[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6CYQMCS3B2ZCXG92VR5RY0X":3,"skill-same:01M6CYQMCS3B2ZCXG92VR5RY0X":103},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":16,"categories":17,"keywords":23,"publishedAt":41,"linkOnly":42,"markdownContent":43,"markdownBody":44,"frontMatter":45,"refName":47,"commitSha":48,"skillDirectory":49,"forksCount":50,"repositoryHtmlUrl":51,"repositoryHomepageUrl":52,"ownerHtmlUrl":53,"ownerBlogUrl":54,"ownerDescription":55,"updatedAt":56,"install":57,"resources":70},"01M6CYQMCS3B2ZCXG92VR5RY0X","simulation-orchestrator",null,"Orchestrate multi-simulation campaigns including parameter sweeps, batch jobs, and result aggregation. Use for running parameter studies, managing simulation batches, tracking job status, combining results from multiple runs, or automating simulation workflows.","eric861129\u002FSKILLS_All-in-one","eric861129","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F74950944?v=4","01M6CXHDYEYRPFGGV4EFXCSYCF","ChiYu-Huang","01M6CXHE2J5CN1EBTY0FKV3ZKW",52,"MIT","https:\u002F\u002Fgithub.com\u002Feric861129\u002FSKILLS_All-in-one\u002Fblob\u002Fmain\u002Fpublic\u002FSKILLS\u002FScientific & Research Tools\u002Fsimulation-orchestrator\u002FSKILL.md",[18],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000023","Skill与智能体开发","SCENARIO","使用场景",[24,25,26,27,28,29,30,31,32,33,34,35,36,37,38,39,40],"simulation orchestrator","simulation","orchestrator","read","campaigns","jobs","use","tracking","results","write","workflows","grep","Bash","aggregation","orchestrate","batch","status","2026-11-10 10:12:30",false,"---\nname: simulation-orchestrator\ndescription: Orchestrate multi-simulation campaigns including parameter sweeps, batch jobs, and result aggregation. Use for running parameter studies, managing simulation batches, tracking job status, combining results from multiple runs, or automating simulation workflows.\nallowed-tools: Read, Bash, Write, Grep, Glob\n---\n\n# Simulation Orchestrator\n\n## Goal\n\nProvide tools to manage multi-simulation campaigns: generate parameter sweeps, track job execution status, and aggregate results from completed runs.\n\n## Requirements\n\n- Python 3.10+\n- No external dependencies (uses Python standard library only)\n- Works on Linux, macOS, and Windows\n\n## Inputs to Gather\n\nBefore running orchestration scripts, collect from the user:\n\n| Input | Description | Example |\n|-------|-------------|---------|\n| Base config | Template simulation configuration | `base_config.json` |\n| Parameter ranges | Parameters to sweep with bounds | `dt:[1e-4,1e-2],kappa:[0.1,1.0]` |\n| Sweep method | How to sample parameter space | `grid`, `lhs`, `linspace` |\n| Output directory | Where to store campaign files | `.\u002Fcampaign_001` |\n| Simulation command | Command to run each simulation | `python sim.py --config {config}` |\n\n## Decision Guidance\n\n### Choosing a Sweep Method\n\n```\nNeed every combination (full factorial)?\n├── YES → Use grid (warning: exponential growth with parameters)\n└── NO → Is space-filling coverage needed?\n    ├── YES → Use lhs (Latin Hypercube Sampling)\n    └── NO → Use linspace for uniform sampling per parameter\n```\n\n| Method | Best For | Sample Count |\n|--------|----------|--------------|\n| `grid` | Low dimensions (1-3), need exact corners | n^d (exponential) |\n| `linspace` | 1D sweeps, uniform spacing | n per parameter |\n| `lhs` | High dimensions, space-filling | user-specified budget |\n\n### Campaign Size Guidelines\n\n| Parameters | Grid Points Each | Total Runs | Recommendation |\n|------------|------------------|------------|----------------|\n| 1 | 10 | 10 | Grid is fine |\n| 2 | 10 | 100 | Grid acceptable |\n| 3 | 10 | 1,000 | Consider LHS |\n| 4+ | 10 | 10,000+ | Use LHS or DOE |\n\n## Script Outputs (JSON Fields)\n\n| Script | Output Fields |\n|--------|---------------|\n| `scripts\u002Fsweep_generator.py` | `configs`, `parameter_space`, `sweep_method`, `total_runs` |\n| `scripts\u002Fcampaign_manager.py` | `campaign_id`, `status`, `jobs`, `progress` |\n| `scripts\u002Fjob_tracker.py` | `job_id`, `status`, `start_time`, `end_time`, `exit_code` |\n| `scripts\u002Fresult_aggregator.py` | `summary`, `statistics`, `best_run`, `failed_runs` |\n\n## Workflow\n\n### Step 1: Generate Parameter Sweep\n\nCreate configurations for all parameter combinations:\n\n```bash\npython3 scripts\u002Fsweep_generator.py \\\n    --base-config base_config.json \\\n    --params \"dt:1e-4:1e-2:5,kappa:0.1:1.0:3\" \\\n    --method linspace \\\n    --output-dir .\u002Fcampaign_001 \\\n    --json\n```\n\n### Step 2: Initialize Campaign\n\nCreate campaign tracking structure:\n\n```bash\npython3 scripts\u002Fcampaign_manager.py \\\n    --action init \\\n    --config-dir .\u002Fcampaign_001 \\\n    --command \"python sim.py --config {config}\" \\\n    --json\n```\n\n### Step 3: Track Job Status\n\nMonitor running jobs:\n\n```bash\npython3 scripts\u002Fjob_tracker.py \\\n    --campaign-dir .\u002Fcampaign_001 \\\n    --update \\\n    --json\n```\n\n### Step 4: Aggregate Results\n\nCombine results from completed runs:\n\n```bash\npython3 scripts\u002Fresult_aggregator.py \\\n    --campaign-dir .\u002Fcampaign_001 \\\n    --metric objective_value \\\n    --json\n```\n\n## CLI Examples\n\n```bash\n# Generate 5x3=15 runs varying dt (5 values) and kappa (3 values)\npython3 scripts\u002Fsweep_generator.py \\\n    --base-config sim.json \\\n    --params \"dt:1e-4:1e-2:5,kappa:0.1:1.0:3\" \\\n    --method linspace \\\n    --output-dir .\u002Fsweep_001 \\\n    --json\n\n# Generate LHS samples for 4 parameters with budget of 20 runs\npython3 scripts\u002Fsweep_generator.py \\\n    --base-config sim.json \\\n    --params \"dt:1e-4:1e-2,kappa:0.1:1.0,M:1e-6:1e-4,W:0.5:2.0\" \\\n    --method lhs \\\n    --samples 20 \\\n    --output-dir .\u002Flhs_001 \\\n    --json\n\n# Check campaign status\npython3 scripts\u002Fcampaign_manager.py \\\n    --action status \\\n    --config-dir .\u002Fsweep_001 \\\n    --json\n\n# Get summary statistics from completed runs\npython3 scripts\u002Fresult_aggregator.py \\\n    --campaign-dir .\u002Fsweep_001 \\\n    --metric final_energy \\\n    --json\n```\n\n## Conversational Workflow Example\n\n**User**: I want to run a parameter sweep on dt and kappa for my phase-field simulation. I want to try 5 values of dt between 1e-4 and 1e-2, and 4 values of kappa between 0.1 and 1.0.\n\n**Agent workflow**:\n1. Calculate total runs: 5 x 4 = 20 runs\n2. Generate sweep configurations:\n   ```bash\n   python3 scripts\u002Fsweep_generator.py \\\n       --base-config simulation.json \\\n       --params \"dt:1e-4:1e-2:5,kappa:0.1:1.0:4\" \\\n       --method linspace \\\n       --output-dir .\u002Fdt_kappa_sweep \\\n       --json\n   ```\n3. Initialize campaign:\n   ```bash\n   python3 scripts\u002Fcampaign_manager.py \\\n       --action init \\\n       --config-dir .\u002Fdt_kappa_sweep \\\n       --command \"python phase_field.py --config {config}\" \\\n       --json\n   ```\n4. After user runs simulations, aggregate results:\n   ```bash\n   python3 scripts\u002Fresult_aggregator.py \\\n       --campaign-dir .\u002Fdt_kappa_sweep \\\n       --metric interface_width \\\n       --json\n   ```\n\n## Error Handling\n\n| Error | Cause | Resolution |\n|-------|-------|------------|\n| `Base config not found` | Invalid file path | Verify base config file exists |\n| `Invalid parameter format` | Malformed param string | Use format `name:min:max:count` or `name:min:max` |\n| `Output directory exists` | Would overwrite | Use `--force` or choose new directory |\n| `No completed jobs` | No results to aggregate | Wait for jobs to complete or check for failures |\n| `Metric not found` | Result files missing field | Verify metric name in result JSON |\n\n## Integration with Other Skills\n\nThe simulation-orchestrator works with other simulation-workflow skills:\n\n```\nparameter-optimization          simulation-orchestrator\n        │                              │\n        │ DOE samples ────────────────>│ Generate configs\n        │                              │\n        │                              │ Run simulations\n        │                              │\n        │\u003C──────────────────────────── │ Aggregate results\n        │                              │\n        │ Sensitivity analysis         │\n        │ Optimizer selection          │\n```\n\n### Typical Combined Workflow\n\n1. Use `parameter-optimization\u002Fdoe_generator.py` to get sample points\n2. Use `simulation-orchestrator\u002Fsweep_generator.py` to create configs\n3. Run simulations (user's responsibility)\n4. Use `simulation-orchestrator\u002Fresult_aggregator.py` to collect results\n5. Use `parameter-optimization\u002Fsensitivity_summary.py` to analyze\n\n## Limitations\n\n- **Not a job scheduler**: Does not submit jobs to SLURM\u002FPBS; generates configs and tracks status\n- **No parallel execution**: User must run simulations externally (can use GNU parallel, SLURM, etc.)\n- **File-based tracking**: Status tracked via files; no database or real-time monitoring\n- **Local filesystem**: Assumes all files accessible from local machine\n\n## References\n\n- `references\u002Fcampaign_patterns.md` - Common campaign structures\n- `references\u002Fsweep_strategies.md` - Parameter sweep design guidance\n- `references\u002Faggregation_methods.md` - Result aggregation techniques\n\n## Version History\n\n- **v1.0.0** (2024-12-24): Initial release with sweep, campaign, tracking, and aggregation\n","# Simulation Orchestrator\n\n## Goal\n\nProvide tools to manage multi-simulation campaigns: generate parameter sweeps, track job execution status, and aggregate results from completed runs.\n\n## Requirements\n\n- Python 3.10+\n- No external dependencies (uses Python standard library only)\n- Works on Linux, macOS, and Windows\n\n## Inputs to Gather\n\nBefore running orchestration scripts, collect from the user:\n\n| Input | Description | Example |\n|-------|-------------|---------|\n| Base config | Template simulation configuration | `base_config.json` |\n| Parameter ranges | Parameters to sweep with bounds | `dt:[1e-4,1e-2],kappa:[0.1,1.0]` |\n| Sweep method | How to sample parameter space | `grid`, `lhs`, `linspace` |\n| Output directory | Where to store campaign files | `.\u002Fcampaign_001` |\n| Simulation command | Command to run each simulation | `python sim.py --config {config}` |\n\n## Decision Guidance\n\n### Choosing a Sweep Method\n\n```\nNeed every combination (full factorial)?\n├── YES → Use grid (warning: exponential growth with parameters)\n└── NO → Is space-filling coverage needed?\n    ├── YES → Use lhs (Latin Hypercube Sampling)\n    └── NO → Use linspace for uniform sampling per parameter\n```\n\n| Method | Best For | Sample Count |\n|--------|----------|--------------|\n| `grid` | Low dimensions (1-3), need exact corners | n^d (exponential) |\n| `linspace` | 1D sweeps, uniform spacing | n per parameter |\n| `lhs` | High dimensions, space-filling | user-specified budget |\n\n### Campaign Size Guidelines\n\n| Parameters | Grid Points Each | Total Runs | Recommendation |\n|------------|------------------|------------|----------------|\n| 1 | 10 | 10 | Grid is fine |\n| 2 | 10 | 100 | Grid acceptable |\n| 3 | 10 | 1,000 | Consider LHS |\n| 4+ | 10 | 10,000+ | Use LHS or DOE |\n\n## Script Outputs (JSON Fields)\n\n| Script | Output Fields |\n|--------|---------------|\n| `scripts\u002Fsweep_generator.py` | `configs`, `parameter_space`, `sweep_method`, `total_runs` |\n| `scripts\u002Fcampaign_manager.py` | `campaign_id`, `status`, `jobs`, `progress` |\n| `scripts\u002Fjob_tracker.py` | `job_id`, `status`, `start_time`, `end_time`, `exit_code` |\n| `scripts\u002Fresult_aggregator.py` | `summary`, `statistics`, `best_run`, `failed_runs` |\n\n## Workflow\n\n### Step 1: Generate Parameter Sweep\n\nCreate configurations for all parameter combinations:\n\n```bash\npython3 scripts\u002Fsweep_generator.py \\\n    --base-config base_config.json \\\n    --params \"dt:1e-4:1e-2:5,kappa:0.1:1.0:3\" \\\n    --method linspace \\\n    --output-dir .\u002Fcampaign_001 \\\n    --json\n```\n\n### Step 2: Initialize Campaign\n\nCreate campaign tracking structure:\n\n```bash\npython3 scripts\u002Fcampaign_manager.py \\\n    --action init \\\n    --config-dir .\u002Fcampaign_001 \\\n    --command \"python sim.py --config {config}\" \\\n    --json\n```\n\n### Step 3: Track Job Status\n\nMonitor running jobs:\n\n```bash\npython3 scripts\u002Fjob_tracker.py \\\n    --campaign-dir .\u002Fcampaign_001 \\\n    --update \\\n    --json\n```\n\n### Step 4: Aggregate Results\n\nCombine results from completed runs:\n\n```bash\npython3 scripts\u002Fresult_aggregator.py \\\n    --campaign-dir .\u002Fcampaign_001 \\\n    --metric objective_value \\\n    --json\n```\n\n## CLI Examples\n\n```bash\n# Generate 5x3=15 runs varying dt (5 values) and kappa (3 values)\npython3 scripts\u002Fsweep_generator.py \\\n    --base-config sim.json \\\n    --params \"dt:1e-4:1e-2:5,kappa:0.1:1.0:3\" \\\n    --method linspace \\\n    --output-dir .\u002Fsweep_001 \\\n    --json\n\n# Generate LHS samples for 4 parameters with budget of 20 runs\npython3 scripts\u002Fsweep_generator.py \\\n    --base-config sim.json \\\n    --params \"dt:1e-4:1e-2,kappa:0.1:1.0,M:1e-6:1e-4,W:0.5:2.0\" \\\n    --method lhs \\\n    --samples 20 \\\n    --output-dir .\u002Flhs_001 \\\n    --json\n\n# Check campaign status\npython3 scripts\u002Fcampaign_manager.py \\\n    --action status \\\n    --config-dir .\u002Fsweep_001 \\\n    --json\n\n# Get summary statistics from completed runs\npython3 scripts\u002Fresult_aggregator.py \\\n    --campaign-dir .\u002Fsweep_001 \\\n    --metric final_energy \\\n    --json\n```\n\n## Conversational Workflow Example\n\n**User**: I want to run a parameter sweep on dt and kappa for my phase-field simulation. I want to try 5 values of dt between 1e-4 and 1e-2, and 4 values of kappa between 0.1 and 1.0.\n\n**Agent workflow**:\n1. Calculate total runs: 5 x 4 = 20 runs\n2. Generate sweep configurations:\n   ```bash\n   python3 scripts\u002Fsweep_generator.py \\\n       --base-config simulation.json \\\n       --params \"dt:1e-4:1e-2:5,kappa:0.1:1.0:4\" \\\n       --method linspace \\\n       --output-dir .\u002Fdt_kappa_sweep \\\n       --json\n   ```\n3. Initialize campaign:\n   ```bash\n   python3 scripts\u002Fcampaign_manager.py \\\n       --action init \\\n       --config-dir .\u002Fdt_kappa_sweep \\\n       --command \"python phase_field.py --config {config}\" \\\n       --json\n   ```\n4. After user runs simulations, aggregate results:\n   ```bash\n   python3 scripts\u002Fresult_aggregator.py \\\n       --campaign-dir .\u002Fdt_kappa_sweep \\\n       --metric interface_width \\\n       --json\n   ```\n\n## Error Handling\n\n| Error | Cause | Resolution |\n|-------|-------|------------|\n| `Base config not found` | Invalid file path | Verify base config file exists |\n| `Invalid parameter format` | Malformed param string | Use format `name:min:max:count` or `name:min:max` |\n| `Output directory exists` | Would overwrite | Use `--force` or choose new directory |\n| `No completed jobs` | No results to aggregate | Wait for jobs to complete or check for failures |\n| `Metric not found` | Result files missing field | Verify metric name in result JSON |\n\n## Integration with Other Skills\n\nThe simulation-orchestrator works with other simulation-workflow skills:\n\n```\nparameter-optimization          simulation-orchestrator\n        │                              │\n        │ DOE samples ────────────────>│ Generate configs\n        │                              │\n        │                              │ Run simulations\n        │                              │\n        │\u003C──────────────────────────── │ Aggregate results\n        │                              │\n        │ Sensitivity analysis         │\n        │ Optimizer selection          │\n```\n\n### Typical Combined Workflow\n\n1. Use `parameter-optimization\u002Fdoe_generator.py` to get sample points\n2. Use `simulation-orchestrator\u002Fsweep_generator.py` to create configs\n3. Run simulations (user's responsibility)\n4. Use `simulation-orchestrator\u002Fresult_aggregator.py` to collect results\n5. Use `parameter-optimization\u002Fsensitivity_summary.py` to analyze\n\n## Limitations\n\n- **Not a job scheduler**: Does not submit jobs to SLURM\u002FPBS; generates configs and tracks status\n- **No parallel execution**: User must run simulations externally (can use GNU parallel, SLURM, etc.)\n- **File-based tracking**: Status tracked via files; no database or real-time monitoring\n- **Local filesystem**: Assumes all files accessible from local machine\n\n## References\n\n- `references\u002Fcampaign_patterns.md` - Common campaign structures\n- `references\u002Fsweep_strategies.md` - Parameter sweep design guidance\n- `references\u002Faggregation_methods.md` - Result aggregation techniques\n\n## Version History\n\n- **v1.0.0** (2024-12-24): Initial release with sweep, campaign, tracking, and aggregation\n",{"name":5,"description":7,"allowed-tools":46},"Read, Bash, Write, Grep, Glob","main","cbdd44aae21131521c09e42762e36178c790eacf","public\u002FSKILLS\u002FScientific & Research Tools\u002Fsimulation-orchestrator",13,"https:\u002F\u002Fgithub.com\u002Feric861129\u002FSKILLS_All-in-one","http:\u002F\u002Fhuangchiyu.com\u002FSKILLS_All-in-one\u002F","https:\u002F\u002Fgithub.com\u002Feric861129","https:\u002F\u002Fhuangchiyu.com\u002FChiYu-Blog\u002F","開發工程師，專注於 C#／.NET 系統現代化、AI-assisted engineering、開源工具與技術寫作。","2026-04-16 14:28:14",{"source":8,"skillName":5,"commands":58,"prompt":68,"zipAvailable":69},[59,62,65],{"tool":60,"command":61},"npx","npx skills add eric861129\u002FSKILLS_All-in-one --skill simulation-orchestrator",{"tool":63,"command":64},"bunx","bunx skills add eric861129\u002FSKILLS_All-in-one --skill simulation-orchestrator",{"tool":66,"command":67},"pnpm","pnpm dlx skills add eric861129\u002FSKILLS_All-in-one --skill simulation-orchestrator","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Feric861129\u002FSKILLS_All-in-one\u002Fblob\u002Fmain\u002Fpublic\u002FSKILLS\u002FScientific & Research Tools\u002Fsimulation-orchestrator\u002FSKILL.md",true,[71,77,81,85,91,95,99],{"path":72,"resourceType":73,"resourceTypeDesc":74,"sizeBytes":75,"sourceHtmlUrl":76},"references\u002Faggregation_methods.md","REFERENCE","参考文档",4102,"https:\u002F\u002Fgithub.com\u002Feric861129\u002FSKILLS_All-in-one\u002Fblob\u002Fmain\u002Fpublic\u002FSKILLS\u002FScientific & Research Tools\u002Fsimulation-orchestrator\u002Freferences\u002Faggregation_methods.md",{"path":78,"resourceType":73,"resourceTypeDesc":74,"sizeBytes":79,"sourceHtmlUrl":80},"references\u002Fcampaign_patterns.md",3861,"https:\u002F\u002Fgithub.com\u002Feric861129\u002FSKILLS_All-in-one\u002Fblob\u002Fmain\u002Fpublic\u002FSKILLS\u002FScientific & Research Tools\u002Fsimulation-orchestrator\u002Freferences\u002Fcampaign_patterns.md",{"path":82,"resourceType":73,"resourceTypeDesc":74,"sizeBytes":83,"sourceHtmlUrl":84},"references\u002Fsweep_strategies.md",3335,"https:\u002F\u002Fgithub.com\u002Feric861129\u002FSKILLS_All-in-one\u002Fblob\u002Fmain\u002Fpublic\u002FSKILLS\u002FScientific & Research Tools\u002Fsimulation-orchestrator\u002Freferences\u002Fsweep_strategies.md",{"path":86,"resourceType":87,"resourceTypeDesc":88,"sizeBytes":89,"sourceHtmlUrl":90},"scripts\u002Fcampaign_manager.py","SCRIPT","脚本",8231,"https:\u002F\u002Fgithub.com\u002Feric861129\u002FSKILLS_All-in-one\u002Fblob\u002Fmain\u002Fpublic\u002FSKILLS\u002FScientific & Research Tools\u002Fsimulation-orchestrator\u002Fscripts\u002Fcampaign_manager.py",{"path":92,"resourceType":87,"resourceTypeDesc":88,"sizeBytes":93,"sourceHtmlUrl":94},"scripts\u002Fjob_tracker.py",9643,"https:\u002F\u002Fgithub.com\u002Feric861129\u002FSKILLS_All-in-one\u002Fblob\u002Fmain\u002Fpublic\u002FSKILLS\u002FScientific & Research Tools\u002Fsimulation-orchestrator\u002Fscripts\u002Fjob_tracker.py",{"path":96,"resourceType":87,"resourceTypeDesc":88,"sizeBytes":97,"sourceHtmlUrl":98},"scripts\u002Fresult_aggregator.py",9658,"https:\u002F\u002Fgithub.com\u002Feric861129\u002FSKILLS_All-in-one\u002Fblob\u002Fmain\u002Fpublic\u002FSKILLS\u002FScientific & Research Tools\u002Fsimulation-orchestrator\u002Fscripts\u002Fresult_aggregator.py",{"path":100,"resourceType":87,"resourceTypeDesc":88,"sizeBytes":101,"sourceHtmlUrl":102},"scripts\u002Fsweep_generator.py",10330,"https:\u002F\u002Fgithub.com\u002Feric861129\u002FSKILLS_All-in-one\u002Fblob\u002Fmain\u002Fpublic\u002FSKILLS\u002FScientific & Research Tools\u002Fsimulation-orchestrator\u002Fscripts\u002Fsweep_generator.py",[104,130,162,190,214,234],{"skillNo":105,"name":106,"nameZh":6,"description":107,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":108,"categories":109,"keywords":111,"publishedAt":41},"01M6CZ1WR3KNVTKSWH4GNWT646","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\u002Feric861129\u002FSKILLS_All-in-one\u002Fblob\u002Fmain\u002Fpublic\u002FSKILLS\u002FWriting & Research\u002Fwhat-if-oracle\u002FSKILL.md",[110],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},[112,113,114,115,116,117,118,119,120,121,122,123,124,27,33,125,126,127,128,129],"oracle","what if oracle","go","run","planning","ux","futures","risk","analysis","explore","decision","branch","question","idea","exploration","options","stress-test","strategies",{"skillNo":131,"name":132,"nameZh":6,"description":133,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":134,"categories":135,"keywords":148,"publishedAt":41},"01M6CZ1QHGJE91A95MSN5EK5Q9","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\u002Feric861129\u002FSKILLS_All-in-one\u002Fblob\u002Fmain\u002Fpublic\u002FSKILLS\u002FWriting & Research\u002Fvenue-templates\u002FSKILL.md",[136,139,142,143],{"categoryNo":137,"categoryName":138,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000018","写作与文案",{"categoryNo":140,"categoryName":141,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000021","资料检索与研究",{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},{"categoryNo":144,"categoryName":145,"taxonomyType":146,"taxonomyTypeDesc":147},"01JBSEEDCAT000000000000036","内容创作者","PROFESSION","适用职业",[149,150,151,152,153,154,155,156,36,157,27,33,158,159,160,161],"templates","venue templates","research","guidelines","NeurIPS","ICML","LaTeX","science","access","edit","proposals","Academic","requirements",{"skillNo":163,"name":164,"nameZh":6,"description":165,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":166,"categories":167,"keywords":172,"publishedAt":41},"01M6CZ1KBQD2E5RTFB3BGVX7CD","the-fool","Use when challenging ideas, plans, decisions, or proposals using structured critical reasoning. Invoke to play devil's advocate, run a pre-mortem, red team, or audit evidence and assumptions.","https:\u002F\u002Fgithub.com\u002Feric861129\u002FSKILLS_All-in-one\u002Fblob\u002Fmain\u002Fpublic\u002FSKILLS\u002FWriting & Research\u002Fthe-fool\u002FSKILL.md",[168,169],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},{"categoryNo":170,"categoryName":171,"taxonomyType":146,"taxonomyTypeDesc":147},"01JBSEEDCAT000000000000030","开发工程师",[173,174,114,175,176,115,177,178,179,180,181,182,183,184,159,185,186,187,188,189],"the fool","review","workflow","architecture","code","audit","forge","devil","team","designer","reviewer","challenge","stress test","evidence","expert","poke","ideas",{"skillNo":191,"name":192,"nameZh":6,"description":193,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":194,"categories":195,"keywords":199,"publishedAt":41},"01M6CZ1ES826S7P1X3333E40TA","scientific-writing","Core skill for the deep research and writing tool. Write scientific manuscripts in full paragraphs (never bullet points). Use two-stage process with (1) section outlines with key points using research-lookup then (2) convert to flowing prose. IMRAD structure, citations (APA\u002FAMA\u002FVancouver), figures\u002Ftables, reporting guidelines (CONSORT\u002FSTROBE\u002FPRISMA), for research papers and journal submissions.","https:\u002F\u002Fgithub.com\u002Feric861129\u002FSKILLS_All-in-one\u002Fblob\u002Fmain\u002Fpublic\u002FSKILLS\u002FWriting & Research\u002Fscientific-writing\u002FSKILL.md",[196,197,198],{"categoryNo":137,"categoryName":138,"taxonomyType":21,"taxonomyTypeDesc":22},{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},{"categoryNo":144,"categoryName":145,"taxonomyType":146,"taxonomyTypeDesc":147},[200,201,152,202,203,204,205,206,36,207,27,33,158,30,208,209,210,211,212,213],"writing","scientific writing","core","reporting","deep research","Citations","Outlines","tool","never","structure","deep","full","stage","prisma",{"skillNo":215,"name":216,"nameZh":6,"description":217,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":218,"categories":219,"keywords":221,"publishedAt":41},"01M6CZ1B2JGJTB9FRD0TW4RXXE","scientific-brainstorming","Creative research ideation and exploration. Use for open-ended brainstorming sessions, exploring interdisciplinary connections, challenging assumptions, or identifying research gaps. Best for early-stage research planning when you do not have specific observations yet. For formulating testable hypotheses from data use hypothesis-generation.","https:\u002F\u002Fgithub.com\u002Feric861129\u002FSKILLS_All-in-one\u002Fblob\u002Fmain\u002Fpublic\u002FSKILLS\u002FWriting & Research\u002Fscientific-brainstorming\u002FSKILL.md",[220],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},[222,223,151,224,116,225,226,227,30,228,229,230,126,231,232,212,233],"brainstorming","scientific brainstorming","sessions","data","hypothesis","open","ideation","creative","do","connections","research ideation","generation",{"skillNo":235,"name":236,"nameZh":6,"description":237,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":238,"categories":239,"keywords":246,"publishedAt":41},"01M6CZ16JG8N7A2ZX04BGE8J2Y","research-lookup","Look up current research information using the Parallel Chat API (primary) or Perplexity sonar-pro-search (academic paper searches). Automatically routes queries to the best backend. Use for finding papers, gathering research data, and verifying scientific information.","https:\u002F\u002Fgithub.com\u002Feric861129\u002FSKILLS_All-in-one\u002Fblob\u002Fmain\u002Fpublic\u002FSKILLS\u002FWriting & Research\u002Fresearch-lookup\u002FSKILL.md",[240,243,244,245],{"categoryNo":241,"categoryName":242,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000010","后端与接口",{"categoryNo":140,"categoryName":141,"taxonomyType":21,"taxonomyTypeDesc":22},{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},{"categoryNo":170,"categoryName":171,"taxonomyType":146,"taxonomyTypeDesc":147},[151,247,248,249,225,250,251,36,252,253,27,33,158,30,254,255,256,257,258,160],"lookup","research lookup","search","perplexity","api","parallel","openrouter","backend","up","look","queries","chat"]