[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6EGJMQ0SRV8BFN5W4AYWWEZ":3,"skill-same:01M6EGJMQ0SRV8BFN5W4AYWWEZ":71},{"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":29,"linkOnly":30,"markdownContent":31,"markdownBody":32,"frontMatter":33,"refName":34,"commitSha":35,"skillDirectory":36,"forksCount":37,"repositoryHtmlUrl":38,"repositoryHomepageUrl":6,"ownerHtmlUrl":39,"ownerBlogUrl":40,"ownerDescription":41,"updatedAt":42,"install":43,"resources":56},"01M6EGJMQ0SRV8BFN5W4AYWWEZ","ln-644-dependency-graph-auditor",null,"Builds dependency graph, detects cycles (DFS), validates boundary rules, calculates coupling metrics (Ca\u002FCe\u002FI, CCD\u002FNCCD). Adaptive architecture detection.","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-644-dependency-graph-auditor\u002FSKILL.md",[],[19,20,21,22,23,24,25,26,27,28],"graph","dependency","dependency graph","ln 644 dependency graph auditor","architecture","metrics","detection","boundary","Rules","coupling","2026-11-10 10:12:30",false,"---\nname: ln-644-dependency-graph-auditor\ndescription: \"Builds dependency graph, detects cycles (DFS), validates boundary rules, calculates coupling metrics (Ca\u002FCe\u002FI, CCD\u002FNCCD). Adaptive architecture detection.\"\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# Dependency Graph Auditor\n\nL3 Worker that builds and analyzes the module dependency graph to enforce architectural boundaries.\n\n## Purpose & Scope\n\n- **Worker in ln-640 coordinator pipeline** - invoked by ln-640-pattern-evolution-auditor\n- Build module dependency graph from import statements (Python, TS\u002FJS, C#, Java)\n- Detect circular dependencies: pairwise (HIGH) + transitive via DFS (CRITICAL)\n- Validate boundary rules: forbidden, allowed, required (per dependency-cruiser pattern)\n- Calculate Robert C. Martin metrics (Ca, Ce, Instability) + Lakos aggregate (CCD, NCCD)\n- Validate Stable Dependencies Principle (SDP)\n- Support baseline\u002Ffreeze for incremental legacy adoption (per ArchUnit FreezingArchRule)\n- **Adaptive:** 3-tier architecture detection — custom rules > docs > auto-detect\n\n**Out of Scope** (owned by other workers):\n- I\u002FO isolation violations (grep-based) -> ln-642-layer-boundary-auditor\n- API contract violations -> ln-643-api-contract-auditor\n- Code duplication -> ln-623-code-principles-auditor\n\n## Input (from ln-640)\n\n```\n- architecture_path: string    # Path to docs\u002Farchitecture.md\n- codebase_root: string        # Root directory to scan\n- output_dir: string           # e.g., \"docs\u002Fproject\u002F.audit\u002Fln-640\u002F{YYYY-MM-DD}\"\n\n# Domain-aware (optional, from coordinator)\n- domain_mode: \"global\" | \"domain-aware\"   # Default: \"global\"\n- current_domain: string                   # e.g., \"users\", \"billing\" (only if domain-aware)\n- scan_path: string                        # e.g., \"src\u002Fusers\u002F\" (only if domain-aware)\n\n# Baseline (optional)\n- update_baseline: boolean                 # If true, save current state as baseline\n```\n\n**When domain_mode=\"domain-aware\":** Use `scan_path` instead of `codebase_root` for all Grep\u002FGlob operations. Tag all findings with `domain` field.\n\n## Workflow\n\n**MANDATORY READ:** Load `shared\u002Freferences\u002Ftwo_layer_detection.md` for detection methodology.\n\n### Phase 1: Discover Architecture (Adaptive)\n\n**MANDATORY READ:** Load `references\u002Fdependency_rules.md` — use 3-Tier Priority Chain, Architecture Presets, Auto-Detection Heuristics.\n\nArchitecture detection uses **3-tier priority** — explicit config wins over docs, docs win over auto-detection:\n\n```\n# Priority 1: Explicit project config\nIF docs\u002Fproject\u002Fdependency_rules.yaml exists:\n  Load custom rules (modules, forbidden, allowed, required)\n  SKIP preset detection\n\n# Priority 2: Architecture documentation\nELIF docs\u002Farchitecture.md exists:\n  Read Section 4.2 (modules, layers, architecture_type)\n  Read Section 6.4 (boundary rules, if defined)\n  Map documented layers to presets from dependency_rules.md\n  Apply preset rules, override with explicit rules from Section 6.4\n\n# Priority 3: Auto-detection from directory structure\nELSE:\n  scan_root = scan_path IF domain_mode == \"domain-aware\" ELSE codebase_root\n  Run structure heuristics:\n\n  signals = {}\n  IF Glob(\"**\u002Fdomain\u002F**\") AND Glob(\"**\u002Finfrastructure\u002F**\"):\n    signals[\"clean\"] = HIGH\n  IF Glob(\"**\u002Fcontrollers\u002F**\") AND Glob(\"**\u002Fservices\u002F**\") AND Glob(\"**\u002Frepositories\u002F**\"):\n    signals[\"layered\"] = HIGH\n  IF Glob(\"**\u002Ffeatures\u002F*\u002F\") with internal structure:\n    signals[\"vertical\"] = HIGH\n  IF Glob(\"**\u002Fadapters\u002F**\") AND Glob(\"**\u002Fports\u002F**\"):\n    signals[\"hexagonal\"] = HIGH\n  IF Glob(\"**\u002Fviews\u002F**\") AND Glob(\"**\u002Fmodels\u002F**\"):\n    signals[\"mvc\"] = HIGH\n\n  IF len(signals) == 0:\n    architecture_mode = \"custom\"\n    confidence = \"LOW\"\n    # Only check cycles + metrics, no boundary presets\n  ELIF len(signals) == 1:\n    architecture_mode = signals.keys()[0]\n    confidence = signals.values()[0]\n    Apply matching preset from dependency_rules.md\n  ELSE:\n    architecture_mode = \"hybrid\"\n    confidence = \"MEDIUM\"\n    # Identify zones, apply different presets per zone (see dependency_rules.md Hybrid section)\n    FOR EACH detected_style IN signals:\n      zone_path = identify_zone(detected_style)\n      zone_preset = load_preset(detected_style)\n      zones.append({path: zone_path, preset: zone_preset})\n    Add cross-zone rules: inner zones accessible, outer zones forbidden to depend on inner\n```\n\n### Phase 2: Build Dependency Graph\n\n**MANDATORY READ:** Load `references\u002Fimport_patterns.md` — use Language Detection, Import Grep Patterns, Module Resolution Algorithm, Exclusion Lists.\n\n```\nscan_root = scan_path IF domain_mode == \"domain-aware\" ELSE codebase_root\n\n# Step 1: Detect primary language\ntech_stack = Read(docs\u002Fproject\u002Ftech_stack.md) IF exists\n  ELSE detect from file extensions: Glob(\"**\u002F*.py\", \"**\u002F*.ts\", \"**\u002F*.cs\", \"**\u002F*.java\", root=scan_root)\n\n# Step 2: Extract imports per language\nFOR EACH source_file IN Glob(language_glob_pattern, root=scan_root):\n  imports = []\n\n  # Python\n  IF language == \"python\":\n    from_imports = Grep(\"^from\\s+([\\w.]+)\\s+import\", source_file)\n    plain_imports = Grep(\"^import\\s+([\\w.]+)\", source_file)\n    imports = from_imports + plain_imports\n\n  # TypeScript \u002F JavaScript\n  ELIF language == \"typescript\" OR language == \"javascript\":\n    es6_imports = Grep(\"import\\s+.*\\s+from\\s+['\\\"]([^'\\\"]+)['\\\"]\", source_file)\n    require_imports = Grep(\"require\\(['\\\"]([^'\\\"]+)['\\\"]\\)\", source_file)\n    imports = es6_imports + require_imports\n\n  # C#\n  ELIF language == \"csharp\":\n    using_imports = Grep(\"^using\\s+([\\w.]+);\", source_file)\n    imports = using_imports\n\n  # Java\n  ELIF language == \"java\":\n    java_imports = Grep(\"^import\\s+([\\w.]+);\", source_file)\n    imports = java_imports\n\n  # Step 3: Filter internal only (per import_patterns.md Exclusion Lists)\n  internal_imports = filter_internal(imports, scan_root)\n\n  # Step 4: Resolve to modules\n  FOR EACH imp IN internal_imports:\n    source_module = resolve_module(source_file, scan_root)\n    target_module = resolve_module(imp, scan_root)\n    IF source_module != target_module:\n      graph[source_module].add(target_module)\n```\n\n### Phase 3: Detect Cycles (ADP)\n\nPer Robert C. Martin (Clean Architecture Ch14): \"Allow no cycles in the component dependency graph.\"\n\n```\n# Pairwise cycles (A \u003C-> B)\nFOR EACH (A, B) WHERE B IN graph[A] AND A IN graph[B]:\n  cycles.append({\n    type: \"pairwise\",\n    path: [A, B, A],\n    severity: \"HIGH\",\n    fix: suggest_cycle_fix(A, B)\n  })\n  # Layer 2: Test-only dependencies (devDependencies, test imports) → skip cycle\n  # Plugin\u002Fextension architecture with documented bidirectional design → downgrade to LOW\n\n# Transitive cycles via DFS (A -> B -> C -> A)\nvisited = {}\nrec_stack = {}\n\nFUNCTION dfs(node, path):\n  visited[node] = true\n  rec_stack[node] = true\n\n  FOR EACH neighbor IN graph[node]:\n    IF NOT visited[neighbor]:\n      dfs(neighbor, path + [node])\n    ELIF rec_stack[neighbor]:\n      cycle_path = extract_cycle(path + [node], neighbor)\n      IF len(cycle_path) > 2:  # Skip pairwise (already detected)\n        cycles.append({\n          type: \"transitive\",\n          path: cycle_path,\n          severity: \"CRITICAL\",\n          fix: suggest_cycle_fix_transitive(cycle_path)\n        })\n\n  rec_stack[node] = false\n\nFOR EACH module IN graph:\n  IF NOT visited[module]:\n    dfs(module, [])\n\n# Folder-level cycles (per dependency-cruiser pattern)\nfolder_graph = collapse_to_folders(graph)\nRepeat DFS on folder_graph for folder-level cycles\n```\n\n**Cycle-breaking recommendations** (from Clean Architecture Ch14):\n1. **DIP** — extract interface in depended-upon module, implement in depending module\n2. **Extract Shared Component** — move shared code to new module both depend on\n3. **Domain Events \u002F Message Bus** — for cross-domain cycles, decouple via async communication\n\n### Phase 4: Validate Boundary Rules\n\n```\n# Load rules from Phase 1 discovery\n# rules = {forbidden: [], allowed: [], required: []}\n\n# Check FORBIDDEN rules\nFOR EACH rule IN rules.forbidden:\n  FOR EACH edge (source -> target) IN graph:\n    IF matches(source, rule.from) AND matches(target, rule.to):\n      IF rule.cross AND same_group(source, target):\n        CONTINUE  # cross=true means only cross-group violations\n      boundary_violations.append({\n        rule_type: \"forbidden\",\n        from: source,\n        to: target,\n        file: get_import_location(source, target),\n        severity: rule.severity,\n        reason: rule.reason\n      })\n\n# Check ALLOWED rules (whitelist mode)\nIF rules.allowed.length > 0:\n  FOR EACH edge (source -> target) IN graph:\n    allowed = false\n    FOR EACH rule IN rules.allowed:\n      IF matches(source, rule.from) AND matches(target, rule.to):\n        allowed = true\n        BREAK\n    IF NOT allowed:\n      boundary_violations.append({\n        rule_type: \"not_in_allowed\",\n        from: source,\n        to: target,\n        file: get_import_location(source, target),\n        severity: \"MEDIUM\",\n        reason: \"Dependency not in allowed list\"\n      })\n\n# Check REQUIRED rules\nFOR EACH rule IN rules.required:\n  FOR EACH module IN graph WHERE matches(module, rule.module):\n    has_required = false\n    FOR EACH dep IN graph[module]:\n      IF matches(dep, rule.must_depend_on):\n        has_required = true\n        BREAK\n    IF NOT has_required:\n      boundary_violations.append({\n        rule_type: \"required_missing\",\n        module: module,\n        missing: rule.must_depend_on,\n        severity: \"MEDIUM\",\n        reason: rule.reason\n      })\n```\n\n### Phase 5: Calculate Graph Metrics\n\n**MANDATORY READ:** Load `references\u002Fgraph_metrics.md` — use Metric Definitions, Thresholds per Layer, SDP Algorithm, Lakos Formulas.\n\n```\n# Per-module metrics (Robert C. Martin)\nFOR EACH module IN graph:\n  Ce = len(graph[module])                          # Efferent: outgoing\n  Ca = count(m for m in graph if module in graph[m])  # Afferent: incoming\n  I = Ce \u002F (Ca + Ce) IF (Ca + Ce) > 0 ELSE 0      # Instability\n\n  metrics[module] = {Ca, Ce, I}\n\n# SDP validation (Stable Dependencies Principle)\nFOR EACH edge (A -> B) IN graph:\n  IF metrics[A].I \u003C metrics[B].I:\n    # Stable module depends on less stable module — SDP violation\n    sdp_violations.append({\n      from: A, to: B,\n      I_from: metrics[A].I, I_to: metrics[B].I,\n      severity: \"HIGH\"\n    })\n\n# Threshold checks (per graph_metrics.md, considering detected layer)\nFOR EACH module IN metrics:\n  layer = get_layer(module)  # From Phase 1 discovery\n  thresholds = get_thresholds(layer)  # From graph_metrics.md\n\n  IF metrics[module].I > thresholds.max_instability:\n    findings.append({severity: thresholds.severity, issue: f\"{module} instability {I} exceeds {thresholds.max_instability}\"})\n  IF metrics[module].Ce > thresholds.max_ce:\n    findings.append({severity: \"MEDIUM\", issue: f\"{module} efferent coupling {Ce} exceeds {thresholds.max_ce}\"})\n\n# Lakos aggregate metrics\nCCD = 0\nFOR EACH module IN graph:\n  DependsOn = count_transitive_deps(module, graph) + 1  # Including self\n  CCD += DependsOn\n\nN = len(graph)\nCCD_balanced = N * log2(N)  # CCD of balanced binary tree with N nodes\nNCCD = CCD \u002F CCD_balanced IF CCD_balanced > 0 ELSE 0\n\nIF NCCD > 1.5:\n  findings.append({severity: \"MEDIUM\", issue: f\"Graph complexity (NCCD={NCCD:.2f}) exceeds balanced tree threshold (1.5)\"})\n```\n\n**Cascade chain extension:** For service files (`**\u002Fservices\u002F**`), extend module-level graph to function-level. Find longest side-effect chain per public function (markers per `shared\u002Freferences\u002Fai_ready_architecture.md`). If chain_length >= 3: add to cascade_findings. Output `\"runtime_cascades\"` array in Phase 8 DATA-EXTENDED JSON. Severity: HIGH (4+), MEDIUM (3).\n\n### Phase 6: Baseline Support\n\nInspired by ArchUnit FreezingArchRule — enables incremental adoption in legacy projects.\n\n```\nbaseline_path = docs\u002Fproject\u002Fdependency_baseline.json\n\nIF file_exists(baseline_path):\n  known = load_json(baseline_path)\n  current = serialize_violations(cycles + boundary_violations + sdp_violations)\n\n  new_violations = current - known\n  resolved_violations = known - current\n\n  # Report only NEW violations as findings\n  active_findings = new_violations\n  baseline_info = {new: len(new_violations), resolved: len(resolved_violations), frozen: len(known - resolved_violations)}\n\n  IF input.update_baseline == true:\n    save_json(baseline_path, current)\n\nELSE:\n  # First run — report all\n  active_findings = all_violations\n  baseline_info = {new: len(all_violations), resolved: 0, frozen: 0}\n  # Suggest: output note \"Run with update_baseline=true to freeze current violations\"\n```\n\n### Phase 7: Calculate Score\n\n**MANDATORY READ:** Load `shared\u002Freferences\u002Faudit_worker_core_contract.md` and `shared\u002Freferences\u002Faudit_scoring.md`.\n\n```\npenalty = (critical * 2.0) + (high * 1.0) + (medium * 0.5) + (low * 0.2)\nscore = max(0, 10 - penalty)\n```\n\n**Note:** When baseline is active, penalty is calculated from `active_findings` only (new violations), not frozen ones.\n\n### Phase 8: Write Report\n\n**MANDATORY READ:** Load `shared\u002Freferences\u002Faudit_worker_core_contract.md` and `shared\u002Ftemplates\u002Faudit_worker_report_template.md`.\n\n```\n# Build markdown report in memory with:\n# - AUDIT-META (standard penalty-based: score, counts)\n# - Checks table (cycle_detection, boundary_rules, sdp_validation, metrics_thresholds, baseline_comparison)\n# - Findings table (active violations sorted by severity)\n# - DATA-EXTENDED: {graph_stats, cycles, boundary_violations, sdp_violations, metrics, baseline}\n\nIF domain_mode == \"domain-aware\":\n  Write to {output_dir}\u002F644-dep-graph-{current_domain}.md\nELSE:\n  Write to {output_dir}\u002F644-dep-graph.md\n```\n\n### Phase 9: Return Summary\n\n```\nReport written: docs\u002Fproject\u002F.audit\u002Fln-640\u002F{YYYY-MM-DD}\u002F644-dep-graph-users.md\nScore: 6.5\u002F10 | Issues: 8 (C:1 H:3 M:3 L:1)\n```\n\n## Critical Rules\n\n**MANDATORY READ:** Load `shared\u002Freferences\u002Faudit_worker_core_contract.md`.\n\n- **Adaptive architecture** — never assume one style; detect from project structure or docs\n- **3-tier priority** — custom rules > architecture.md > auto-detection\n- **Hybrid support** — projects mix styles; apply different presets per zone\n- **Custom = safe mode** — if no pattern detected, only check cycles + metrics (no false boundary violations)\n- **Internal only** — exclude stdlib, third-party from graph (only project modules)\n- **Baseline mode** — when baseline exists, report only NEW violations\n- **Cycle fixes** — always provide actionable recommendation (DIP, Extract Shared, Domain Events)\n- **File + line** — always provide exact import location for violations\n\n## Definition of Done\n\n**MANDATORY READ:** Load `shared\u002Freferences\u002Faudit_worker_core_contract.md`.\n\n- Architecture discovered (adaptive 3-tier detection applied)\n- Dependency graph built from import statements (internal modules only)\n- Circular dependencies detected (pairwise + transitive DFS + folder-level)\n- Boundary rules validated (forbidden + allowed + required)\n- Metrics calculated (Ca, Ce, I per module + CCD, NCCD aggregate)\n- SDP validated (stable modules not depending on unstable)\n- Baseline applied if exists (only new violations reported)\n- If domain-aware: all Grep\u002FGlob scoped to scan_path, findings tagged with domain\n- Score calculated per audit_scoring.md\n- Report written to `{output_dir}\u002F644-dep-graph[-{domain}].md` (atomic single Write call)\n- Summary returned to coordinator\n\n## Reference Files\n\n- Boundary rules & presets: `references\u002Fdependency_rules.md`\n- Metrics & thresholds: `references\u002Fgraph_metrics.md`\n- Import patterns: `references\u002Fimport_patterns.md`\n- Scoring algorithm: `shared\u002Freferences\u002Faudit_scoring.md`\n\n---\n\n**Version:** 1.0.0\n**Last Updated:** 2026-02-11\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# Dependency Graph Auditor\n\nL3 Worker that builds and analyzes the module dependency graph to enforce architectural boundaries.\n\n## Purpose & Scope\n\n- **Worker in ln-640 coordinator pipeline** - invoked by ln-640-pattern-evolution-auditor\n- Build module dependency graph from import statements (Python, TS\u002FJS, C#, Java)\n- Detect circular dependencies: pairwise (HIGH) + transitive via DFS (CRITICAL)\n- Validate boundary rules: forbidden, allowed, required (per dependency-cruiser pattern)\n- Calculate Robert C. Martin metrics (Ca, Ce, Instability) + Lakos aggregate (CCD, NCCD)\n- Validate Stable Dependencies Principle (SDP)\n- Support baseline\u002Ffreeze for incremental legacy adoption (per ArchUnit FreezingArchRule)\n- **Adaptive:** 3-tier architecture detection — custom rules > docs > auto-detect\n\n**Out of Scope** (owned by other workers):\n- I\u002FO isolation violations (grep-based) -> ln-642-layer-boundary-auditor\n- API contract violations -> ln-643-api-contract-auditor\n- Code duplication -> ln-623-code-principles-auditor\n\n## Input (from ln-640)\n\n```\n- architecture_path: string    # Path to docs\u002Farchitecture.md\n- codebase_root: string        # Root directory to scan\n- output_dir: string           # e.g., \"docs\u002Fproject\u002F.audit\u002Fln-640\u002F{YYYY-MM-DD}\"\n\n# Domain-aware (optional, from coordinator)\n- domain_mode: \"global\" | \"domain-aware\"   # Default: \"global\"\n- current_domain: string                   # e.g., \"users\", \"billing\" (only if domain-aware)\n- scan_path: string                        # e.g., \"src\u002Fusers\u002F\" (only if domain-aware)\n\n# Baseline (optional)\n- update_baseline: boolean                 # If true, save current state as baseline\n```\n\n**When domain_mode=\"domain-aware\":** Use `scan_path` instead of `codebase_root` for all Grep\u002FGlob operations. Tag all findings with `domain` field.\n\n## Workflow\n\n**MANDATORY READ:** Load `shared\u002Freferences\u002Ftwo_layer_detection.md` for detection methodology.\n\n### Phase 1: Discover Architecture (Adaptive)\n\n**MANDATORY READ:** Load `references\u002Fdependency_rules.md` — use 3-Tier Priority Chain, Architecture Presets, Auto-Detection Heuristics.\n\nArchitecture detection uses **3-tier priority** — explicit config wins over docs, docs win over auto-detection:\n\n```\n# Priority 1: Explicit project config\nIF docs\u002Fproject\u002Fdependency_rules.yaml exists:\n  Load custom rules (modules, forbidden, allowed, required)\n  SKIP preset detection\n\n# Priority 2: Architecture documentation\nELIF docs\u002Farchitecture.md exists:\n  Read Section 4.2 (modules, layers, architecture_type)\n  Read Section 6.4 (boundary rules, if defined)\n  Map documented layers to presets from dependency_rules.md\n  Apply preset rules, override with explicit rules from Section 6.4\n\n# Priority 3: Auto-detection from directory structure\nELSE:\n  scan_root = scan_path IF domain_mode == \"domain-aware\" ELSE codebase_root\n  Run structure heuristics:\n\n  signals = {}\n  IF Glob(\"**\u002Fdomain\u002F**\") AND Glob(\"**\u002Finfrastructure\u002F**\"):\n    signals[\"clean\"] = HIGH\n  IF Glob(\"**\u002Fcontrollers\u002F**\") AND Glob(\"**\u002Fservices\u002F**\") AND Glob(\"**\u002Frepositories\u002F**\"):\n    signals[\"layered\"] = HIGH\n  IF Glob(\"**\u002Ffeatures\u002F*\u002F\") with internal structure:\n    signals[\"vertical\"] = HIGH\n  IF Glob(\"**\u002Fadapters\u002F**\") AND Glob(\"**\u002Fports\u002F**\"):\n    signals[\"hexagonal\"] = HIGH\n  IF Glob(\"**\u002Fviews\u002F**\") AND Glob(\"**\u002Fmodels\u002F**\"):\n    signals[\"mvc\"] = HIGH\n\n  IF len(signals) == 0:\n    architecture_mode = \"custom\"\n    confidence = \"LOW\"\n    # Only check cycles + metrics, no boundary presets\n  ELIF len(signals) == 1:\n    architecture_mode = signals.keys()[0]\n    confidence = signals.values()[0]\n    Apply matching preset from dependency_rules.md\n  ELSE:\n    architecture_mode = \"hybrid\"\n    confidence = \"MEDIUM\"\n    # Identify zones, apply different presets per zone (see dependency_rules.md Hybrid section)\n    FOR EACH detected_style IN signals:\n      zone_path = identify_zone(detected_style)\n      zone_preset = load_preset(detected_style)\n      zones.append({path: zone_path, preset: zone_preset})\n    Add cross-zone rules: inner zones accessible, outer zones forbidden to depend on inner\n```\n\n### Phase 2: Build Dependency Graph\n\n**MANDATORY READ:** Load `references\u002Fimport_patterns.md` — use Language Detection, Import Grep Patterns, Module Resolution Algorithm, Exclusion Lists.\n\n```\nscan_root = scan_path IF domain_mode == \"domain-aware\" ELSE codebase_root\n\n# Step 1: Detect primary language\ntech_stack = Read(docs\u002Fproject\u002Ftech_stack.md) IF exists\n  ELSE detect from file extensions: Glob(\"**\u002F*.py\", \"**\u002F*.ts\", \"**\u002F*.cs\", \"**\u002F*.java\", root=scan_root)\n\n# Step 2: Extract imports per language\nFOR EACH source_file IN Glob(language_glob_pattern, root=scan_root):\n  imports = []\n\n  # Python\n  IF language == \"python\":\n    from_imports = Grep(\"^from\\s+([\\w.]+)\\s+import\", source_file)\n    plain_imports = Grep(\"^import\\s+([\\w.]+)\", source_file)\n    imports = from_imports + plain_imports\n\n  # TypeScript \u002F JavaScript\n  ELIF language == \"typescript\" OR language == \"javascript\":\n    es6_imports = Grep(\"import\\s+.*\\s+from\\s+['\\\"]([^'\\\"]+)['\\\"]\", source_file)\n    require_imports = Grep(\"require\\(['\\\"]([^'\\\"]+)['\\\"]\\)\", source_file)\n    imports = es6_imports + require_imports\n\n  # C#\n  ELIF language == \"csharp\":\n    using_imports = Grep(\"^using\\s+([\\w.]+);\", source_file)\n    imports = using_imports\n\n  # Java\n  ELIF language == \"java\":\n    java_imports = Grep(\"^import\\s+([\\w.]+);\", source_file)\n    imports = java_imports\n\n  # Step 3: Filter internal only (per import_patterns.md Exclusion Lists)\n  internal_imports = filter_internal(imports, scan_root)\n\n  # Step 4: Resolve to modules\n  FOR EACH imp IN internal_imports:\n    source_module = resolve_module(source_file, scan_root)\n    target_module = resolve_module(imp, scan_root)\n    IF source_module != target_module:\n      graph[source_module].add(target_module)\n```\n\n### Phase 3: Detect Cycles (ADP)\n\nPer Robert C. Martin (Clean Architecture Ch14): \"Allow no cycles in the component dependency graph.\"\n\n```\n# Pairwise cycles (A \u003C-> B)\nFOR EACH (A, B) WHERE B IN graph[A] AND A IN graph[B]:\n  cycles.append({\n    type: \"pairwise\",\n    path: [A, B, A],\n    severity: \"HIGH\",\n    fix: suggest_cycle_fix(A, B)\n  })\n  # Layer 2: Test-only dependencies (devDependencies, test imports) → skip cycle\n  # Plugin\u002Fextension architecture with documented bidirectional design → downgrade to LOW\n\n# Transitive cycles via DFS (A -> B -> C -> A)\nvisited = {}\nrec_stack = {}\n\nFUNCTION dfs(node, path):\n  visited[node] = true\n  rec_stack[node] = true\n\n  FOR EACH neighbor IN graph[node]:\n    IF NOT visited[neighbor]:\n      dfs(neighbor, path + [node])\n    ELIF rec_stack[neighbor]:\n      cycle_path = extract_cycle(path + [node], neighbor)\n      IF len(cycle_path) > 2:  # Skip pairwise (already detected)\n        cycles.append({\n          type: \"transitive\",\n          path: cycle_path,\n          severity: \"CRITICAL\",\n          fix: suggest_cycle_fix_transitive(cycle_path)\n        })\n\n  rec_stack[node] = false\n\nFOR EACH module IN graph:\n  IF NOT visited[module]:\n    dfs(module, [])\n\n# Folder-level cycles (per dependency-cruiser pattern)\nfolder_graph = collapse_to_folders(graph)\nRepeat DFS on folder_graph for folder-level cycles\n```\n\n**Cycle-breaking recommendations** (from Clean Architecture Ch14):\n1. **DIP** — extract interface in depended-upon module, implement in depending module\n2. **Extract Shared Component** — move shared code to new module both depend on\n3. **Domain Events \u002F Message Bus** — for cross-domain cycles, decouple via async communication\n\n### Phase 4: Validate Boundary Rules\n\n```\n# Load rules from Phase 1 discovery\n# rules = {forbidden: [], allowed: [], required: []}\n\n# Check FORBIDDEN rules\nFOR EACH rule IN rules.forbidden:\n  FOR EACH edge (source -> target) IN graph:\n    IF matches(source, rule.from) AND matches(target, rule.to):\n      IF rule.cross AND same_group(source, target):\n        CONTINUE  # cross=true means only cross-group violations\n      boundary_violations.append({\n        rule_type: \"forbidden\",\n        from: source,\n        to: target,\n        file: get_import_location(source, target),\n        severity: rule.severity,\n        reason: rule.reason\n      })\n\n# Check ALLOWED rules (whitelist mode)\nIF rules.allowed.length > 0:\n  FOR EACH edge (source -> target) IN graph:\n    allowed = false\n    FOR EACH rule IN rules.allowed:\n      IF matches(source, rule.from) AND matches(target, rule.to):\n        allowed = true\n        BREAK\n    IF NOT allowed:\n      boundary_violations.append({\n        rule_type: \"not_in_allowed\",\n        from: source,\n        to: target,\n        file: get_import_location(source, target),\n        severity: \"MEDIUM\",\n        reason: \"Dependency not in allowed list\"\n      })\n\n# Check REQUIRED rules\nFOR EACH rule IN rules.required:\n  FOR EACH module IN graph WHERE matches(module, rule.module):\n    has_required = false\n    FOR EACH dep IN graph[module]:\n      IF matches(dep, rule.must_depend_on):\n        has_required = true\n        BREAK\n    IF NOT has_required:\n      boundary_violations.append({\n        rule_type: \"required_missing\",\n        module: module,\n        missing: rule.must_depend_on,\n        severity: \"MEDIUM\",\n        reason: rule.reason\n      })\n```\n\n### Phase 5: Calculate Graph Metrics\n\n**MANDATORY READ:** Load `references\u002Fgraph_metrics.md` — use Metric Definitions, Thresholds per Layer, SDP Algorithm, Lakos Formulas.\n\n```\n# Per-module metrics (Robert C. Martin)\nFOR EACH module IN graph:\n  Ce = len(graph[module])                          # Efferent: outgoing\n  Ca = count(m for m in graph if module in graph[m])  # Afferent: incoming\n  I = Ce \u002F (Ca + Ce) IF (Ca + Ce) > 0 ELSE 0      # Instability\n\n  metrics[module] = {Ca, Ce, I}\n\n# SDP validation (Stable Dependencies Principle)\nFOR EACH edge (A -> B) IN graph:\n  IF metrics[A].I \u003C metrics[B].I:\n    # Stable module depends on less stable module — SDP violation\n    sdp_violations.append({\n      from: A, to: B,\n      I_from: metrics[A].I, I_to: metrics[B].I,\n      severity: \"HIGH\"\n    })\n\n# Threshold checks (per graph_metrics.md, considering detected layer)\nFOR EACH module IN metrics:\n  layer = get_layer(module)  # From Phase 1 discovery\n  thresholds = get_thresholds(layer)  # From graph_metrics.md\n\n  IF metrics[module].I > thresholds.max_instability:\n    findings.append({severity: thresholds.severity, issue: f\"{module} instability {I} exceeds {thresholds.max_instability}\"})\n  IF metrics[module].Ce > thresholds.max_ce:\n    findings.append({severity: \"MEDIUM\", issue: f\"{module} efferent coupling {Ce} exceeds {thresholds.max_ce}\"})\n\n# Lakos aggregate metrics\nCCD = 0\nFOR EACH module IN graph:\n  DependsOn = count_transitive_deps(module, graph) + 1  # Including self\n  CCD += DependsOn\n\nN = len(graph)\nCCD_balanced = N * log2(N)  # CCD of balanced binary tree with N nodes\nNCCD = CCD \u002F CCD_balanced IF CCD_balanced > 0 ELSE 0\n\nIF NCCD > 1.5:\n  findings.append({severity: \"MEDIUM\", issue: f\"Graph complexity (NCCD={NCCD:.2f}) exceeds balanced tree threshold (1.5)\"})\n```\n\n**Cascade chain extension:** For service files (`**\u002Fservices\u002F**`), extend module-level graph to function-level. Find longest side-effect chain per public function (markers per `shared\u002Freferences\u002Fai_ready_architecture.md`). If chain_length >= 3: add to cascade_findings. Output `\"runtime_cascades\"` array in Phase 8 DATA-EXTENDED JSON. Severity: HIGH (4+), MEDIUM (3).\n\n### Phase 6: Baseline Support\n\nInspired by ArchUnit FreezingArchRule — enables incremental adoption in legacy projects.\n\n```\nbaseline_path = docs\u002Fproject\u002Fdependency_baseline.json\n\nIF file_exists(baseline_path):\n  known = load_json(baseline_path)\n  current = serialize_violations(cycles + boundary_violations + sdp_violations)\n\n  new_violations = current - known\n  resolved_violations = known - current\n\n  # Report only NEW violations as findings\n  active_findings = new_violations\n  baseline_info = {new: len(new_violations), resolved: len(resolved_violations), frozen: len(known - resolved_violations)}\n\n  IF input.update_baseline == true:\n    save_json(baseline_path, current)\n\nELSE:\n  # First run — report all\n  active_findings = all_violations\n  baseline_info = {new: len(all_violations), resolved: 0, frozen: 0}\n  # Suggest: output note \"Run with update_baseline=true to freeze current violations\"\n```\n\n### Phase 7: Calculate Score\n\n**MANDATORY READ:** Load `shared\u002Freferences\u002Faudit_worker_core_contract.md` and `shared\u002Freferences\u002Faudit_scoring.md`.\n\n```\npenalty = (critical * 2.0) + (high * 1.0) + (medium * 0.5) + (low * 0.2)\nscore = max(0, 10 - penalty)\n```\n\n**Note:** When baseline is active, penalty is calculated from `active_findings` only (new violations), not frozen ones.\n\n### Phase 8: Write Report\n\n**MANDATORY READ:** Load `shared\u002Freferences\u002Faudit_worker_core_contract.md` and `shared\u002Ftemplates\u002Faudit_worker_report_template.md`.\n\n```\n# Build markdown report in memory with:\n# - AUDIT-META (standard penalty-based: score, counts)\n# - Checks table (cycle_detection, boundary_rules, sdp_validation, metrics_thresholds, baseline_comparison)\n# - Findings table (active violations sorted by severity)\n# - DATA-EXTENDED: {graph_stats, cycles, boundary_violations, sdp_violations, metrics, baseline}\n\nIF domain_mode == \"domain-aware\":\n  Write to {output_dir}\u002F644-dep-graph-{current_domain}.md\nELSE:\n  Write to {output_dir}\u002F644-dep-graph.md\n```\n\n### Phase 9: Return Summary\n\n```\nReport written: docs\u002Fproject\u002F.audit\u002Fln-640\u002F{YYYY-MM-DD}\u002F644-dep-graph-users.md\nScore: 6.5\u002F10 | Issues: 8 (C:1 H:3 M:3 L:1)\n```\n\n## Critical Rules\n\n**MANDATORY READ:** Load `shared\u002Freferences\u002Faudit_worker_core_contract.md`.\n\n- **Adaptive architecture** — never assume one style; detect from project structure or docs\n- **3-tier priority** — custom rules > architecture.md > auto-detection\n- **Hybrid support** — projects mix styles; apply different presets per zone\n- **Custom = safe mode** — if no pattern detected, only check cycles + metrics (no false boundary violations)\n- **Internal only** — exclude stdlib, third-party from graph (only project modules)\n- **Baseline mode** — when baseline exists, report only NEW violations\n- **Cycle fixes** — always provide actionable recommendation (DIP, Extract Shared, Domain Events)\n- **File + line** — always provide exact import location for violations\n\n## Definition of Done\n\n**MANDATORY READ:** Load `shared\u002Freferences\u002Faudit_worker_core_contract.md`.\n\n- Architecture discovered (adaptive 3-tier detection applied)\n- Dependency graph built from import statements (internal modules only)\n- Circular dependencies detected (pairwise + transitive DFS + folder-level)\n- Boundary rules validated (forbidden + allowed + required)\n- Metrics calculated (Ca, Ce, I per module + CCD, NCCD aggregate)\n- SDP validated (stable modules not depending on unstable)\n- Baseline applied if exists (only new violations reported)\n- If domain-aware: all Grep\u002FGlob scoped to scan_path, findings tagged with domain\n- Score calculated per audit_scoring.md\n- Report written to `{output_dir}\u002F644-dep-graph[-{domain}].md` (atomic single Write call)\n- Summary returned to coordinator\n\n## Reference Files\n\n- Boundary rules & presets: `references\u002Fdependency_rules.md`\n- Metrics & thresholds: `references\u002Fgraph_metrics.md`\n- Import patterns: `references\u002Fimport_patterns.md`\n- Scoring algorithm: `shared\u002Freferences\u002Faudit_scoring.md`\n\n---\n\n**Version:** 1.0.0\n**Last Updated:** 2026-02-11\n",{"name":5,"license":15,"description":7},"main","fa638b97a18ff6d9f26cf0eaf3dfa123531bcc87","organized-skills\u002Fln-644-dependency-graph-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":44,"prompt":54,"zipAvailable":55},[45,48,51],{"tool":46,"command":47},"npx","npx skills add levalencia\u002Fagent-god-mode --skill ln-644-dependency-graph-auditor",{"tool":49,"command":50},"bunx","bunx skills add levalencia\u002Fagent-god-mode --skill ln-644-dependency-graph-auditor",{"tool":52,"command":53},"pnpm","pnpm dlx skills add levalencia\u002Fagent-god-mode --skill ln-644-dependency-graph-auditor","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Flevalencia\u002Fagent-god-mode\u002Fblob\u002Fmain\u002Forganized-skills\u002Fln-644-dependency-graph-auditor\u002FSKILL.md",true,[57,63,67],{"path":58,"resourceType":59,"resourceTypeDesc":60,"sizeBytes":61,"sourceHtmlUrl":62},"references\u002Fdependency_rules.md","REFERENCE","参考文档",6747,"https:\u002F\u002Fgithub.com\u002Flevalencia\u002Fagent-god-mode\u002Fblob\u002Fmain\u002Forganized-skills\u002Fln-644-dependency-graph-auditor\u002Freferences\u002Fdependency_rules.md",{"path":64,"resourceType":59,"resourceTypeDesc":60,"sizeBytes":65,"sourceHtmlUrl":66},"references\u002Fgraph_metrics.md",3486,"https:\u002F\u002Fgithub.com\u002Flevalencia\u002Fagent-god-mode\u002Fblob\u002Fmain\u002Forganized-skills\u002Fln-644-dependency-graph-auditor\u002Freferences\u002Fgraph_metrics.md",{"path":68,"resourceType":59,"resourceTypeDesc":60,"sizeBytes":69,"sourceHtmlUrl":70},"references\u002Fimport_patterns.md",5469,"https:\u002F\u002Fgithub.com\u002Flevalencia\u002Fagent-god-mode\u002Fblob\u002Fmain\u002Forganized-skills\u002Fln-644-dependency-graph-auditor\u002Freferences\u002Fimport_patterns.md",[72,94,132,159,185,213],{"skillNo":73,"name":74,"nameZh":6,"description":75,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":76,"categories":77,"keywords":78,"publishedAt":29},"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",[],[79,80,81,82,83,84,85,86,87,88,89,90,91,92,93],"python","zarr python","storage","integration","s3","gcs","cloud","dask","parallel","pipelines","arrays","numpy","scientific computing","scale","scientific",{"skillNo":95,"name":96,"nameZh":6,"description":97,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":98,"categories":99,"keywords":113,"publishedAt":29},"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",[100,105,108],{"categoryNo":101,"categoryName":102,"taxonomyType":103,"taxonomyTypeDesc":104},"01JBSEEDCAT000000000000010","后端与接口","SCENARIO","使用场景",{"categoryNo":106,"categoryName":107,"taxonomyType":103,"taxonomyTypeDesc":104},"01JBSEEDCAT000000000000023","Skill与智能体开发",{"categoryNo":109,"categoryName":110,"taxonomyType":111,"taxonomyTypeDesc":112},"01JBSEEDCAT000000000000030","开发工程师","PROFESSION","适用职业",[96,79,114,115,116,117,118,119,120,121,122,123,124,125,126,127,128,129,130,131],"automation","window management","monitoring","data","templates","api","system","operations","use","maintenance","objects","permission","bulk operations","triggers","host","events","via","bulk",{"skillNo":133,"name":134,"nameZh":6,"description":135,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":136,"categories":137,"keywords":138,"publishedAt":29},"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",[],[139,140,141,142,143,144,145,146,147,148,149,150,151,152,153,154,155,156,157,158],"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":160,"name":161,"nameZh":6,"description":162,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":163,"categories":164,"keywords":165,"publishedAt":29},"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",[],[166,167,168,169,170,171,172,173,174,175,176,177,122,178,179,180,181,182,183,184],"oracle","what if oracle","test","planning","ux","futures","risk","analysis","explore","decision","branch","question","exploration","options","stress-test","strategies","trigger","case","multi",{"skillNo":186,"name":187,"nameZh":6,"description":188,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":189,"categories":190,"keywords":194,"publishedAt":29},"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",[191],{"categoryNo":192,"categoryName":193,"taxonomyType":103,"taxonomyTypeDesc":104},"01JBSEEDCAT000000000000009","前端开发",[195,196,197,198,199,200,201,202,203,204,205,206,207,117,208,209,210,211,212,127],"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":214,"name":215,"nameZh":6,"description":216,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":217,"categories":218,"keywords":229,"publishedAt":29},"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",[219,222,225,226],{"categoryNo":220,"categoryName":221,"taxonomyType":103,"taxonomyTypeDesc":104},"01JBSEEDCAT000000000000018","写作与文案",{"categoryNo":223,"categoryName":224,"taxonomyType":103,"taxonomyTypeDesc":104},"01JBSEEDCAT000000000000021","资料检索与研究",{"categoryNo":106,"categoryName":107,"taxonomyType":103,"taxonomyTypeDesc":104},{"categoryNo":227,"categoryName":228,"taxonomyType":111,"taxonomyTypeDesc":112},"01JBSEEDCAT000000000000036","内容创作者",[118,230,231,204,232,233,234,235,236,237,238,150,239,240,241,242,243,244,93,245],"venue templates","research","NeurIPS","ICML","LaTeX","science","Bash","access","read","edit","proposals","Academic","requirements","formatting","journal","chi"]