[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6CYRKWZ9J8MVRWHB9GPAN2H":3,"skill-same:01M6CYRKWZ9J8MVRWHB9GPAN2H":100},{"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":38,"linkOnly":39,"markdownContent":40,"markdownBody":41,"frontMatter":42,"refName":44,"commitSha":45,"skillDirectory":46,"forksCount":47,"repositoryHtmlUrl":48,"repositoryHomepageUrl":49,"ownerHtmlUrl":50,"ownerBlogUrl":51,"ownerDescription":52,"updatedAt":53,"install":54,"resources":67},"01M6CYRKWZ9J8MVRWHB9GPAN2H","time-stepping",null,"Plan and control time-step policies for simulations. Use when coupling CFL\u002Fphysics limits with adaptive stepping, ramping initial transients, scheduling outputs\u002Fcheckpoints, or planning restart strategies for long runs.","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\u002Ftime-stepping\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],"time","time stepping","planning","Bash","plan","grep","read","write","use","scheduling","restart","strategies","physics","control","2026-11-10 10:12:30",false,"---\nname: time-stepping\ndescription: Plan and control time-step policies for simulations. Use when coupling CFL\u002Fphysics limits with adaptive stepping, ramping initial transients, scheduling outputs\u002Fcheckpoints, or planning restart strategies for long runs.\nallowed-tools: Read, Bash, Write, Grep, Glob\n---\n\n# Time Stepping\n\n## Goal\n\nProvide a reliable workflow for choosing, ramping, and monitoring time steps plus output\u002Fcheckpoint cadence.\n\n## Requirements\n\n- Python 3.8+\n- No external dependencies (uses stdlib)\n\n## Inputs to Gather\n\n| Input | Description | Example |\n|-------|-------------|---------|\n| Stability limits | CFL\u002FFourier\u002Freaction limits | `dt_max = 1e-4` |\n| Target dt | Desired time step | `1e-5` |\n| Total run time | Simulation duration | `10 s` |\n| Output interval | Time between outputs | `0.1 s` |\n| Checkpoint cost | Time to write checkpoint | `120 s` |\n\n## Decision Guidance\n\n### Time Step Selection\n\n```\nIs stability limit known?\n├── YES → Use min(dt_target, dt_limit × safety)\n└── NO → Start conservative, increase adaptively\n\nNeed ramping for startup?\n├── YES → Start at dt_init, ramp to dt_target over N steps\n└── NO → Use dt_target from start\n```\n\n### Ramping Strategy\n\n| Problem Type | Ramp Steps | Initial dt |\n|--------------|------------|------------|\n| Smooth IC | None needed | Full dt |\n| Sharp gradients | 5-10 | 0.1 × dt |\n| Phase change | 10-20 | 0.01 × dt |\n| Cold start | 10-50 | 0.001 × dt |\n\n## Script Outputs (JSON Fields)\n\n| Script | Key Outputs |\n|--------|-------------|\n| `scripts\u002Ftimestep_planner.py` | `dt_limit`, `dt_recommended`, `ramp_schedule` |\n| `scripts\u002Foutput_schedule.py` | `output_times`, `interval`, `count` |\n| `scripts\u002Fcheckpoint_planner.py` | `checkpoint_interval`, `checkpoints`, `overhead_fraction` |\n\n## Workflow\n\n1. **Get stability limits** - Use numerical-stability skill\n2. **Plan time stepping** - Run `scripts\u002Ftimestep_planner.py`\n3. **Schedule outputs** - Run `scripts\u002Foutput_schedule.py`\n4. **Plan checkpoints** - Run `scripts\u002Fcheckpoint_planner.py`\n5. **Monitor during run** - Adjust dt if limits change\n\n## Conversational Workflow Example\n\n**User**: I'm running a 10-hour phase-field simulation. How often should I checkpoint?\n\n**Agent workflow**:\n1. Plan checkpoints based on acceptable lost work:\n   ```bash\n   python3 scripts\u002Fcheckpoint_planner.py --run-time 36000 --checkpoint-cost 120 --max-lost-time 1800 --json\n   ```\n2. Interpret: Checkpoint every 30 minutes, overhead ~0.7%, max 30 min lost work on crash.\n\n## Pre-Run Checklist\n\n- [ ] Confirm dt limits from stability analysis\n- [ ] Define ramping strategy for transient startup\n- [ ] Choose output interval consistent with physics time scales\n- [ ] Plan checkpoints based on restart risk\n- [ ] Re-evaluate dt after parameter changes\n\n## CLI Examples\n\n```bash\n# Plan time stepping with ramping\npython3 scripts\u002Ftimestep_planner.py --dt-target 1e-4 --dt-limit 2e-4 --safety 0.8 --ramp-steps 10 --json\n\n# Schedule output times\npython3 scripts\u002Foutput_schedule.py --t-start 0 --t-end 10 --interval 0.1 --json\n\n# Plan checkpoints for long run\npython3 scripts\u002Fcheckpoint_planner.py --run-time 36000 --checkpoint-cost 120 --max-lost-time 1800 --json\n```\n\n## Error Handling\n\n| Error | Cause | Resolution |\n|-------|-------|------------|\n| `dt-target must be positive` | Invalid time step | Use positive value |\n| `t-end must be > t-start` | Invalid time range | Check time bounds |\n| `checkpoint-cost must be \u003C run-time` | Checkpoint too expensive | Reduce checkpoint size |\n\n## Interpretation Guidance\n\n### dt Behavior\n\n| Observation | Meaning | Action |\n|-------------|---------|--------|\n| dt stable at target | Good | Continue |\n| dt shrinking | Stability issue | Check CFL, reduce target |\n| dt oscillating | Borderline stability | Add safety factor |\n\n### Checkpoint Overhead\n\n| Overhead | Acceptability |\n|----------|---------------|\n| \u003C 1% | Excellent |\n| 1-5% | Good |\n| 5-10% | Acceptable |\n| > 10% | Too frequent, increase interval |\n\n## Limitations\n\n- **Not adaptive control**: Plans static schedules, not runtime adaptation\n- **Assumes constant physics**: If parameters change, re-plan\n\n## References\n\n- `references\u002Fcfl_coupling.md` - Combining multiple stability limits\n- `references\u002Framping_strategies.md` - Startup policies\n- `references\u002Foutput_checkpoint_guidelines.md` - Cadence rules\n\n## Version History\n\n- **v1.1.0** (2024-12-24): Enhanced documentation, decision guidance, examples\n- **v1.0.0**: Initial release with 3 planning scripts\n","# Time Stepping\n\n## Goal\n\nProvide a reliable workflow for choosing, ramping, and monitoring time steps plus output\u002Fcheckpoint cadence.\n\n## Requirements\n\n- Python 3.8+\n- No external dependencies (uses stdlib)\n\n## Inputs to Gather\n\n| Input | Description | Example |\n|-------|-------------|---------|\n| Stability limits | CFL\u002FFourier\u002Freaction limits | `dt_max = 1e-4` |\n| Target dt | Desired time step | `1e-5` |\n| Total run time | Simulation duration | `10 s` |\n| Output interval | Time between outputs | `0.1 s` |\n| Checkpoint cost | Time to write checkpoint | `120 s` |\n\n## Decision Guidance\n\n### Time Step Selection\n\n```\nIs stability limit known?\n├── YES → Use min(dt_target, dt_limit × safety)\n└── NO → Start conservative, increase adaptively\n\nNeed ramping for startup?\n├── YES → Start at dt_init, ramp to dt_target over N steps\n└── NO → Use dt_target from start\n```\n\n### Ramping Strategy\n\n| Problem Type | Ramp Steps | Initial dt |\n|--------------|------------|------------|\n| Smooth IC | None needed | Full dt |\n| Sharp gradients | 5-10 | 0.1 × dt |\n| Phase change | 10-20 | 0.01 × dt |\n| Cold start | 10-50 | 0.001 × dt |\n\n## Script Outputs (JSON Fields)\n\n| Script | Key Outputs |\n|--------|-------------|\n| `scripts\u002Ftimestep_planner.py` | `dt_limit`, `dt_recommended`, `ramp_schedule` |\n| `scripts\u002Foutput_schedule.py` | `output_times`, `interval`, `count` |\n| `scripts\u002Fcheckpoint_planner.py` | `checkpoint_interval`, `checkpoints`, `overhead_fraction` |\n\n## Workflow\n\n1. **Get stability limits** - Use numerical-stability skill\n2. **Plan time stepping** - Run `scripts\u002Ftimestep_planner.py`\n3. **Schedule outputs** - Run `scripts\u002Foutput_schedule.py`\n4. **Plan checkpoints** - Run `scripts\u002Fcheckpoint_planner.py`\n5. **Monitor during run** - Adjust dt if limits change\n\n## Conversational Workflow Example\n\n**User**: I'm running a 10-hour phase-field simulation. How often should I checkpoint?\n\n**Agent workflow**:\n1. Plan checkpoints based on acceptable lost work:\n   ```bash\n   python3 scripts\u002Fcheckpoint_planner.py --run-time 36000 --checkpoint-cost 120 --max-lost-time 1800 --json\n   ```\n2. Interpret: Checkpoint every 30 minutes, overhead ~0.7%, max 30 min lost work on crash.\n\n## Pre-Run Checklist\n\n- [ ] Confirm dt limits from stability analysis\n- [ ] Define ramping strategy for transient startup\n- [ ] Choose output interval consistent with physics time scales\n- [ ] Plan checkpoints based on restart risk\n- [ ] Re-evaluate dt after parameter changes\n\n## CLI Examples\n\n```bash\n# Plan time stepping with ramping\npython3 scripts\u002Ftimestep_planner.py --dt-target 1e-4 --dt-limit 2e-4 --safety 0.8 --ramp-steps 10 --json\n\n# Schedule output times\npython3 scripts\u002Foutput_schedule.py --t-start 0 --t-end 10 --interval 0.1 --json\n\n# Plan checkpoints for long run\npython3 scripts\u002Fcheckpoint_planner.py --run-time 36000 --checkpoint-cost 120 --max-lost-time 1800 --json\n```\n\n## Error Handling\n\n| Error | Cause | Resolution |\n|-------|-------|------------|\n| `dt-target must be positive` | Invalid time step | Use positive value |\n| `t-end must be > t-start` | Invalid time range | Check time bounds |\n| `checkpoint-cost must be \u003C run-time` | Checkpoint too expensive | Reduce checkpoint size |\n\n## Interpretation Guidance\n\n### dt Behavior\n\n| Observation | Meaning | Action |\n|-------------|---------|--------|\n| dt stable at target | Good | Continue |\n| dt shrinking | Stability issue | Check CFL, reduce target |\n| dt oscillating | Borderline stability | Add safety factor |\n\n### Checkpoint Overhead\n\n| Overhead | Acceptability |\n|----------|---------------|\n| \u003C 1% | Excellent |\n| 1-5% | Good |\n| 5-10% | Acceptable |\n| > 10% | Too frequent, increase interval |\n\n## Limitations\n\n- **Not adaptive control**: Plans static schedules, not runtime adaptation\n- **Assumes constant physics**: If parameters change, re-plan\n\n## References\n\n- `references\u002Fcfl_coupling.md` - Combining multiple stability limits\n- `references\u002Framping_strategies.md` - Startup policies\n- `references\u002Foutput_checkpoint_guidelines.md` - Cadence rules\n\n## Version History\n\n- **v1.1.0** (2024-12-24): Enhanced documentation, decision guidance, examples\n- **v1.0.0**: Initial release with 3 planning scripts\n",{"name":5,"description":7,"allowed-tools":43},"Read, Bash, Write, Grep, Glob","main","cbdd44aae21131521c09e42762e36178c790eacf","public\u002FSKILLS\u002FScientific & Research Tools\u002Ftime-stepping",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":55,"prompt":65,"zipAvailable":66},[56,59,62],{"tool":57,"command":58},"npx","npx skills add eric861129\u002FSKILLS_All-in-one --skill time-stepping",{"tool":60,"command":61},"bunx","bunx skills add eric861129\u002FSKILLS_All-in-one --skill time-stepping",{"tool":63,"command":64},"pnpm","pnpm dlx skills add eric861129\u002FSKILLS_All-in-one --skill time-stepping","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Feric861129\u002FSKILLS_All-in-one\u002Fblob\u002Fmain\u002Fpublic\u002FSKILLS\u002FScientific & Research Tools\u002Ftime-stepping\u002FSKILL.md",true,[68,74,78,82,88,92,96],{"path":69,"resourceType":70,"resourceTypeDesc":71,"sizeBytes":72,"sourceHtmlUrl":73},"references\u002Fcfl_coupling.md","REFERENCE","参考文档",7426,"https:\u002F\u002Fgithub.com\u002Feric861129\u002FSKILLS_All-in-one\u002Fblob\u002Fmain\u002Fpublic\u002FSKILLS\u002FScientific & Research Tools\u002Ftime-stepping\u002Freferences\u002Fcfl_coupling.md",{"path":75,"resourceType":70,"resourceTypeDesc":71,"sizeBytes":76,"sourceHtmlUrl":77},"references\u002Foutput_checkpoint_guidelines.md",9315,"https:\u002F\u002Fgithub.com\u002Feric861129\u002FSKILLS_All-in-one\u002Fblob\u002Fmain\u002Fpublic\u002FSKILLS\u002FScientific & Research Tools\u002Ftime-stepping\u002Freferences\u002Foutput_checkpoint_guidelines.md",{"path":79,"resourceType":70,"resourceTypeDesc":71,"sizeBytes":80,"sourceHtmlUrl":81},"references\u002Framping_strategies.md",7832,"https:\u002F\u002Fgithub.com\u002Feric861129\u002FSKILLS_All-in-one\u002Fblob\u002Fmain\u002Fpublic\u002FSKILLS\u002FScientific & Research Tools\u002Ftime-stepping\u002Freferences\u002Framping_strategies.md",{"path":83,"resourceType":84,"resourceTypeDesc":85,"sizeBytes":86,"sourceHtmlUrl":87},"scripts\u002Fcheckpoint_planner.py","SCRIPT","脚本",2955,"https:\u002F\u002Fgithub.com\u002Feric861129\u002FSKILLS_All-in-one\u002Fblob\u002Fmain\u002Fpublic\u002FSKILLS\u002FScientific & Research Tools\u002Ftime-stepping\u002Fscripts\u002Fcheckpoint_planner.py",{"path":89,"resourceType":84,"resourceTypeDesc":85,"sizeBytes":90,"sourceHtmlUrl":91},"scripts\u002Flighthouse_audit.py",2657,"https:\u002F\u002Fgithub.com\u002Fsapsapshen\u002Fai-memory-router\u002Fblob\u002Fmain\u002Fskills-store\u002Fcopilot\u002Fperformance-profiling\u002Fscripts\u002Flighthouse_audit.py",{"path":93,"resourceType":84,"resourceTypeDesc":85,"sizeBytes":94,"sourceHtmlUrl":95},"scripts\u002Foutput_schedule.py",2308,"https:\u002F\u002Fgithub.com\u002Feric861129\u002FSKILLS_All-in-one\u002Fblob\u002Fmain\u002Fpublic\u002FSKILLS\u002FScientific & Research Tools\u002Ftime-stepping\u002Fscripts\u002Foutput_schedule.py",{"path":97,"resourceType":84,"resourceTypeDesc":85,"sizeBytes":98,"sourceHtmlUrl":99},"scripts\u002Ftimestep_planner.py",4960,"https:\u002F\u002Fgithub.com\u002Feric861129\u002FSKILLS_All-in-one\u002Fblob\u002Fmain\u002Fpublic\u002FSKILLS\u002FScientific & Research Tools\u002Ftime-stepping\u002Fscripts\u002Ftimestep_planner.py",[101,125,157,185,209,229],{"skillNo":102,"name":103,"nameZh":6,"description":104,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":105,"categories":106,"keywords":108,"publishedAt":38},"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",[107],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},[109,110,111,112,26,113,114,115,116,117,118,119,120,30,31,121,122,123,124,35],"oracle","what if oracle","go","run","ux","futures","risk","analysis","explore","decision","branch","question","idea","exploration","options","stress-test",{"skillNo":126,"name":127,"nameZh":6,"description":128,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":129,"categories":130,"keywords":143,"publishedAt":38},"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",[131,134,137,138],{"categoryNo":132,"categoryName":133,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000018","写作与文案",{"categoryNo":135,"categoryName":136,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000021","资料检索与研究",{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},{"categoryNo":139,"categoryName":140,"taxonomyType":141,"taxonomyTypeDesc":142},"01JBSEEDCAT000000000000036","内容创作者","PROFESSION","适用职业",[144,145,146,147,148,149,150,151,27,152,30,31,153,154,155,156],"templates","venue templates","research","guidelines","NeurIPS","ICML","LaTeX","science","access","edit","proposals","Academic","requirements",{"skillNo":158,"name":159,"nameZh":6,"description":160,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":161,"categories":162,"keywords":167,"publishedAt":38},"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",[163,164],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},{"categoryNo":165,"categoryName":166,"taxonomyType":141,"taxonomyTypeDesc":142},"01JBSEEDCAT000000000000030","开发工程师",[168,169,111,170,171,112,172,173,174,175,176,177,178,179,154,180,181,182,183,184],"the fool","review","workflow","architecture","code","audit","forge","devil","team","designer","reviewer","challenge","stress test","evidence","expert","poke","ideas",{"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":38},"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",[191,192,193],{"categoryNo":132,"categoryName":133,"taxonomyType":21,"taxonomyTypeDesc":22},{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},{"categoryNo":139,"categoryName":140,"taxonomyType":141,"taxonomyTypeDesc":142},[195,196,147,197,198,199,200,201,27,202,30,31,153,32,203,204,205,206,207,208],"writing","scientific writing","core","reporting","deep research","Citations","Outlines","tool","never","structure","deep","full","stage","prisma",{"skillNo":210,"name":211,"nameZh":6,"description":212,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":213,"categories":214,"keywords":216,"publishedAt":38},"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",[215],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},[217,218,146,219,26,220,221,222,32,223,224,225,122,226,227,207,228],"brainstorming","scientific brainstorming","sessions","data","hypothesis","open","ideation","creative","do","connections","research ideation","generation",{"skillNo":230,"name":231,"nameZh":6,"description":232,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":233,"categories":234,"keywords":241,"publishedAt":38},"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",[235,238,239,240],{"categoryNo":236,"categoryName":237,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000010","后端与接口",{"categoryNo":135,"categoryName":136,"taxonomyType":21,"taxonomyTypeDesc":22},{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},{"categoryNo":165,"categoryName":166,"taxonomyType":141,"taxonomyTypeDesc":142},[146,242,243,244,220,245,246,27,247,248,30,31,153,32,249,250,251,252,253,155],"lookup","research lookup","search","perplexity","api","parallel","openrouter","backend","up","look","queries","chat"]