[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6CYQTSVC66C1FWNVCNYACMN":3,"skill-same:01M6CYQTSVC66C1FWNVCNYACMN":82},{"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":40,"linkOnly":41,"markdownContent":42,"markdownBody":43,"frontMatter":44,"refName":46,"commitSha":47,"skillDirectory":48,"forksCount":49,"repositoryHtmlUrl":50,"repositoryHomepageUrl":51,"ownerHtmlUrl":52,"ownerBlogUrl":53,"ownerDescription":54,"updatedAt":55,"install":56,"resources":69},"01M6CYQTSVC66C1FWNVCNYACMN","slurm-job-script-generator",null,"Generate SLURM `sbatch` job scripts and sanity-check HPC resource requests (nodes, tasks, CPUs, memory, GPUs) for simulation runs. Use when preparing submission scripts, deciding MPI vs MPI+OpenMP layouts, standardizing `#SBATCH` directives, or debugging job launch configuration (`sbatch`\u002F`srun`).","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\u002Fslurm-job-script-generator\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],"Slurm","slurm job script generator","memory","launch","debugging","tasks","generate","simulation","Bash","grep","check","read","write","use","Nodes","configuration","2026-11-10 10:12:30",false,"---\nname: slurm-job-script-generator\ndescription: Generate SLURM `sbatch` job scripts and sanity-check HPC resource requests (nodes, tasks, CPUs, memory, GPUs) for simulation runs. Use when preparing submission scripts, deciding MPI vs MPI+OpenMP layouts, standardizing `#SBATCH` directives, or debugging job launch configuration (`sbatch`\u002F`srun`).\nallowed-tools: Read, Bash, Write, Grep, Glob\n---\n\n# SLURM Job Script Generator\n\n## Goal\n\nGenerate a correct, copy-pasteable SLURM job script (`.sbatch`) for running a simulation, and surface common configuration mistakes (bad walltime format, conflicting memory flags, oversubscription hints).\n\n## Requirements\n\n- Python 3.8+\n- No external dependencies (Python standard library only)\n- Works on Linux, macOS, and Windows (script generation only)\n\n## Inputs to Gather\n\n| Input | Description | Example |\n|-------|-------------|---------|\n| Job name | Short identifier for the job | `phasefield-strong-scaling` |\n| Walltime | SLURM time limit | `00:30:00` |\n| Partition | Cluster partition\u002Fqueue (if required) | `compute` |\n| Account | Project\u002Faccount (if required) | `matsim` |\n| Nodes | Number of nodes to allocate | `2` |\n| MPI tasks | Total tasks, or tasks per node | `128` or `64` per node |\n| Threads | CPUs per task (OpenMP threads) | `2` |\n| Memory | `--mem` or `--mem-per-cpu` (cluster policy dependent) | `32G` |\n| GPUs | GPUs per node (optional) | `4` |\n| Working directory | Where the run should execute | `$SLURM_SUBMIT_DIR` |\n| Modules | Environment modules to load (optional) | `gcc\u002F12`, `openmpi\u002F4.1` |\n| Run command | The command to launch under SLURM | `.\u002Fsimulate --config cfg.json` |\n\n## Decision Guidance\n\n### MPI vs MPI+OpenMP layout\n\n```\nDoes the code use OpenMP \u002F threading?\n├── NO  → Use MPI-only: cpus-per-task=1\n└── YES → Use hybrid: set cpus-per-task = threads per MPI rank\n          and export OMP_NUM_THREADS = cpus-per-task\n```\n\n**Rule of thumb:** if you see diminishing strong-scaling efficiency at high MPI ranks, try fewer ranks with more threads per rank (and measure).\n\n### Memory flag selection\n\n- Use **either** `--mem` (per node) **or** `--mem-per-cpu` (per CPU), not both.\n- Follow your cluster’s documentation; some sites enforce one style.\n- SLURM `--mem` units are integer MB by default, or an integer with suffix `K\u002FM\u002FG\u002FT` (and `--mem=0` commonly means “all memory on node”).\n\n## Script Outputs (JSON Fields)\n\n| Script | Key Outputs |\n|--------|-------------|\n| `scripts\u002Fslurm_script_generator.py` | `results.script`, `results.directives`, `results.derived`, `results.warnings` |\n\n## Workflow\n\n1. Gather cluster constraints (partition\u002Faccount, GPU policy, memory policy).\n2. Choose a process layout (MPI-only vs hybrid MPI+OpenMP).\n3. Generate the script with `slurm_script_generator.py`.\n4. Inspect warnings (conflicts, suspicious layouts).\n5. Save the generated script as `job.sbatch`.\n6. Submit with `sbatch job.sbatch` and monitor with `squeue`.\n\n## CLI Examples\n\n```bash\n# Preview a job script (prints to stdout)\npython3 skills\u002Fhpc-deployment\u002Fslurm-job-script-generator\u002Fscripts\u002Fslurm_script_generator.py \\\n  --job-name phasefield \\\n  --time 00:10:00 \\\n  --partition compute \\\n  --nodes 1 \\\n  --ntasks-per-node 8 \\\n  --cpus-per-task 2 \\\n  --mem 16G \\\n  --module gcc\u002F12 \\\n  --module openmpi\u002F4.1 \\\n  -- \\\n  .\u002Fsimulate --config config.json\n\n# Write to a file and also emit structured JSON\npython3 skills\u002Fhpc-deployment\u002Fslurm-job-script-generator\u002Fscripts\u002Fslurm_script_generator.py \\\n  --job-name phasefield \\\n  --time 00:10:00 \\\n  --nodes 1 \\\n  --ntasks 16 \\\n  --cpus-per-task 1 \\\n  --out job.sbatch \\\n  --json \\\n  -- \\\n  \u002Fbin\u002Fecho hello\n```\n\n## Conversational Workflow Example\n\n**User**: I need an `sbatch` script for my MPI simulation. I want 2 nodes, 64 ranks per node, 2 OpenMP threads per rank, and 2 hours.\n\n**Agent workflow**:\n1. Confirm partition\u002Faccount and whether GPUs are needed.\n2. Generate a hybrid job script:\n   ```bash\n   python3 scripts\u002Fslurm_script_generator.py --job-name run --time 02:00:00 --nodes 2 --ntasks-per-node 64 --cpus-per-task 2 -- -- .\u002Fsimulate\n   ```\n3. Explain the mapping:\n   - Total ranks = 128\n   - Threads per rank = 2 (`OMP_NUM_THREADS=2`)\n4. If the user provides node core counts, sanity-check oversubscription using `--cores-per-node`.\n\n## Error Handling\n\n| Error | Cause | Resolution |\n|-------|-------|------------|\n| `time must be HH:MM:SS or D-HH:MM:SS` | Bad walltime format | Use `00:30:00` or `1-00:00:00` |\n| `nodes must be positive` | Non-positive nodes | Provide `--nodes >= 1` |\n| `Provide either --mem or --mem-per-cpu, not both` | Conflicting memory directives | Choose one memory style |\n| `Provide a run command after --` | Missing launch command | Add `-- .\u002Fsimulate ...` |\n\n## Limitations\n\n- Does not query cluster hardware or site policies; it can only validate internal consistency.\n- SLURM installations vary (GPU directives, QoS rules, partitions). Adjust directives for your site.\n\n## References\n\n- `references\u002Fslurm_directives.md` - Common `#SBATCH` directives and mapping tips\n\n## Version History\n\n- **v1.0.0** (2026-02-25): Initial SLURM job script generator\n","# SLURM Job Script Generator\n\n## Goal\n\nGenerate a correct, copy-pasteable SLURM job script (`.sbatch`) for running a simulation, and surface common configuration mistakes (bad walltime format, conflicting memory flags, oversubscription hints).\n\n## Requirements\n\n- Python 3.8+\n- No external dependencies (Python standard library only)\n- Works on Linux, macOS, and Windows (script generation only)\n\n## Inputs to Gather\n\n| Input | Description | Example |\n|-------|-------------|---------|\n| Job name | Short identifier for the job | `phasefield-strong-scaling` |\n| Walltime | SLURM time limit | `00:30:00` |\n| Partition | Cluster partition\u002Fqueue (if required) | `compute` |\n| Account | Project\u002Faccount (if required) | `matsim` |\n| Nodes | Number of nodes to allocate | `2` |\n| MPI tasks | Total tasks, or tasks per node | `128` or `64` per node |\n| Threads | CPUs per task (OpenMP threads) | `2` |\n| Memory | `--mem` or `--mem-per-cpu` (cluster policy dependent) | `32G` |\n| GPUs | GPUs per node (optional) | `4` |\n| Working directory | Where the run should execute | `$SLURM_SUBMIT_DIR` |\n| Modules | Environment modules to load (optional) | `gcc\u002F12`, `openmpi\u002F4.1` |\n| Run command | The command to launch under SLURM | `.\u002Fsimulate --config cfg.json` |\n\n## Decision Guidance\n\n### MPI vs MPI+OpenMP layout\n\n```\nDoes the code use OpenMP \u002F threading?\n├── NO  → Use MPI-only: cpus-per-task=1\n└── YES → Use hybrid: set cpus-per-task = threads per MPI rank\n          and export OMP_NUM_THREADS = cpus-per-task\n```\n\n**Rule of thumb:** if you see diminishing strong-scaling efficiency at high MPI ranks, try fewer ranks with more threads per rank (and measure).\n\n### Memory flag selection\n\n- Use **either** `--mem` (per node) **or** `--mem-per-cpu` (per CPU), not both.\n- Follow your cluster’s documentation; some sites enforce one style.\n- SLURM `--mem` units are integer MB by default, or an integer with suffix `K\u002FM\u002FG\u002FT` (and `--mem=0` commonly means “all memory on node”).\n\n## Script Outputs (JSON Fields)\n\n| Script | Key Outputs |\n|--------|-------------|\n| `scripts\u002Fslurm_script_generator.py` | `results.script`, `results.directives`, `results.derived`, `results.warnings` |\n\n## Workflow\n\n1. Gather cluster constraints (partition\u002Faccount, GPU policy, memory policy).\n2. Choose a process layout (MPI-only vs hybrid MPI+OpenMP).\n3. Generate the script with `slurm_script_generator.py`.\n4. Inspect warnings (conflicts, suspicious layouts).\n5. Save the generated script as `job.sbatch`.\n6. Submit with `sbatch job.sbatch` and monitor with `squeue`.\n\n## CLI Examples\n\n```bash\n# Preview a job script (prints to stdout)\npython3 skills\u002Fhpc-deployment\u002Fslurm-job-script-generator\u002Fscripts\u002Fslurm_script_generator.py \\\n  --job-name phasefield \\\n  --time 00:10:00 \\\n  --partition compute \\\n  --nodes 1 \\\n  --ntasks-per-node 8 \\\n  --cpus-per-task 2 \\\n  --mem 16G \\\n  --module gcc\u002F12 \\\n  --module openmpi\u002F4.1 \\\n  -- \\\n  .\u002Fsimulate --config config.json\n\n# Write to a file and also emit structured JSON\npython3 skills\u002Fhpc-deployment\u002Fslurm-job-script-generator\u002Fscripts\u002Fslurm_script_generator.py \\\n  --job-name phasefield \\\n  --time 00:10:00 \\\n  --nodes 1 \\\n  --ntasks 16 \\\n  --cpus-per-task 1 \\\n  --out job.sbatch \\\n  --json \\\n  -- \\\n  \u002Fbin\u002Fecho hello\n```\n\n## Conversational Workflow Example\n\n**User**: I need an `sbatch` script for my MPI simulation. I want 2 nodes, 64 ranks per node, 2 OpenMP threads per rank, and 2 hours.\n\n**Agent workflow**:\n1. Confirm partition\u002Faccount and whether GPUs are needed.\n2. Generate a hybrid job script:\n   ```bash\n   python3 scripts\u002Fslurm_script_generator.py --job-name run --time 02:00:00 --nodes 2 --ntasks-per-node 64 --cpus-per-task 2 -- -- .\u002Fsimulate\n   ```\n3. Explain the mapping:\n   - Total ranks = 128\n   - Threads per rank = 2 (`OMP_NUM_THREADS=2`)\n4. If the user provides node core counts, sanity-check oversubscription using `--cores-per-node`.\n\n## Error Handling\n\n| Error | Cause | Resolution |\n|-------|-------|------------|\n| `time must be HH:MM:SS or D-HH:MM:SS` | Bad walltime format | Use `00:30:00` or `1-00:00:00` |\n| `nodes must be positive` | Non-positive nodes | Provide `--nodes >= 1` |\n| `Provide either --mem or --mem-per-cpu, not both` | Conflicting memory directives | Choose one memory style |\n| `Provide a run command after --` | Missing launch command | Add `-- .\u002Fsimulate ...` |\n\n## Limitations\n\n- Does not query cluster hardware or site policies; it can only validate internal consistency.\n- SLURM installations vary (GPU directives, QoS rules, partitions). Adjust directives for your site.\n\n## References\n\n- `references\u002Fslurm_directives.md` - Common `#SBATCH` directives and mapping tips\n\n## Version History\n\n- **v1.0.0** (2026-02-25): Initial SLURM job script generator\n",{"name":5,"description":7,"allowed-tools":45},"Read, Bash, Write, Grep, Glob","main","cbdd44aae21131521c09e42762e36178c790eacf","public\u002FSKILLS\u002FScientific & Research Tools\u002Fslurm-job-script-generator",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":57,"prompt":67,"zipAvailable":68},[58,61,64],{"tool":59,"command":60},"npx","npx skills add eric861129\u002FSKILLS_All-in-one --skill slurm-job-script-generator",{"tool":62,"command":63},"bunx","bunx skills add eric861129\u002FSKILLS_All-in-one --skill slurm-job-script-generator",{"tool":65,"command":66},"pnpm","pnpm dlx skills add eric861129\u002FSKILLS_All-in-one --skill slurm-job-script-generator","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Feric861129\u002FSKILLS_All-in-one\u002Fblob\u002Fmain\u002Fpublic\u002FSKILLS\u002FScientific & Research Tools\u002Fslurm-job-script-generator\u002FSKILL.md",true,[70,76],{"path":71,"resourceType":72,"resourceTypeDesc":73,"sizeBytes":74,"sourceHtmlUrl":75},"references\u002Fslurm_directives.md","REFERENCE","参考文档",1811,"https:\u002F\u002Fgithub.com\u002Feric861129\u002FSKILLS_All-in-one\u002Fblob\u002Fmain\u002Fpublic\u002FSKILLS\u002FScientific & Research Tools\u002Fslurm-job-script-generator\u002Freferences\u002Fslurm_directives.md",{"path":77,"resourceType":78,"resourceTypeDesc":79,"sizeBytes":80,"sourceHtmlUrl":81},"scripts\u002Fslurm_script_generator.py","SCRIPT","脚本",16606,"https:\u002F\u002Fgithub.com\u002Feric861129\u002FSKILLS_All-in-one\u002Fblob\u002Fmain\u002Fpublic\u002FSKILLS\u002FScientific & Research Tools\u002Fslurm-job-script-generator\u002Fscripts\u002Fslurm_script_generator.py",[83,109,141,169,193,213],{"skillNo":84,"name":85,"nameZh":6,"description":86,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":87,"categories":88,"keywords":90,"publishedAt":40},"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",[89],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},[91,92,93,94,95,96,97,98,99,100,101,102,103,35,36,104,105,106,107,108],"oracle","what if oracle","go","run","planning","ux","futures","risk","analysis","explore","decision","branch","question","idea","exploration","options","stress-test","strategies",{"skillNo":110,"name":111,"nameZh":6,"description":112,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":113,"categories":114,"keywords":127,"publishedAt":40},"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",[115,118,121,122],{"categoryNo":116,"categoryName":117,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000018","写作与文案",{"categoryNo":119,"categoryName":120,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000021","资料检索与研究",{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},{"categoryNo":123,"categoryName":124,"taxonomyType":125,"taxonomyTypeDesc":126},"01JBSEEDCAT000000000000036","内容创作者","PROFESSION","适用职业",[128,129,130,131,132,133,134,135,32,136,35,36,137,138,139,140],"templates","venue templates","research","guidelines","NeurIPS","ICML","LaTeX","science","access","edit","proposals","Academic","requirements",{"skillNo":142,"name":143,"nameZh":6,"description":144,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":145,"categories":146,"keywords":151,"publishedAt":40},"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",[147,148],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},{"categoryNo":149,"categoryName":150,"taxonomyType":125,"taxonomyTypeDesc":126},"01JBSEEDCAT000000000000030","开发工程师",[152,153,93,154,155,94,156,157,158,159,160,161,162,163,138,164,165,166,167,168],"the fool","review","workflow","architecture","code","audit","forge","devil","team","designer","reviewer","challenge","stress test","evidence","expert","poke","ideas",{"skillNo":170,"name":171,"nameZh":6,"description":172,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":173,"categories":174,"keywords":178,"publishedAt":40},"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",[175,176,177],{"categoryNo":116,"categoryName":117,"taxonomyType":21,"taxonomyTypeDesc":22},{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},{"categoryNo":123,"categoryName":124,"taxonomyType":125,"taxonomyTypeDesc":126},[179,180,131,181,182,183,184,185,32,186,35,36,137,37,187,188,189,190,191,192],"writing","scientific writing","core","reporting","deep research","Citations","Outlines","tool","never","structure","deep","full","stage","prisma",{"skillNo":194,"name":195,"nameZh":6,"description":196,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":197,"categories":198,"keywords":200,"publishedAt":40},"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",[199],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},[201,202,130,203,95,204,205,206,37,207,208,209,105,210,211,191,212],"brainstorming","scientific brainstorming","sessions","data","hypothesis","open","ideation","creative","do","connections","research ideation","generation",{"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":225,"publishedAt":40},"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",[219,222,223,224],{"categoryNo":220,"categoryName":221,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000010","后端与接口",{"categoryNo":119,"categoryName":120,"taxonomyType":21,"taxonomyTypeDesc":22},{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},{"categoryNo":149,"categoryName":150,"taxonomyType":125,"taxonomyTypeDesc":126},[130,226,227,228,204,229,230,32,231,232,35,36,137,37,233,234,235,236,237,139],"lookup","research lookup","search","perplexity","api","parallel","openrouter","backend","up","look","queries","chat"]