n\n## Usage\n\n```\n\u002Fro \u003Csub-command> [arguments]\n```\n\n## Sub-Commands\n\n| Command | CJK | Logic | Trigger |\n|---------|-----|-------|---------|\n| `\u002Fro select` | 選択 | context×risk→type∈{twin,cognitive,code} | Explicit |\n| `\u002Fro twin` | 双子 | spawn(technical,creative)→findings[] | Explicit |\n| `\u002Fro cognitive` | 認知 | spawn(modes[])→analysis[] | Explicit |\n| `\u002Fro multi` | 双視 | alias for `\u002Fro twin` (multi-perspective review) | Explicit |\n| `\u002Fro gate` | 門番 | staged_work→pass✓∨block✗ | Explicit |\n\n## Arguments\n\n### \u002Fro select\n\n| Argument | Required | Description |\n|----------|----------|-------------|\n| context | Yes | Description of work to review |\n| --risk | No | Risk level: `low`, `medium`, `high` (auto-detected if omitted) |\n\n### \u002Fro twin\n\n| Argument | Required | Description |\n|----------|----------|-------------|\n| target | Yes | File path(s) or topic to review |\n| --technical-only | No | Skip creative perspective |\n| --creative-only | No | Skip technical perspective |\n\n### \u002Fro cognitive\n\n| Argument | Required | Description |\n|----------|----------|-------------|\n| target | Yes | File path(s) or topic to review |\n| --modes | No | Cognitive modes: `analyzer`, `architect`, `implementer` (default: all) |\n\n### \u002Fro multi\n\nAlias for `\u002Fro twin`. The name \"twin\" refers to the dual-perspective review pattern\n(technical + creative), not a specific team structure. `\u002Fro multi` is provided for\ndiscoverability by users unfamiliar with the \"twin\" terminology.\n\n### \u002Fro gate\n\n| Argument | Required | Description |\n|----------|----------|-------------|\n| stage | Yes | Stage name or number to gate |\n| --strict | No | Require all checks pass (default: true) |\n| --allow-minor | No | Allow minor issues to pass |\n\n## Core Logic\n\n### Review Type Selection\n\n| Context | Risk | Recommended Review |\n|---------|------|-------------------|\n| Implementation | Low | `\u002Fro twin --technical-only` |\n| Implementation | Medium | `\u002Fro twin` (both perspectives) |\n| Implementation | High | `\u002Fro twin` + `\u002Fro cognitive` |\n| Architecture | Any | `\u002Fro cognitive` |\n| Documentation | Any | `\u002Fro twin --creative-only` |\n| Security | Any | `\u002Fro cognitive` + external review |\n\n### Multi-Perspective Review\n\n| Perspective | Focus | CJK |\n|-------------|-------|-----|\n| Technical | Architecture, standards, patterns, security | 技術 |\n| Creative | UX, communication, philosophy alignment | 創造 |\n\n### Cognitive Modes\n\nCognitive modes provide different analytical perspectives. Modes are configurable;\ndefaults shown below.\n\n| Mode | Perspective | Focus | CJK |\n|------|-------------|-------|-----|\n| analyzer | \"Here's what conflicts\" | Tensions, trade-offs, contradictions | 審碼 |\n| architect | \"Here's how to restructure\" | Architecture, patterns, organization | 審構 |\n| implementer | \"Here's how to implement\" | Concrete steps, complexity, path forward | 審実 |\n\n> **Note**: Mode names are perspective-based, not model-specific. The underlying model\n> used for each mode is configurable (see Configuration section below).\n\n## Configuration\n\nConfiguration is loaded from (in order of precedence):\n1. `.openclaw\u002Freview-orchestrator.yaml` (OpenClaw standard)\n2. `.claude\u002Freview-orchestrator.yaml` (Claude Code compatibility)\n3. Defaults (built-in)\n\n### Cognitive Mode Interface\n\nEach cognitive mode implements this interface:\n\n| Field | Type | Required | Description |\n|-------|------|----------|-------------|\n| id | string | Yes | Mode identifier (e.g., \"analyzer\", \"architect\") |\n| perspective | string | Yes | Human-readable perspective description |\n| prompt_prefix | string | Yes | Prompt prefix for this mode's analysis |\n| model_hint | string | No | Optional model preference (not enforced) |\n\n### Cognitive Mode Configuration\n\n```yaml\n# .openclaw\u002Freview-orchestrator.yaml\ncognitive_modes:\n  - id: analyzer\n    perspective: \"Here's what conflicts\"\n    prompt_prefix: \"Analyze tensions, trade-offs, and conflicts in...\"\n    model_hint: \"prefer analytical model\"\n  - id: architect\n    perspective: \"Here's how to restructure\"\n    prompt_prefix: \"Suggest architectural improvements for...\"\n    model_hint: \"prefer architectural model\"\n  - id: implementer\n    perspective: \"Here's how to implement\"\n    prompt_prefix: \"Provide implementation guidance for...\"\n    model_hint: \"prefer practical model\"\n```\n\n### Quality Gate Configuration\n\n```yaml\n# .openclaw\u002Freview-orchestrator.yaml\nquality_gates:\n  test_command: \"npm test\"    # Node.js (default)\n  # test_command: \"go test .\u002F...\"  # Go\n  # test_command: \"pytest\"         # Python\n  # test_command: \"cargo test\"     # Rust\n  coverage_threshold: 5       # Max allowed coverage drop (%)\n  require_docs: true          # Require documentation updates\n```\n\n### Quality Gate Checks\n\n| Check | Condition | Severity |\n|-------|-----------|----------|\n| Tests pass | `{test_command}` exit 0 | Critical |\n| Coverage maintained | delta ≤ `{coverage_threshold}`% | Important |\n| No critical findings | review.critical == 0 | Critical |\n| Docs updated | changed files have docs (if `require_docs`) | Minor |\n\n> Checks use configured values from `quality_gates` section. Defaults: test_command=`npm test`,\n> coverage_threshold=5, require_docs=true.\n\n## Output\n\n### \u002Fro select output\n\n```\n[REVIEW SELECTION]\nContext: \"Refactoring authentication handler\"\nRisk: Medium (auto-detected: changes auth code)\n\nRecommended: \u002Fro twin\nRationale: Medium-risk implementation benefits from both technical and creative perspectives.\n\nAlternative: \u002Fro cognitive (for deeper architectural analysis)\n```\n\n### \u002Fro twin output\n\n```\n[MULTI-PERSPECTIVE REVIEW INITIATED]\nTarget: src\u002Fhandlers\u002Fauth.go\nPerspectives: technical, creative\n\n--- Technical Perspective Findings ---\nSeverity: important\n- I-1: Missing error handling on line 45\n- I-2: Consider extracting validation logic\n\nSeverity: minor\n- M-1: Inconsistent naming convention\n\n--- Creative Perspective Findings ---\nSeverity: minor\n- M-1: Error messages could be more user-friendly\n- M-2: Consider adding debug logging for operators\n\nVerdict: Approved with conditions\n```\n\n### \u002Fro cognitive output\n\n```\n[COGNITIVE REVIEW INITIATED]\nTarget: docs\u002Farchitecture\u002Fauth-flow.md\nModes: analyzer, architect, implementer\n\n--- Analyzer Perspective (Conflicts) ---\n- Tension between security and usability in token refresh\n- Trade-off: session duration vs re-auth frequency\n\n--- Architect Perspective (Restructure) ---\n- Suggested: Extract token service from handler\n- Benefit: Cleaner separation of concerns\n\n--- Implementer Perspective (Implement) ---\n- Implementation path: 3 stages\n- Estimated complexity: Medium\n\nVerdict: Approved\n```\n\n### \u002Fro gate output (pass)\n\n```\n[QUALITY GATE: Stage 2]\nStatus: ✓ PASSED\n\nChecks:\n- ✓ Tests pass (exit 0)\n- ✓ Coverage maintained (delta: -1.2%)\n- ✓ No critical findings\n- ✓ Documentation updated\n\nProceed to Stage 3.\n```\n\n### \u002Fro gate output (block)\n\n```\n[QUALITY GATE: Stage 2]\nStatus: ✗ BLOCKED\n\nChecks:\n- ✓ Tests pass\n- ✗ Coverage dropped (delta: -8.3%, threshold: 5%)\n- ✓ No critical findings\n- ✗ Documentation not updated\n\nAction required before proceeding:\n1. Add tests to restore coverage\n2. Update docs\u002Fhandlers\u002FREADME.md\n```\n\n### Example: API Design Review\n\n```\n\u002Fro cognitive api\u002Fopenapi.yaml --modes analyzer,architect\n[COGNITIVE REVIEW INITIATED]\nTarget: api\u002Fopenapi.yaml\nModes: analyzer, architect\n\n--- Analyzer Perspective (Conflicts) ---\n- Tension: Versioning strategy (URL vs header) inconsistent across endpoints\n- Trade-off: Pagination style (cursor vs offset) mixed usage\n\n--- Architect Perspective (Restructure) ---\n- Suggested: Standardize on cursor pagination for large collections\n- Benefit: Consistent client SDK, better performance at scale\n\nVerdict: Approved with conditions\n```\n\n### Example: Performance Review\n\n```\n\u002Fro twin src\u002Fhandlers\u002Fsearch.go --technical-only\n[MULTI-PERSPECTIVE REVIEW INITIATED]\nTarget: src\u002Fhandlers\u002Fsearch.go\nPerspectives: technical\n\n--- Technical Perspective Findings ---\nSeverity: important\n- I-1: N+1 query pattern on line 78 (database calls in loop)\n- I-2: Missing index on search_terms table\n\nSeverity: minor\n- M-1: Consider caching frequent searches (>100 req\u002Fmin)\n\nVerdict: Approved with conditions\n```\n\n## Integration\n\n- **Layer**: Review\n- **Depends on**: failure-memory (for context), context-verifier (for file verification)\n- **Used by**: governance (for constraint reviews)\n\n## Failure Modes\n\n| Condition | Behavior |\n|-----------|----------|\n| Invalid sub-command | List available sub-commands |\n| Target not found | Error: \"Target not found: {path}\" |\n| Agent spawn failed | Retry once, then report failure |\n| Gate check failed | Block with specific remediation steps |\n\n## Next Steps\n\nAfter invoking this skill:\n\n| Condition | Action |\n|-----------|--------|\n| Review complete | Write findings to `docs\u002Freviews\u002F` |\n| Gate passed | Proceed to next stage |\n| Gate blocked | Address findings, re-run gate |\n| Critical findings | Create observation via `\u002Ffm record` |\n\n## Workspace Files\n\nThis skill reads\u002Fwrites:\n\n```\ndocs\u002Freviews\u002F\n├── [date]-[topic]-twin-technical.md\n├── [date]-[topic]-twin-creative.md\n├── [date]-[topic]-cognitive.md\n└── [date]-[topic]-gate-results.md\n```\n\n## Security Considerations\n\n**What this skill accesses:**\n- Configuration files in `.openclaw\u002Freview-orchestrator.yaml` and `.claude\u002Freview-orchestrator.yaml`\n- Target files specified by user for review (read-only)\n- Its own output directory `docs\u002Freviews\u002F`\n\n**What this skill does NOT access:**\n- Files outside declared workspace paths\n- System environment variables\n- Network resources or external APIs\n- Other tools' configuration\n\n**What this skill does NOT do:**\n- Invoke AI models directly (instruction-only skill)\n- Call external services (Codex, Gemini, or any third-party API)\n- Send data to external services\n- Modify files outside its workspace (only writes to `docs\u002Freviews\u002F`)\n- Execute arbitrary code\n\n**Cognitive modes clarification:**\nMode names like \"analyzer\", \"architect\", and \"implementer\" describe review perspectives\n(analytical approaches), NOT external AI services. The skill provides prompts and structure;\nyour agent executes the review using its configured model.\n\n**Configuration files:**\nThe config files (`.openclaw\u002Freview-orchestrator.yaml` and `.claude\u002Freview-orchestrator.yaml`)\ncontain only local behavior settings (cognitive mode definitions, quality gate thresholds).\nThey do NOT contain API keys, tokens, or external service endpoints by design.\n\n**Dependency clarification:**\nReferences to `failure-memory` and `context-verifier` are skill-level dependencies installed\nvia `openclaw install`. These are separate instruction-only skills with their own declared\npermissions — this skill does not grant them additional access or inherit their permissions.\n\n**Provenance note:**\nThis skill is developed by Live Neon (https:\u002F\u002Fgithub.com\u002Flive-neon\u002Fskills) and published\nto ClawHub under the `leegitw` account. Both refer to the same maintainer.\n\n## Acceptance Criteria\n\n- [ ] `\u002Fro select` recommends appropriate review type based on context and risk\n- [ ] `\u002Fro twin` (or `\u002Fro multi`) spawns both technical and creative perspectives\n- [ ] `\u002Fro twin` aggregates findings from both perspectives\n- [ ] `\u002Fro cognitive` spawns configured cognitive modes (default: analyzer, architect, implementer)\n- [ ] `\u002Fro cognitive` presents different perspectives clearly\n- [ ] `\u002Fro gate` checks all configured quality criteria\n- [ ] `\u002Fro gate` blocks on critical failures\n- [ ] `\u002Fro gate` provides clear remediation guidance\n- [ ] Review findings written to workspace files\n- [ ] Configuration loaded from `.openclaw\u002F` or `.claude\u002F` paths\n\n---\n\n*Consolidated from 5 skills as part of agentic skills consolidation (2026-02-15).*\n","# review-orchestrator (審査)\n\nUnified skill for selecting review types, spawning multi-perspective and cognitive review agents,\nand managing quality gates. Consolidates 5 granular skills into a single review system.\n\n**Trigger**: レビュー要求 (review requested)\n\n**Source skills**: twin-review, cognitive-review, review-selector, staged-quality-gate, prompt-normalizer\n\n## Installation\n\n```bash\nopenclaw install leegitw\u002Freview-orchestrator\n```\n\n**Dependencies**:\n- `leegitw\u002Ffailure-memory` (for context)\n- `leegitw\u002Fcontext-verifier` (for file verification)\n\n```bash\n# Install with dependencies\nopenclaw install leegitw\u002Fcontext-verifier\nopenclaw install leegitw\u002Ffailure-memory\nopenclaw install leegitw\u002Freview-orchestrator\n```\n\n**Standalone usage**: Review orchestration works independently for multi-perspective reviews.\nIntegration with failure-memory enables automatic observation recording from review findings.\n\n**Data handling**: This skill operates within your agent's trust boundary. When triggered,\nit uses your agent's configured model for multi-perspective review orchestration. No external APIs\nor third-party services are called. Review results are written to `docs\u002Freviews\u002F` in your workspace.\n\n## What This Solves\n\nOne perspective has blind spots. This skill coordinates multiple review perspectives to catch what single-pass review misses:\n\n1. **Twin review** — technical and creative perspectives for balance\n2. **Cognitive modes** — analyzer (\"what conflicts\"), architect (\"how to restructure\"), implementer (\"how to implement\")\n\n**The insight**: N=2 catches more than N=1. Different perspectives see different things. Coordinate them systematically.\n\n> **Note**: \"Cognitive modes\" are review perspectives with different analytical focus, not\n> external API calls. Mode names (analyzer, architect, implementer) describe the review\n> approach, not specific AI models or services.\n\n## Usage\n\n```\n\u002Fro \u003Csub-command> [arguments]\n```\n\n## Sub-Commands\n\n| Command | CJK | Logic | Trigger |\n|---------|-----|-------|---------|\n| `\u002Fro select` | 選択 | context×risk→type∈{twin,cognitive,code} | Explicit |\n| `\u002Fro twin` | 双子 | spawn(technical,creative)→findings[] | Explicit |\n| `\u002Fro cognitive` | 認知 | spawn(modes[])→analysis[] | Explicit |\n| `\u002Fro multi` | 双視 | alias for `\u002Fro twin` (multi-perspective review) | Explicit |\n| `\u002Fro gate` | 門番 | staged_work→pass✓∨block✗ | Explicit |\n\n## Arguments\n\n### \u002Fro select\n\n| Argument | Required | Description |\n|----------|----------|-------------|\n| context | Yes | Description of work to review |\n| --risk | No | Risk level: `low`, `medium`, `high` (auto-detected if omitted) |\n\n### \u002Fro twin\n\n| Argument | Required | Description |\n|----------|----------|-------------|\n| target | Yes | File path(s) or topic to review |\n| --technical-only | No | Skip creative perspective |\n| --creative-only | No | Skip technical perspective |\n\n### \u002Fro cognitive\n\n| Argument | Required | Description |\n|----------|----------|-------------|\n| target | Yes | File path(s) or topic to review |\n| --modes | No | Cognitive modes: `analyzer`, `architect`, `implementer` (default: all) |\n\n### \u002Fro multi\n\nAlias for `\u002Fro twin`. The name \"twin\" refers to the dual-perspective review pattern\n(technical + creative), not a specific team structure. `\u002Fro multi` is provided for\ndiscoverability by users unfamiliar with the \"twin\" terminology.\n\n### \u002Fro gate\n\n| Argument | Required | Description |\n|----------|----------|-------------|\n| stage | Yes | Stage name or number to gate |\n| --strict | No | Require all checks pass (default: true) |\n| --allow-minor | No | Allow minor issues to pass |\n\n## Core Logic\n\n### Review Type Selection\n\n| Context | Risk | Recommended Review |\n|---------|------|-------------------|\n| Implementation | Low | `\u002Fro twin --technical-only` |\n| Implementation | Medium | `\u002Fro twin` (both perspectives) |\n| Implementation | High | `\u002Fro twin` + `\u002Fro cognitive` |\n| Architecture | Any | `\u002Fro cognitive` |\n| Documentation | Any | `\u002Fro twin --creative-only` |\n| Security | Any | `\u002Fro cognitive` + external review |\n\n### Multi-Perspective Review\n\n| Perspective | Focus | CJK |\n|-------------|-------|-----|\n| Technical | Architecture, standards, patterns, security | 技術 |\n| Creative | UX, communication, philosophy alignment | 創造 |\n\n### Cognitive Modes\n\nCognitive modes provide different analytical perspectives. Modes are configurable;\ndefaults shown below.\n\n| Mode | Perspective | Focus | CJK |\n|------|-------------|-------|-----|\n| analyzer | \"Here's what conflicts\" | Tensions, trade-offs, contradictions | 審碼 |\n| architect | \"Here's how to restructure\" | Architecture, patterns, organization | 審構 |\n| implementer | \"Here's how to implement\" | Concrete steps, complexity, path forward | 審実 |\n\n> **Note**: Mode names are perspective-based, not model-specific. The underlying model\n> used for each mode is configurable (see Configuration section below).\n\n## Configuration\n\nConfiguration is loaded from (in order of precedence):\n1. `.openclaw\u002Freview-orchestrator.yaml` (OpenClaw standard)\n2. `.claude\u002Freview-orchestrator.yaml` (Claude Code compatibility)\n3. Defaults (built-in)\n\n### Cognitive Mode Interface\n\nEach cognitive mode implements this interface:\n\n| Field | Type | Required | Description |\n|-------|------|----------|-------------|\n| id | string | Yes | Mode identifier (e.g., \"analyzer\", \"architect\") |\n| perspective | string | Yes | Human-readable perspective description |\n| prompt_prefix | string | Yes | Prompt prefix for this mode's analysis |\n| model_hint | string | No | Optional model preference (not enforced) |\n\n### Cognitive Mode Configuration\n\n```yaml\n# .openclaw\u002Freview-orchestrator.yaml\ncognitive_modes:\n  - id: analyzer\n    perspective: \"Here's what conflicts\"\n    prompt_prefix: \"Analyze tensions, trade-offs, and conflicts in...\"\n    model_hint: \"prefer analytical model\"\n  - id: architect\n    perspective: \"Here's how to restructure\"\n    prompt_prefix: \"Suggest architectural improvements for...\"\n    model_hint: \"prefer architectural model\"\n  - id: implementer\n    perspective: \"Here's how to implement\"\n    prompt_prefix: \"Provide implementation guidance for...\"\n    model_hint: \"prefer practical model\"\n```\n\n### Quality Gate Configuration\n\n```yaml\n# .openclaw\u002Freview-orchestrator.yaml\nquality_gates:\n  test_command: \"npm test\"    # Node.js (default)\n  # test_command: \"go test .\u002F...\"  # Go\n  # test_command: \"pytest\"         # Python\n  # test_command: \"cargo test\"     # Rust\n  coverage_threshold: 5       # Max allowed coverage drop (%)\n  require_docs: true          # Require documentation updates\n```\n\n### Quality Gate Checks\n\n| Check | Condition | Severity |\n|-------|-----------|----------|\n| Tests pass | `{test_command}` exit 0 | Critical |\n| Coverage maintained | delta ≤ `{coverage_threshold}`% | Important |\n| No critical findings | review.critical == 0 | Critical |\n| Docs updated | changed files have docs (if `require_docs`) | Minor |\n\n> Checks use configured values from `quality_gates` section. Defaults: test_command=`npm test`,\n> coverage_threshold=5, require_docs=true.\n\n## Output\n\n### \u002Fro select output\n\n```\n[REVIEW SELECTION]\nContext: \"Refactoring authentication handler\"\nRisk: Medium (auto-detected: changes auth code)\n\nRecommended: \u002Fro twin\nRationale: Medium-risk implementation benefits from both technical and creative perspectives.\n\nAlternative: \u002Fro cognitive (for deeper architectural analysis)\n```\n\n### \u002Fro twin output\n\n```\n[MULTI-PERSPECTIVE REVIEW INITIATED]\nTarget: src\u002Fhandlers\u002Fauth.go\nPerspectives: technical, creative\n\n--- Technical Perspective Findings ---\nSeverity: important\n- I-1: Missing error handling on line 45\n- I-2: Consider extracting validation logic\n\nSeverity: minor\n- M-1: Inconsistent naming convention\n\n--- Creative Perspective Findings ---\nSeverity: minor\n- M-1: Error messages could be more user-friendly\n- M-2: Consider adding debug logging for operators\n\nVerdict: Approved with conditions\n```\n\n### \u002Fro cognitive output\n\n```\n[COGNITIVE REVIEW INITIATED]\nTarget: docs\u002Farchitecture\u002Fauth-flow.md\nModes: analyzer, architect, implementer\n\n--- Analyzer Perspective (Conflicts) ---\n- Tension between security and usability in token refresh\n- Trade-off: session duration vs re-auth frequency\n\n--- Architect Perspective (Restructure) ---\n- Suggested: Extract token service from handler\n- Benefit: Cleaner separation of concerns\n\n--- Implementer Perspective (Implement) ---\n- Implementation path: 3 stages\n- Estimated complexity: Medium\n\nVerdict: Approved\n```\n\n### \u002Fro gate output (pass)\n\n```\n[QUALITY GATE: Stage 2]\nStatus: ✓ PASSED\n\nChecks:\n- ✓ Tests pass (exit 0)\n- ✓ Coverage maintained (delta: -1.2%)\n- ✓ No critical findings\n- ✓ Documentation updated\n\nProceed to Stage 3.\n```\n\n### \u002Fro gate output (block)\n\n```\n[QUALITY GATE: Stage 2]\nStatus: ✗ BLOCKED\n\nChecks:\n- ✓ Tests pass\n- ✗ Coverage dropped (delta: -8.3%, threshold: 5%)\n- ✓ No critical findings\n- ✗ Documentation not updated\n\nAction required before proceeding:\n1. Add tests to restore coverage\n2. Update docs\u002Fhandlers\u002FREADME.md\n```\n\n### Example: API Design Review\n\n```\n\u002Fro cognitive api\u002Fopenapi.yaml --modes analyzer,architect\n[COGNITIVE REVIEW INITIATED]\nTarget: api\u002Fopenapi.yaml\nModes: analyzer, architect\n\n--- Analyzer Perspective (Conflicts) ---\n- Tension: Versioning strategy (URL vs header) inconsistent across endpoints\n- Trade-off: Pagination style (cursor vs offset) mixed usage\n\n--- Architect Perspective (Restructure) ---\n- Suggested: Standardize on cursor pagination for large collections\n- Benefit: Consistent client SDK, better performance at scale\n\nVerdict: Approved with conditions\n```\n\n### Example: Performance Review\n\n```\n\u002Fro twin src\u002Fhandlers\u002Fsearch.go --technical-only\n[MULTI-PERSPECTIVE REVIEW INITIATED]\nTarget: src\u002Fhandlers\u002Fsearch.go\nPerspectives: technical\n\n--- Technical Perspective Findings ---\nSeverity: important\n- I-1: N+1 query pattern on line 78 (database calls in loop)\n- I-2: Missing index on search_terms table\n\nSeverity: minor\n- M-1: Consider caching frequent searches (>100 req\u002Fmin)\n\nVerdict: Approved with conditions\n```\n\n## Integration\n\n- **Layer**: Review\n- **Depends on**: failure-memory (for context), context-verifier (for file verification)\n- **Used by**: governance (for constraint reviews)\n\n## Failure Modes\n\n| Condition | Behavior |\n|-----------|----------|\n| Invalid sub-command | List available sub-commands |\n| Target not found | Error: \"Target not found: {path}\" |\n| Agent spawn failed | Retry once, then report failure |\n| Gate check failed | Block with specific remediation steps |\n\n## Next Steps\n\nAfter invoking this skill:\n\n| Condition | Action |\n|-----------|--------|\n| Review complete | Write findings to `docs\u002Freviews\u002F` |\n| Gate passed | Proceed to next stage |\n| Gate blocked | Address findings, re-run gate |\n| Critical findings | Create observation via `\u002Ffm record` |\n\n## Workspace Files\n\nThis skill reads\u002Fwrites:\n\n```\ndocs\u002Freviews\u002F\n├── [date]-[topic]-twin-technical.md\n├── [date]-[topic]-twin-creative.md\n├── [date]-[topic]-cognitive.md\n└── [date]-[topic]-gate-results.md\n```\n\n## Security Considerations\n\n**What this skill accesses:**\n- Configuration files in `.openclaw\u002Freview-orchestrator.yaml` and `.claude\u002Freview-orchestrator.yaml`\n- Target files specified by user for review (read-only)\n- Its own output directory `docs\u002Freviews\u002F`\n\n**What this skill does NOT access:**\n- Files outside declared workspace paths\n- System environment variables\n- Network resources or external APIs\n- Other tools' configuration\n\n**What this skill does NOT do:**\n- Invoke AI models directly (instruction-only skill)\n- Call external services (Codex, Gemini, or any third-party API)\n- Send data to external services\n- Modify files outside its workspace (only writes to `docs\u002Freviews\u002F`)\n- Execute arbitrary code\n\n**Cognitive modes clarification:**\nMode names like \"analyzer\", \"architect\", and \"implementer\" describe review perspectives\n(analytical approaches), NOT external AI services. The skill provides prompts and structure;\nyour agent executes the review using its configured model.\n\n**Configuration files:**\nThe config files (`.openclaw\u002Freview-orchestrator.yaml` and `.claude\u002Freview-orchestrator.yaml`)\ncontain only local behavior settings (cognitive mode definitions, quality gate thresholds).\nThey do NOT contain API keys, tokens, or external service endpoints by design.\n\n**Dependency clarification:**\nReferences to `failure-memory` and `context-verifier` are skill-level dependencies installed\nvia `openclaw install`. These are separate instruction-only skills with their own declared\npermissions — this skill does not grant them additional access or inherit their permissions.\n\n**Provenance note:**\nThis skill is developed by Live Neon (https:\u002F\u002Fgithub.com\u002Flive-neon\u002Fskills) and published\nto ClawHub under the `leegitw` account. Both refer to the same maintainer.\n\n## Acceptance Criteria\n\n- [ ] `\u002Fro select` recommends appropriate review type based on context and risk\n- [ ] `\u002Fro twin` (or `\u002Fro multi`) spawns both technical and creative perspectives\n- [ ] `\u002Fro twin` aggregates findings from both perspectives\n- [ ] `\u002Fro cognitive` spawns configured cognitive modes (default: analyzer, architect, implementer)\n- [ ] `\u002Fro cognitive` presents different perspectives clearly\n- [ ] `\u002Fro gate` checks all configured quality criteria\n- [ ] `\u002Fro gate` blocks on critical failures\n- [ ] `\u002Fro gate` provides clear remediation guidance\n- [ ] Review findings written to workspace files\n- [ ] Configuration loaded from `.openclaw\u002F` or `.claude\u002F` paths\n\n---\n\n*Consolidated from 5 skills as part of agentic skills consolidation (2026-02-15).*\n",{"name":5,"tags":24,"alias":33,"layer":26,"author":34,"status":35,"license":15,"version":36,"homepage":37,"metadata":38,"repository":46,"description":7},[25,26,27,28,29,30,31,32],"agentic","review","orchestration","multi-perspective","code-review","quality","twin-review","feedback","ro","Live Neon \u003Ccontact@liveneon.dev>","active","1.5.0","https:\u002F\u002Fgithub.com\u002Flive-neon\u002Fskills\u002Ftree\u002Fmain\u002Fagentic\u002Freview-orchestrator",{"openclaw":39},{"requires":40},{"config":41,"workspace":44},[42,43],".openclaw\u002Freview-orchestrator.yaml",".claude\u002Freview-orchestrator.yaml",[45],"docs\u002Freviews\u002F","leegitw\u002Freview-orchestrator","main","f9d3fe7cf9ac8f1ea63a0d96e98e1f510a3814db","skills\u002Fleegitw\u002Freview-orchestrator",1,"https:\u002F\u002Fgithub.com\u002Fjavimosch\u002Fopen-claw-skills","https:\u002F\u002Fgithub.com\u002Fjavimosch","intrane.fr","Building robust, open-source infrastructure for the commons. AI-leveraged, self-hosted, built to last.","2026-06-07 03:34:58",{"source":8,"skillName":5,"commands":57,"prompt":67,"zipAvailable":68},[58,61,64],{"tool":59,"command":60},"npx","npx skills add javimosch\u002Fopen-claw-skills --skill review-orchestrator",{"tool":62,"command":63},"bunx","bunx skills add javimosch\u002Fopen-claw-skills --skill review-orchestrator",{"tool":65,"command":66},"pnpm","pnpm dlx skills add javimosch\u002Fopen-claw-skills --skill review-orchestrator","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fjavimosch\u002Fopen-claw-skills\u002Fblob\u002Fmain\u002Fskills\u002Fleegitw\u002Freview-orchestrator\u002FSKILL.md",true,[],[71,79,86,93,100,107],{"skillNo":72,"name":73,"nameZh":6,"description":74,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":75,"categories":76,"keywords":77,"publishedAt":78},"01M778GGXG2VQ0YF31W2MKGMQZ","crowd-prompting","A marketplace where AI agents improve prompts, system instructions, tool descriptions, and other text-based content with domain expertise from real-world operations — and earn tokens for valuable contributions.","https:\u002F\u002Fgithub.com\u002Fjavimosch\u002Fopen-claw-skills\u002Fblob\u002Fmain\u002Fskills\u002Fzzadrian\u002Fcrowd-prompting\u002FSKILL.md",[],[],"2026-11-15 14:19:17",{"skillNo":80,"name":81,"nameZh":6,"description":82,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":83,"categories":84,"keywords":85,"publishedAt":78},"01M778G7BH8SBJ9FJ6C3G7CB1K","ceaser","Interact with the Ceaser privacy protocol on Base L2 using the ceaser-mcp MCP tools. This skill uses the ceaser-mcp npm package for ALL operations -- shield, unshield, note management, and protocol queries. All ceaser tool calls use CLI subcommands (npx -y ceaser-mcp \u003Csubcommand>). Ceaser is a privacy-preserving ETH wrapper using Noir\u002FUltraHonk zero-knowledge proofs on Base L2 (chain ID 8453).","https:\u002F\u002Fgithub.com\u002Fjavimosch\u002Fopen-claw-skills\u002Fblob\u002Fmain\u002Fskills\u002Fzyra-v21\u002Fceaser\u002FSKILL.md",[],[],{"skillNo":87,"name":88,"nameZh":6,"description":89,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":90,"categories":91,"keywords":92,"publishedAt":78},"01M778FYCJQZWFKKX5FYMK3S47","ceaser-send","Fully automated private ETH transfer via Ceaser Protocol on Base L2 using the ceaser-mcp MCP tools. This skill uses the ceaser-mcp npm package for ALL operations -- all ceaser tool calls use CLI subcommands (npx -y ceaser-mcp \u003Csubcommand>). WARNING -- creates observable on-chain links between user wallet and hot wallet (see Privacy Warning). Generates an ephemeral hot wallet with BIP-39 mnemonic recovery, user funds it, agent signs and broadcasts the Shield TX automatically. Exactly one manual step required (funding the hot wallet with ETH). Uses Noir\u002FUltraHonk zero-knowledge proofs.","https:\u002F\u002Fgithub.com\u002Fjavimosch\u002Fopen-claw-skills\u002Fblob\u002Fmain\u002Fskills\u002Fzyra-v21\u002Fceaser-send\u002FSKILL.md",[],[],{"skillNo":94,"name":95,"nameZh":6,"description":96,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":97,"categories":98,"keywords":99,"publishedAt":78},"01M778FQQNSEYA3HJKZBPQ4M9Z","dilemm-ai","Compete in DilemmAI, the prisoner's dilemma AI arena at dilemm.ai. Use when an OpenClaw agent wants to create an account, design and submit strategy prompts for their bot, enter matchmaking, analyze historical matches and leaderboards, and iterate on bot strategy. Requires headless browser automation (no API available yet).","https:\u002F\u002Fgithub.com\u002Fjavimosch\u002Fopen-claw-skills\u002Fblob\u002Fmain\u002Fskills\u002Fzyori\u002Fdilemm-ai\u002FSKILL.md",[],[],{"skillNo":101,"name":102,"nameZh":6,"description":103,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":104,"categories":105,"keywords":106,"publishedAt":78},"01M778FGVZX7QA2TF9BFMM37FY","moldium","Post and manage content on the Moldium blog platform. Triggered by \"post to Moldium\", \"write a blog post\", \"publish an article\", etc.","https:\u002F\u002Fgithub.com\u002Fjavimosch\u002Fopen-claw-skills\u002Fblob\u002Fmain\u002Fskills\u002Fzyom45\u002Fmoldium\u002FSKILL.md",[],[],{"skillNo":108,"name":109,"nameZh":6,"description":110,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":111,"categories":112,"keywords":113,"publishedAt":78},"01M778F88D8PQ9MQ0KNW2TJ8ZH","arxiv-paper-reviews","Interact with arXiv Crawler API to fetch papers, read reviews, submit comments, search papers, and import papers. Use when working with arXiv papers, fetching paper lists by date\u002Fcategory\u002Finterest, viewing paper details with comments, submitting paper reviews, searching papers by title, or importing papers from arXiv URLs via API at http:\u002F\u002Fweakaccept.top:8000\u002F.","https:\u002F\u002Fgithub.com\u002Fjavimosch\u002Fopen-claw-skills\u002Fblob\u002Fmain\u002Fskills\u002Fzxrys\u002Farxiv-paper-reviews\u002FSKILL.md",[],[]]