[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M77YK1QYWJWD5638PTHTHDB1":3,"skill-same:01M77YK1QYWJWD5638PTHTHDB1":74},{"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":51,"commitSha":52,"skillDirectory":53,"forksCount":54,"repositoryHtmlUrl":55,"repositoryHomepageUrl":56,"ownerHtmlUrl":57,"ownerBlogUrl":6,"ownerDescription":58,"updatedAt":59,"install":60,"resources":73},"01M77YK1QYWJWD5638PTHTHDB1","workflow-tools",null,"Work smarter with loop detection, parallel decisions, and file size analysis","Lord1Egypt\u002Fawesome-skill-forge","Lord1Egypt","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F99746359?v=4","01M7592YDNT0XK9WJ0T2MQVPDN","Mohamed Mounir Ali AL Keshita","01M75GRFNHC8VZNWEB8DKDE433",3,"MIT","https:\u002F\u002Fgithub.com\u002FLord1Egypt\u002Fawesome-skill-forge\u002Fblob\u002Fmaster\u002Fcommunity\u002Fclawhub\u002Fw\u002Fworkflow-tools\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: workflow-tools\nversion: 1.5.0\ndescription: Work smarter with loop detection, parallel decisions, and file size analysis\nauthor: Live Neon \u003Chello@liveneon.ai>\nhomepage: https:\u002F\u002Fgithub.com\u002Flive-neon\u002Fskills\u002Ftree\u002Fmain\u002Fagentic\u002Fworkflow-tools\nrepository: leegitw\u002Fworkflow-tools\nlicense: MIT\ntags: [agentic, workflow, automation, orchestration, parallel, decision-making, loops, task-management]\nlayer: extensions\nstatus: active\nalias: wt\nmetadata:\n  openclaw:\n    requires:\n      config:\n        - .openclaw\u002Fworkflow-tools.yaml\n        - .claude\u002Fworkflow-tools.yaml\n      workspace:\n        - output\u002Floops\u002F\n        - output\u002Fparallel-decisions\u002F\n        - output\u002Fmce-analysis\u002F\n        - output\u002Fsubworkflows\u002F\n---\n\n# workflow-tools (工具)\n\nUnified skill for workflow utilities including open loop detection, parallel\u002Fserial\ndecision framework, MCE file analysis, and subworkflow spawning. Consolidates 4 skills.\n\n**Trigger**: 明示呼出 (explicit invocation)\n\n**Source skills**: loop-closer, parallel-decision, MCE (minimal-context-engineering), subworkflow-spawner\n\n**Removed**: pbd-strength-classifier (redundant with `\u002Ffm classify`)\n\n## Installation\n\n```bash\nopenclaw install leegitw\u002Fworkflow-tools\n```\n\n**Dependencies**:\n- `leegitw\u002Ffailure-memory` (for loop context)\n- `leegitw\u002Fconstraint-engine` (for enforcement context)\n\n```bash\n# Install with dependencies\nopenclaw install leegitw\u002Fcontext-verifier\nopenclaw install leegitw\u002Ffailure-memory\nopenclaw install leegitw\u002Fconstraint-engine\nopenclaw install leegitw\u002Fworkflow-tools\n```\n\n**Standalone usage**: Loop detection, parallel decisions, and MCE analysis work independently.\nFull integration provides constraint-aware workflow recommendations.\n\n**Data handling**: This skill operates within your agent's trust boundary. When triggered,\nit uses your agent's configured model for workflow analysis and decision support. No external APIs\nor third-party services are called. Results are written to `output\u002F` subdirectories in your workspace.\n\n**⚠️ File access**: This skill reads user-specified directories and files for analysis:\n- `\u002Fwt loops [path]` scans the specified directory (default: current working directory)\n- `\u002Fwt mce \u003Cfile>` reads the specified file for size analysis\nThe metadata declares only config and output paths. See Security Considerations for details.\n\n## What This Solves\n\nWorkflows accumulate friction — loops that never close, decisions about parallel vs serial execution, files that grow too large. This skill provides utilities for common workflow problems:\n\n1. **Loop detection** — find DEFERRED, PLACEHOLDER, and TODO markers before marking work complete\n2. **Parallel decisions** — 5-factor framework for when to parallelize vs serialize\n3. **MCE analysis** — identify files exceeding size thresholds, suggest splits\n\n**The insight**: Small tools that do one thing well. Don't overthink the workflow — detect, decide, analyze, move on.\n\n## Usage\n\n```\n\u002Fwt \u003Csub-command> [arguments]\n```\n\n## Sub-Commands\n\n| Command | CJK | Logic | Trigger |\n|---------|-----|-------|---------|\n| `\u002Fwt loops` | 循環 | scan(DEFERRED∨PLACEHOLDER∨TODO)→openloop[] | Explicit |\n| `\u002Fwt parallel` | 並列 | 5因子→serial∨parallel | Explicit |\n| `\u002Fwt mce` | 極限 | file.lines>200→split_suggestions[] | Explicit |\n| `\u002Fwt subworkflow` | 副流 | task→spawn(clawhub.skill) | Explicit |\n\n## Arguments\n\n### \u002Fwt loops\n\n| Argument | Required | Description |\n|----------|----------|-------------|\n| path | No | Directory to scan (default: current) |\n| --pattern | No | Custom patterns to detect (comma-separated) |\n| --exclude | No | Paths to exclude (comma-separated) |\n\n### \u002Fwt parallel\n\n| Argument | Required | Description |\n|----------|----------|-------------|\n| task | Yes | Description of task to evaluate |\n| --factors | No | Specific factors to evaluate (default: all 5) |\n\n### \u002Fwt mce\n\n| Argument | Required | Description |\n|----------|----------|-------------|\n| file | Yes | File to analyze |\n| --threshold | No | Line threshold (default: 200) |\n| --suggest | No | Generate split suggestions |\n\n### \u002Fwt subworkflow\n\n| Argument | Required | Description |\n|----------|----------|-------------|\n| task | Yes | Task description |\n| --skill | No | Specific ClawHub skill to use |\n| --background | No | Run in background |\n\n## Configuration\n\nConfiguration is loaded from (in order of precedence):\n1. `.openclaw\u002Fworkflow-tools.yaml` (OpenClaw standard)\n2. `.claude\u002Fworkflow-tools.yaml` (Claude Code compatibility)\n3. Defaults (built-in)\n\n```yaml\n# .openclaw\u002Fworkflow-tools.yaml\nloops:\n  patterns:                  # Patterns to detect as open loops\n    - \"TODO:\"\n    - \"FIXME:\"\n    - \"HACK:\"\n    - \"XXX:\"\n    - \"DEFERRED:\"\n    - \"PLACEHOLDER:\"\n  exclude:                   # Paths to exclude from scanning\n    - \"vendor\u002F\"\n    - \"node_modules\u002F\"\nmce:\n  threshold: 200             # Line threshold for MCE compliance\n  warning_threshold: 300     # Line threshold for warning\nparallel:\n  default_factors: 5         # Number of factors to evaluate\n```\n\n## Core Logic\n\n### Open Loop Detection\n\nScans for unclosed work items:\n\n| Pattern | Type | Example |\n|---------|------|---------|\n| `DEFERRED:` | Postponed work | `\u002F\u002F DEFERRED: handle edge case` |\n| `PLACEHOLDER:` | Temporary code | `\u002F\u002F PLACEHOLDER: implement auth` |\n| `TODO:` | Task marker | `\u002F\u002F TODO: add error handling` |\n| `FIXME:` | Bug marker | `\u002F\u002F FIXME: race condition` |\n| `HACK:` | Technical debt | `\u002F\u002F HACK: workaround for bug` |\n| `XXX:` | Attention needed | `\u002F\u002F XXX: review this logic` |\n\n### Parallel vs Serial Decision Framework\n\nFive factors determine parallel suitability:\n\n| Factor | Question | Parallel If | Serial If |\n|--------|----------|-------------|-----------|\n| **Team** | Can different people work on parts? | Independent parts | Shared expertise needed |\n| **Coupling** | How connected are the tasks? | Loose coupling | Tight coupling |\n| **Interface** | Are boundaries clear? | Well-defined | Fluid\u002Fevolving |\n| **Pattern** | Is approach consistent? | Divergent exploration | Convergent refinement |\n| **Integration** | How complex is merging? | Simple merge | Complex coordination |\n\nDecision matrix:\n\n| Factors favoring parallel | Recommendation |\n|---------------------------|----------------|\n| 5\u002F5 | Strongly parallel |\n| 4\u002F5 | Parallel with coordination checkpoints |\n| 3\u002F5 | Consider case-by-case |\n| 2\u002F5 | Serial with parallel sub-tasks |\n| 0-1\u002F5 | Serial |\n\n### MCE (Minimal Context Engineering)\n\nFile size thresholds for context efficiency:\n\n| Lines | Status | Action |\n|-------|--------|--------|\n| ≤200 | ✓ MCE compliant | No action needed |\n| 201-300 | ⚠ Approaching limit | Consider refactoring |\n| >300 | ✗ Exceeds MCE | Split recommended |\n\nSplit suggestions based on:\n- Function\u002Fmethod boundaries\n- Logical groupings\n- Import dependencies\n- Test coverage boundaries\n\n### Subworkflow Spawning\n\nDelegate tasks to specialized ClawHub skills:\n\n```\nTask → Skill Selection → Spawn → Monitor → Collect Results\n```\n\nAvailable skill categories:\n- `research-*`: Investigation and analysis\n- `generate-*`: Content generation\n- `validate-*`: Verification and testing\n- `transform-*`: Data transformation\n\n### Example: Deployment Workflow Analysis\n\n```\n\u002Fwt parallel \"Deploy new payment service to production\"\n[PARALLEL VS SERIAL ANALYSIS]\nTask: \"Deploy new payment service to production\"\n\nFactor Analysis:\n1. Team: ✗ Serial - Single SRE team handles deploys\n2. Coupling: ✗ Serial - Payment depends on auth service\n3. Interface: ✓ Parallel - Clear API contracts defined\n4. Pattern: ✗ Serial - Requires sequential rollout (canary → staging → prod)\n5. Integration: ✗ Serial - Payment gateway integration must be verified\n\nScore: 1\u002F5 factors favor parallel\nRecommendation: SERIAL deployment\nRationale: High-risk service requiring careful sequential verification.\n```\n\n### Example: Infrastructure Loop Detection\n\n```\n\u002Fwt loops infra\u002F --pattern \"MANUAL:,HARDCODED:\"\n[OPEN LOOPS DETECTED]\nScanned: .\u002Finfra\nFiles checked: 23\n\nInfrastructure Issues (5):\n  infra\u002Fterraform\u002Fmain.tf:45  HARDCODED: AWS region\n  infra\u002Fk8s\u002Fdeployment.yaml:78  MANUAL: replica count\n  infra\u002Fdocker\u002FDockerfile:12  TODO: multi-stage build\n  infra\u002Fscripts\u002Fdeploy.sh:34  FIXME: rollback not implemented\n  infra\u002Fhelm\u002Fvalues.yaml:56  PLACEHOLDER: production secrets\n\nSummary: 2 high, 2 medium, 1 low priority\nAction: Address HARDCODED and FIXME before next release.\n```\n\n## Output\n\n### \u002Fwt loops output\n\n```\n[OPEN LOOPS DETECTED]\nScanned: .\u002Fsrc\nFiles checked: 47\n\nOpen loops found (12):\n\nHigh Priority (FIXME, XXX):\n  src\u002Fauth\u002Fhandler.go:45  FIXME: race condition in token refresh\n  src\u002Fapi\u002Fclient.go:123   XXX: review error handling\n\nMedium Priority (TODO):\n  src\u002Fhandlers\u002Fuser.go:78  TODO: add input validation\n  src\u002Fdb\u002Fqueries.go:234    TODO: optimize query\n  src\u002Futils\u002Fhash.go:12     TODO: add caching\n\nLow Priority (DEFERRED, PLACEHOLDER):\n  src\u002Fconfig\u002Floader.go:89  DEFERRED: support YAML config\n  src\u002Ftemplates\u002Femail.go:34 PLACEHOLDER: email templates\n  ...\n\nSummary: 2 high, 5 medium, 5 low priority loops\nAction: Address high priority loops before release.\n```\n\n### \u002Fwt parallel output\n\n```\n[PARALLEL VS SERIAL ANALYSIS]\nTask: \"Implement authentication and authorization\"\n\nFactor Analysis:\n\n1. Team (独立性):\n   ✓ Parallel - Auth and authz can be assigned separately\n\n2. Coupling (結合度):\n   ✗ Serial - Authz depends on auth tokens\n\n3. Interface (境界):\n   ✓ Parallel - Clear token interface between them\n\n4. Pattern (手法):\n   ✓ Parallel - Both follow established patterns\n\n5. Integration (統合):\n   ✗ Serial - Token format must match exactly\n\nScore: 3\u002F5 factors favor parallel\n\nRecommendation: SERIAL with parallel sub-tasks\nRationale: Core dependency between auth and authz, but sub-components\n           within each can be developed in parallel.\n\nSuggested approach:\n1. Define token interface (serial, required first)\n2. Implement auth + authz (parallel, once interface stable)\n3. Integration testing (serial, final step)\n```\n\n### \u002Fwt mce output\n\n```\n[MCE ANALYSIS]\nFile: src\u002Fhandlers\u002Fuser.go\nLines: 347\n\nStatus: ✗ EXCEEDS MCE THRESHOLD (200 lines)\n\nComplexity Analysis:\n  Functions: 12\n  Avg function length: 29 lines\n  Max function length: 67 lines (HandleUserUpdate)\n  Import groups: 4\n\nSplit Suggestions:\n\n1. Extract CRUD handlers (lines 45-180):\n   → src\u002Fhandlers\u002Fuser_crud.go (~135 lines)\n   - CreateUser, GetUser, UpdateUser, DeleteUser\n\n2. Extract validation (lines 181-250):\n   → src\u002Fhandlers\u002Fuser_validation.go (~70 lines)\n   - ValidateUserInput, ValidateEmail, ValidatePassword\n\n3. Keep orchestration (remaining):\n   → src\u002Fhandlers\u002Fuser.go (~142 lines)\n   - Handler setup, middleware, routing\n\nAfter split: 3 files, all ≤200 lines ✓\n```\n\n### \u002Fwt subworkflow output\n\n```\n[SUBWORKFLOW SPAWNED]\nTask: \"Research competitor authentication implementations\"\nSkill: research-web-analysis\nStatus: Running in background\n\nJob ID: SW-20260215-001\nMonitor: \u002Fwt subworkflow --status SW-20260215-001\n\nExpected completion: ~5 minutes\nResults will be written to: output\u002Fsubworkflows\u002FSW-20260215-001\u002F\n```\n\n## Integration\n\n- **Layer**: Extensions\n- **Depends on**: failure-memory (for loop context), constraint-engine (for enforcement context)\n- **Used by**: governance (for loop detection), review-orchestrator (for parallel decisions)\n\n## Failure Modes\n\n| Condition | Behavior |\n|-----------|----------|\n| Invalid sub-command | List available sub-commands |\n| File not found | Error: \"File not found: {path}\" |\n| No patterns found | Info: \"No open loops detected\" |\n| Skill not available | Error: \"Skill not found: {skill}\" |\n\n## Next Steps\n\nAfter invoking this skill:\n\n| Condition | Action |\n|-----------|--------|\n| Loops found | Prioritize and address high-priority loops |\n| Parallel recommended | Create parallel work streams |\n| MCE exceeded | Apply split suggestions |\n| Subworkflow complete | Review and integrate results |\n\n## Workspace Files\n\nThis skill reads\u002Fwrites:\n\n```\noutput\u002F\n├── loops\u002F\n│   └── scan-YYYY-MM-DD.md    # Loop scan results\n├── parallel-decisions\u002F\n│   └── task-YYYY-MM-DD.md    # Decision records\n├── mce-analysis\u002F\n│   └── file-YYYY-MM-DD.md    # MCE analysis results\n└── subworkflows\u002F\n    └── SW-YYYYMMDD-XXX\u002F      # Subworkflow outputs\n        ├── status.json\n        └── results.md\n```\n\n## Security Considerations\n\n**What this skill accesses:**\n- Configuration files in `.openclaw\u002Fworkflow-tools.yaml` and `.claude\u002Fworkflow-tools.yaml`\n- **User-specified directories** via `\u002Fwt loops [path]` — scans for patterns (read-only)\n- **User-specified files** via `\u002Fwt mce \u003Cfile>` — reads for size analysis (read-only)\n- Its own output directories (write):\n  - `output\u002Floops\u002F` — loop scan results\n  - `output\u002Fparallel-decisions\u002F` — decision records\n  - `output\u002Fmce-analysis\u002F` — file analysis results\n  - `output\u002Fsubworkflows\u002F` — subworkflow outputs\n\n**⚠️ IMPORTANT**: The metadata declares only config and output paths. However, `\u002Fwt loops` and\n`\u002Fwt mce` read **arbitrary user-specified paths** beyond the declared metadata. This is by\ndesign — analysis requires reading the files\u002Fdirectories you want to analyze.\n\n**What this skill does NOT access:**\n- System environment variables\n- Network resources or external APIs\n\n**What this skill does NOT do:**\n- Send data to external services\n- Execute arbitrary code\n- Modify source files (analysis is read-only)\n\n**⚠️ Path scanning (`\u002Fwt loops`):**\nThe `\u002Fwt loops` command accepts an arbitrary directory path argument. It will recursively\nscan the specified directory for loop patterns (TODO, FIXME, etc.). This is a read-only\noperation but can scan any directory you have filesystem access to. The skill does NOT\nrestrict which paths can be scanned — use caution with sensitive directories. Consider\nusing `--exclude` to skip sensitive paths.\n\n**Subworkflow spawning (`\u002Fwt subworkflow`):**\nThe `\u002Fwt subworkflow` command spawns other ClawHub skills installed in your environment.\n- **Scope**: Can invoke any skill installed via `openclaw install`\n- **Permissions**: Spawned skills execute with their own declared permissions (not elevated)\n- **Categories**: Typically `research-*`, `generate-*`, `validate-*`, `transform-*` skills\n- **Risk**: The effective permission footprint is the union of this skill plus any spawned skills\n\nReview your installed skills (`openclaw list`) to understand the combined permission scope\nwhen using subworkflow spawning.\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- [ ] `\u002Fwt loops` detects all standard loop patterns\n- [ ] `\u002Fwt loops` categorizes by priority (high\u002Fmedium\u002Flow)\n- [ ] `\u002Fwt parallel` evaluates all 5 factors\n- [ ] `\u002Fwt parallel` provides clear recommendation with rationale\n- [ ] `\u002Fwt mce` identifies files exceeding threshold\n- [ ] `\u002Fwt mce --suggest` generates actionable split suggestions\n- [ ] `\u002Fwt subworkflow` spawns ClawHub skills correctly\n- [ ] `\u002Fwt subworkflow` supports background execution\n- [ ] Results written to workspace files\n\n---\n\n*Consolidated from 4 skills as part of agentic skills consolidation (2026-02-15).*\n","# workflow-tools (工具)\n\nUnified skill for workflow utilities including open loop detection, parallel\u002Fserial\ndecision framework, MCE file analysis, and subworkflow spawning. Consolidates 4 skills.\n\n**Trigger**: 明示呼出 (explicit invocation)\n\n**Source skills**: loop-closer, parallel-decision, MCE (minimal-context-engineering), subworkflow-spawner\n\n**Removed**: pbd-strength-classifier (redundant with `\u002Ffm classify`)\n\n## Installation\n\n```bash\nopenclaw install leegitw\u002Fworkflow-tools\n```\n\n**Dependencies**:\n- `leegitw\u002Ffailure-memory` (for loop context)\n- `leegitw\u002Fconstraint-engine` (for enforcement context)\n\n```bash\n# Install with dependencies\nopenclaw install leegitw\u002Fcontext-verifier\nopenclaw install leegitw\u002Ffailure-memory\nopenclaw install leegitw\u002Fconstraint-engine\nopenclaw install leegitw\u002Fworkflow-tools\n```\n\n**Standalone usage**: Loop detection, parallel decisions, and MCE analysis work independently.\nFull integration provides constraint-aware workflow recommendations.\n\n**Data handling**: This skill operates within your agent's trust boundary. When triggered,\nit uses your agent's configured model for workflow analysis and decision support. No external APIs\nor third-party services are called. Results are written to `output\u002F` subdirectories in your workspace.\n\n**⚠️ File access**: This skill reads user-specified directories and files for analysis:\n- `\u002Fwt loops [path]` scans the specified directory (default: current working directory)\n- `\u002Fwt mce \u003Cfile>` reads the specified file for size analysis\nThe metadata declares only config and output paths. See Security Considerations for details.\n\n## What This Solves\n\nWorkflows accumulate friction — loops that never close, decisions about parallel vs serial execution, files that grow too large. This skill provides utilities for common workflow problems:\n\n1. **Loop detection** — find DEFERRED, PLACEHOLDER, and TODO markers before marking work complete\n2. **Parallel decisions** — 5-factor framework for when to parallelize vs serialize\n3. **MCE analysis** — identify files exceeding size thresholds, suggest splits\n\n**The insight**: Small tools that do one thing well. Don't overthink the workflow — detect, decide, analyze, move on.\n\n## Usage\n\n```\n\u002Fwt \u003Csub-command> [arguments]\n```\n\n## Sub-Commands\n\n| Command | CJK | Logic | Trigger |\n|---------|-----|-------|---------|\n| `\u002Fwt loops` | 循環 | scan(DEFERRED∨PLACEHOLDER∨TODO)→openloop[] | Explicit |\n| `\u002Fwt parallel` | 並列 | 5因子→serial∨parallel | Explicit |\n| `\u002Fwt mce` | 極限 | file.lines>200→split_suggestions[] | Explicit |\n| `\u002Fwt subworkflow` | 副流 | task→spawn(clawhub.skill) | Explicit |\n\n## Arguments\n\n### \u002Fwt loops\n\n| Argument | Required | Description |\n|----------|----------|-------------|\n| path | No | Directory to scan (default: current) |\n| --pattern | No | Custom patterns to detect (comma-separated) |\n| --exclude | No | Paths to exclude (comma-separated) |\n\n### \u002Fwt parallel\n\n| Argument | Required | Description |\n|----------|----------|-------------|\n| task | Yes | Description of task to evaluate |\n| --factors | No | Specific factors to evaluate (default: all 5) |\n\n### \u002Fwt mce\n\n| Argument | Required | Description |\n|----------|----------|-------------|\n| file | Yes | File to analyze |\n| --threshold | No | Line threshold (default: 200) |\n| --suggest | No | Generate split suggestions |\n\n### \u002Fwt subworkflow\n\n| Argument | Required | Description |\n|----------|----------|-------------|\n| task | Yes | Task description |\n| --skill | No | Specific ClawHub skill to use |\n| --background | No | Run in background |\n\n## Configuration\n\nConfiguration is loaded from (in order of precedence):\n1. `.openclaw\u002Fworkflow-tools.yaml` (OpenClaw standard)\n2. `.claude\u002Fworkflow-tools.yaml` (Claude Code compatibility)\n3. Defaults (built-in)\n\n```yaml\n# .openclaw\u002Fworkflow-tools.yaml\nloops:\n  patterns:                  # Patterns to detect as open loops\n    - \"TODO:\"\n    - \"FIXME:\"\n    - \"HACK:\"\n    - \"XXX:\"\n    - \"DEFERRED:\"\n    - \"PLACEHOLDER:\"\n  exclude:                   # Paths to exclude from scanning\n    - \"vendor\u002F\"\n    - \"node_modules\u002F\"\nmce:\n  threshold: 200             # Line threshold for MCE compliance\n  warning_threshold: 300     # Line threshold for warning\nparallel:\n  default_factors: 5         # Number of factors to evaluate\n```\n\n## Core Logic\n\n### Open Loop Detection\n\nScans for unclosed work items:\n\n| Pattern | Type | Example |\n|---------|------|---------|\n| `DEFERRED:` | Postponed work | `\u002F\u002F DEFERRED: handle edge case` |\n| `PLACEHOLDER:` | Temporary code | `\u002F\u002F PLACEHOLDER: implement auth` |\n| `TODO:` | Task marker | `\u002F\u002F TODO: add error handling` |\n| `FIXME:` | Bug marker | `\u002F\u002F FIXME: race condition` |\n| `HACK:` | Technical debt | `\u002F\u002F HACK: workaround for bug` |\n| `XXX:` | Attention needed | `\u002F\u002F XXX: review this logic` |\n\n### Parallel vs Serial Decision Framework\n\nFive factors determine parallel suitability:\n\n| Factor | Question | Parallel If | Serial If |\n|--------|----------|-------------|-----------|\n| **Team** | Can different people work on parts? | Independent parts | Shared expertise needed |\n| **Coupling** | How connected are the tasks? | Loose coupling | Tight coupling |\n| **Interface** | Are boundaries clear? | Well-defined | Fluid\u002Fevolving |\n| **Pattern** | Is approach consistent? | Divergent exploration | Convergent refinement |\n| **Integration** | How complex is merging? | Simple merge | Complex coordination |\n\nDecision matrix:\n\n| Factors favoring parallel | Recommendation |\n|---------------------------|----------------|\n| 5\u002F5 | Strongly parallel |\n| 4\u002F5 | Parallel with coordination checkpoints |\n| 3\u002F5 | Consider case-by-case |\n| 2\u002F5 | Serial with parallel sub-tasks |\n| 0-1\u002F5 | Serial |\n\n### MCE (Minimal Context Engineering)\n\nFile size thresholds for context efficiency:\n\n| Lines | Status | Action |\n|-------|--------|--------|\n| ≤200 | ✓ MCE compliant | No action needed |\n| 201-300 | ⚠ Approaching limit | Consider refactoring |\n| >300 | ✗ Exceeds MCE | Split recommended |\n\nSplit suggestions based on:\n- Function\u002Fmethod boundaries\n- Logical groupings\n- Import dependencies\n- Test coverage boundaries\n\n### Subworkflow Spawning\n\nDelegate tasks to specialized ClawHub skills:\n\n```\nTask → Skill Selection → Spawn → Monitor → Collect Results\n```\n\nAvailable skill categories:\n- `research-*`: Investigation and analysis\n- `generate-*`: Content generation\n- `validate-*`: Verification and testing\n- `transform-*`: Data transformation\n\n### Example: Deployment Workflow Analysis\n\n```\n\u002Fwt parallel \"Deploy new payment service to production\"\n[PARALLEL VS SERIAL ANALYSIS]\nTask: \"Deploy new payment service to production\"\n\nFactor Analysis:\n1. Team: ✗ Serial - Single SRE team handles deploys\n2. Coupling: ✗ Serial - Payment depends on auth service\n3. Interface: ✓ Parallel - Clear API contracts defined\n4. Pattern: ✗ Serial - Requires sequential rollout (canary → staging → prod)\n5. Integration: ✗ Serial - Payment gateway integration must be verified\n\nScore: 1\u002F5 factors favor parallel\nRecommendation: SERIAL deployment\nRationale: High-risk service requiring careful sequential verification.\n```\n\n### Example: Infrastructure Loop Detection\n\n```\n\u002Fwt loops infra\u002F --pattern \"MANUAL:,HARDCODED:\"\n[OPEN LOOPS DETECTED]\nScanned: .\u002Finfra\nFiles checked: 23\n\nInfrastructure Issues (5):\n  infra\u002Fterraform\u002Fmain.tf:45  HARDCODED: AWS region\n  infra\u002Fk8s\u002Fdeployment.yaml:78  MANUAL: replica count\n  infra\u002Fdocker\u002FDockerfile:12  TODO: multi-stage build\n  infra\u002Fscripts\u002Fdeploy.sh:34  FIXME: rollback not implemented\n  infra\u002Fhelm\u002Fvalues.yaml:56  PLACEHOLDER: production secrets\n\nSummary: 2 high, 2 medium, 1 low priority\nAction: Address HARDCODED and FIXME before next release.\n```\n\n## Output\n\n### \u002Fwt loops output\n\n```\n[OPEN LOOPS DETECTED]\nScanned: .\u002Fsrc\nFiles checked: 47\n\nOpen loops found (12):\n\nHigh Priority (FIXME, XXX):\n  src\u002Fauth\u002Fhandler.go:45  FIXME: race condition in token refresh\n  src\u002Fapi\u002Fclient.go:123   XXX: review error handling\n\nMedium Priority (TODO):\n  src\u002Fhandlers\u002Fuser.go:78  TODO: add input validation\n  src\u002Fdb\u002Fqueries.go:234    TODO: optimize query\n  src\u002Futils\u002Fhash.go:12     TODO: add caching\n\nLow Priority (DEFERRED, PLACEHOLDER):\n  src\u002Fconfig\u002Floader.go:89  DEFERRED: support YAML config\n  src\u002Ftemplates\u002Femail.go:34 PLACEHOLDER: email templates\n  ...\n\nSummary: 2 high, 5 medium, 5 low priority loops\nAction: Address high priority loops before release.\n```\n\n### \u002Fwt parallel output\n\n```\n[PARALLEL VS SERIAL ANALYSIS]\nTask: \"Implement authentication and authorization\"\n\nFactor Analysis:\n\n1. Team (独立性):\n   ✓ Parallel - Auth and authz can be assigned separately\n\n2. Coupling (結合度):\n   ✗ Serial - Authz depends on auth tokens\n\n3. Interface (境界):\n   ✓ Parallel - Clear token interface between them\n\n4. Pattern (手法):\n   ✓ Parallel - Both follow established patterns\n\n5. Integration (統合):\n   ✗ Serial - Token format must match exactly\n\nScore: 3\u002F5 factors favor parallel\n\nRecommendation: SERIAL with parallel sub-tasks\nRationale: Core dependency between auth and authz, but sub-components\n           within each can be developed in parallel.\n\nSuggested approach:\n1. Define token interface (serial, required first)\n2. Implement auth + authz (parallel, once interface stable)\n3. Integration testing (serial, final step)\n```\n\n### \u002Fwt mce output\n\n```\n[MCE ANALYSIS]\nFile: src\u002Fhandlers\u002Fuser.go\nLines: 347\n\nStatus: ✗ EXCEEDS MCE THRESHOLD (200 lines)\n\nComplexity Analysis:\n  Functions: 12\n  Avg function length: 29 lines\n  Max function length: 67 lines (HandleUserUpdate)\n  Import groups: 4\n\nSplit Suggestions:\n\n1. Extract CRUD handlers (lines 45-180):\n   → src\u002Fhandlers\u002Fuser_crud.go (~135 lines)\n   - CreateUser, GetUser, UpdateUser, DeleteUser\n\n2. Extract validation (lines 181-250):\n   → src\u002Fhandlers\u002Fuser_validation.go (~70 lines)\n   - ValidateUserInput, ValidateEmail, ValidatePassword\n\n3. Keep orchestration (remaining):\n   → src\u002Fhandlers\u002Fuser.go (~142 lines)\n   - Handler setup, middleware, routing\n\nAfter split: 3 files, all ≤200 lines ✓\n```\n\n### \u002Fwt subworkflow output\n\n```\n[SUBWORKFLOW SPAWNED]\nTask: \"Research competitor authentication implementations\"\nSkill: research-web-analysis\nStatus: Running in background\n\nJob ID: SW-20260215-001\nMonitor: \u002Fwt subworkflow --status SW-20260215-001\n\nExpected completion: ~5 minutes\nResults will be written to: output\u002Fsubworkflows\u002FSW-20260215-001\u002F\n```\n\n## Integration\n\n- **Layer**: Extensions\n- **Depends on**: failure-memory (for loop context), constraint-engine (for enforcement context)\n- **Used by**: governance (for loop detection), review-orchestrator (for parallel decisions)\n\n## Failure Modes\n\n| Condition | Behavior |\n|-----------|----------|\n| Invalid sub-command | List available sub-commands |\n| File not found | Error: \"File not found: {path}\" |\n| No patterns found | Info: \"No open loops detected\" |\n| Skill not available | Error: \"Skill not found: {skill}\" |\n\n## Next Steps\n\nAfter invoking this skill:\n\n| Condition | Action |\n|-----------|--------|\n| Loops found | Prioritize and address high-priority loops |\n| Parallel recommended | Create parallel work streams |\n| MCE exceeded | Apply split suggestions |\n| Subworkflow complete | Review and integrate results |\n\n## Workspace Files\n\nThis skill reads\u002Fwrites:\n\n```\noutput\u002F\n├── loops\u002F\n│   └── scan-YYYY-MM-DD.md    # Loop scan results\n├── parallel-decisions\u002F\n│   └── task-YYYY-MM-DD.md    # Decision records\n├── mce-analysis\u002F\n│   └── file-YYYY-MM-DD.md    # MCE analysis results\n└── subworkflows\u002F\n    └── SW-YYYYMMDD-XXX\u002F      # Subworkflow outputs\n        ├── status.json\n        └── results.md\n```\n\n## Security Considerations\n\n**What this skill accesses:**\n- Configuration files in `.openclaw\u002Fworkflow-tools.yaml` and `.claude\u002Fworkflow-tools.yaml`\n- **User-specified directories** via `\u002Fwt loops [path]` — scans for patterns (read-only)\n- **User-specified files** via `\u002Fwt mce \u003Cfile>` — reads for size analysis (read-only)\n- Its own output directories (write):\n  - `output\u002Floops\u002F` — loop scan results\n  - `output\u002Fparallel-decisions\u002F` — decision records\n  - `output\u002Fmce-analysis\u002F` — file analysis results\n  - `output\u002Fsubworkflows\u002F` — subworkflow outputs\n\n**⚠️ IMPORTANT**: The metadata declares only config and output paths. However, `\u002Fwt loops` and\n`\u002Fwt mce` read **arbitrary user-specified paths** beyond the declared metadata. This is by\ndesign — analysis requires reading the files\u002Fdirectories you want to analyze.\n\n**What this skill does NOT access:**\n- System environment variables\n- Network resources or external APIs\n\n**What this skill does NOT do:**\n- Send data to external services\n- Execute arbitrary code\n- Modify source files (analysis is read-only)\n\n**⚠️ Path scanning (`\u002Fwt loops`):**\nThe `\u002Fwt loops` command accepts an arbitrary directory path argument. It will recursively\nscan the specified directory for loop patterns (TODO, FIXME, etc.). This is a read-only\noperation but can scan any directory you have filesystem access to. The skill does NOT\nrestrict which paths can be scanned — use caution with sensitive directories. Consider\nusing `--exclude` to skip sensitive paths.\n\n**Subworkflow spawning (`\u002Fwt subworkflow`):**\nThe `\u002Fwt subworkflow` command spawns other ClawHub skills installed in your environment.\n- **Scope**: Can invoke any skill installed via `openclaw install`\n- **Permissions**: Spawned skills execute with their own declared permissions (not elevated)\n- **Categories**: Typically `research-*`, `generate-*`, `validate-*`, `transform-*` skills\n- **Risk**: The effective permission footprint is the union of this skill plus any spawned skills\n\nReview your installed skills (`openclaw list`) to understand the combined permission scope\nwhen using subworkflow spawning.\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- [ ] `\u002Fwt loops` detects all standard loop patterns\n- [ ] `\u002Fwt loops` categorizes by priority (high\u002Fmedium\u002Flow)\n- [ ] `\u002Fwt parallel` evaluates all 5 factors\n- [ ] `\u002Fwt parallel` provides clear recommendation with rationale\n- [ ] `\u002Fwt mce` identifies files exceeding threshold\n- [ ] `\u002Fwt mce --suggest` generates actionable split suggestions\n- [ ] `\u002Fwt subworkflow` spawns ClawHub skills correctly\n- [ ] `\u002Fwt subworkflow` supports background execution\n- [ ] Results written to workspace files\n\n---\n\n*Consolidated from 4 skills as part of agentic skills consolidation (2026-02-15).*\n",{"name":5,"tags":24,"alias":33,"layer":34,"author":35,"status":36,"license":15,"version":37,"homepage":38,"metadata":39,"repository":50,"description":7},[25,26,27,28,29,30,31,32],"agentic","workflow","automation","orchestration","parallel","decision-making","loops","task-management","wt","extensions","Live Neon \u003Chello@liveneon.ai>","active","1.5.0","https:\u002F\u002Fgithub.com\u002Flive-neon\u002Fskills\u002Ftree\u002Fmain\u002Fagentic\u002Fworkflow-tools",{"openclaw":40},{"requires":41},{"config":42,"workspace":45},[43,44],".openclaw\u002Fworkflow-tools.yaml",".claude\u002Fworkflow-tools.yaml",[46,47,48,49],"output\u002Floops\u002F","output\u002Fparallel-decisions\u002F","output\u002Fmce-analysis\u002F","output\u002Fsubworkflows\u002F","leegitw\u002Fworkflow-tools","master","4aa004da461d820f4ea5499e58eb8d196cf99016","community\u002Fclawhub\u002Fw\u002Fworkflow-tools",0,"https:\u002F\u002Fgithub.com\u002FLord1Egypt\u002Fawesome-skill-forge","https:\u002F\u002Fskill-explorer-rho.vercel.app","https:\u002F\u002Fgithub.com\u002FLord1Egypt","Unbreakable. Unstoppable. Unmatched⚡.\r\n Speaker of machine tongues 🤖  | World-builder of decentralized dreams 🌐 | Defender of the digital realm🛡️.","2026-06-10 08:21:01",{"source":8,"skillName":5,"commands":61,"prompt":71,"zipAvailable":72},[62,65,68],{"tool":63,"command":64},"npx","npx skills add Lord1Egypt\u002Fawesome-skill-forge --skill workflow-tools",{"tool":66,"command":67},"bunx","bunx skills add Lord1Egypt\u002Fawesome-skill-forge --skill workflow-tools",{"tool":69,"command":70},"pnpm","pnpm dlx skills add Lord1Egypt\u002Fawesome-skill-forge --skill workflow-tools","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FLord1Egypt\u002Fawesome-skill-forge\u002Fblob\u002Fmaster\u002Fcommunity\u002Fclawhub\u002Fw\u002Fworkflow-tools\u002FSKILL.md",true,[],[75,82,89,96,103,110],{"skillNo":76,"name":77,"nameZh":6,"description":78,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":79,"categories":80,"keywords":81,"publishedAt":19},"01M785WKJB99G3STR1NF9NRTJW","youtube-content","YouTube transcripts to summaries, threads, blogs.","https:\u002F\u002Fgithub.com\u002FLord1Egypt\u002Fawesome-skill-forge\u002Fblob\u002Fmaster\u002Fskills\u002Fyoutube-content\u002FSKILL.md",[],[],{"skillNo":83,"name":84,"nameZh":6,"description":85,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":86,"categories":87,"keywords":88,"publishedAt":19},"01M785WEFHB0G2S9YA6EPR3H0E","xurl","X\u002FTwitter via xurl CLI: post, search, DM, media, v2 API.","https:\u002F\u002Fgithub.com\u002FLord1Egypt\u002Fawesome-skill-forge\u002Fblob\u002Fmaster\u002Fskills\u002Fxurl\u002FSKILL.md",[],[],{"skillNo":90,"name":91,"nameZh":6,"description":92,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":93,"categories":94,"keywords":95,"publishedAt":19},"01M785W98EDN4EFJXJPMQEHCRC","touchdesigner-mcp","Control a running TouchDesigner instance via twozero MCP — create operators, set parameters, wire connections, execute Python, build real-time visuals. 36 native tools.","https:\u002F\u002Fgithub.com\u002FLord1Egypt\u002Fawesome-skill-forge\u002Fblob\u002Fmaster\u002Fskills\u002Ftouchdesigner-mcp\u002FSKILL.md",[],[],{"skillNo":97,"name":98,"nameZh":6,"description":99,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":100,"categories":101,"keywords":102,"publishedAt":19},"01M785W5S9FP3QBH2V191E025P","test-driven-development","TDD: enforce RED-GREEN-REFACTOR, tests before code.","https:\u002F\u002Fgithub.com\u002FLord1Egypt\u002Fawesome-skill-forge\u002Fblob\u002Fmaster\u002Fskills\u002Ftest-driven-development\u002FSKILL.md",[],[],{"skillNo":104,"name":105,"nameZh":6,"description":106,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":107,"categories":108,"keywords":109,"publishedAt":19},"01M785W2AS08NSSH9YATCV6FJB","teams-meeting-pipeline","Operate the Teams meeting summary pipeline via Hermes CLI — summarize meetings, inspect pipeline status, replay jobs, manage Microsoft Graph subscriptions.","https:\u002F\u002Fgithub.com\u002FLord1Egypt\u002Fawesome-skill-forge\u002Fblob\u002Fmaster\u002Fskills\u002Fteams-meeting-pipeline\u002FSKILL.md",[],[],{"skillNo":111,"name":112,"nameZh":6,"description":113,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":114,"categories":115,"keywords":116,"publishedAt":19},"01M785VXKW4T34BTP1SCHW1R7F","systematic-debugging","4-phase root cause debugging: understand bugs before fixing.","https:\u002F\u002Fgithub.com\u002FLord1Egypt\u002Fawesome-skill-forge\u002Fblob\u002Fmaster\u002Fskills\u002Fsystematic-debugging\u002FSKILL.md",[],[]]