[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7FED69GFB54FRF7AV5066DN":3,"skill-same:01M7FED69GFB54FRF7AV5066DN":48},{"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":26,"commitSha":27,"skillDirectory":28,"forksCount":29,"repositoryHtmlUrl":30,"repositoryHomepageUrl":6,"ownerHtmlUrl":31,"ownerBlogUrl":6,"ownerDescription":32,"updatedAt":33,"install":34,"resources":47},"01M7FED69GFB54FRF7AV5066DN","writing-systems-papers",null,"Paragraph-level structural blueprint for 10-12 page systems papers targeting OSDI, SOSP, ASPLOS, NSDI, and EuroSys. Provides page allocation, paragraph templates, and writing patterns. Use when user says \"写系统论文\", \"systems paper structure\", \"OSDI paper\", \"SOSP paper\", or wants fine-grained structural guidance for a systems conference submission.","CZX-LBJ\u002Fdeepseek-science","CZX-LBJ","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F204594689?v=4","01M7FC59WQ9PFXT04MKGJDCFFT","czx","01M7FC59XB2GW0BKWN9JTDBQS7",1,"MIT","https:\u002F\u002Fgithub.com\u002FCZX-LBJ\u002Fdeepseek-science\u002Fblob\u002Fmain\u002Fpackages\u002Fskill\u002Fskill-science\u002Fassets\u002Fsources\u002Faris\u002Fskills\u002Fwriting-systems-papers\u002FSKILL.md",[],[],"2026-11-16 10:05:34",false,"---\nname: writing-systems-papers\ndescription: \"Paragraph-level structural blueprint for 10-12 page systems papers targeting OSDI, SOSP, ASPLOS, NSDI, and EuroSys. Provides page allocation, paragraph templates, and writing patterns. Use when user says \\\"写系统论文\\\", \\\"systems paper structure\\\", \\\"OSDI paper\\\", \\\"SOSP paper\\\", or wants fine-grained structural guidance for a systems conference submission.\"\nargument-hint: \"[venue-or-section]\"\nallowed-tools: Bash(*), Read, Write, Edit, Grep, Glob, WebSearch, WebFetch, mcp__codex__codex, mcp__codex__codex-reply\n---\n\n# Writing Systems Papers: Paragraph-Level Blueprint\n\nStructural guidance for **$ARGUMENTS**\n\n## Relationship to Other ARIS Skills\n\n- **paper-write**: General paper generation workflow with citation verification. This skill complements it with systems-specific structural blueprints.\n- **paper-slides**: Conference presentation generation (Beamer+PPTX). Already covers talks — no overlap.\n- **paper-plan**: Research outline creation. Use paper-plan first, then this skill for paragraph-level structure.\n\n**Boundary**: paper-write handles the generation workflow (LaTeX output, DBLP verification, section-by-section drafting). This skill provides the **structural skeleton** — page budgets, paragraph roles, and writing patterns specific to systems venues.\n\n---\n\n## Page Allocation: 12-Page Systems Paper\n\n| Section | Pages | Key Content |\n|---------|-------|-------------|\n| Abstract | ~0.25 | 150–250 words, 5 sentences |\n| S1 Introduction | 1.5–2 | Problem → Gap → Insight → Contributions |\n| S2 Background & Motivation | 1–1.5 | Terms + Production observations |\n| S3 Design | 3–4 | Architecture + Modules + Alternatives |\n| S4 Implementation | 0.5–1 | Prototype, LOC, engineering |\n| S5 Evaluation | 3–4 | Setup + E2E + Ablation + Scalability |\n| S6 Related Work | 1 | By methodology, explicit comparison |\n| S7 Conclusion | 0.5 | 3-sentence summary |\n\n---\n\n## Section Blueprints\n\n### Abstract (5 sentences)\n\n```text\nS1: Problem context and importance\nS2: Gap in existing approaches\nS3: Thesis — \"X is better for Y in environment Z\" (Irene Zhang formula)\nS4: Approach summary + headline results\nS5: Impact or availability\n```\n\nSources: Levin & Redell — \"Can you state the new idea concisely?\"; Irene Zhang — \"abstract cannot use terms introduced in the paper.\"\n\n### S1 Introduction (1.5–2 pages)\n\n1. **Problem** (~0.5p) — Domain + concrete numbers + why it matters\n2. **Gap analysis** (~0.5p) — G1–Gn: specific shortcomings with evidence\n3. **Key insight** (1 para) — Thesis: \"X is better for Y in Z\"\n4. **Contributions** (~0.5p) — 3–5 numbered, testable claims with §N references\n\nPattern: hzwer Move 1 (territory) → Move 2 (niche) → Move 3 (occupy).\n\n### S2 Background & Motivation (1–1.5 pages)\n\n1. **Technical background** (~0.5p) — Define-before-use (Gernot Heiser)\n2. **Observations** (~0.5–1p) — O1, O2, O3 from production data → design insights\n\n### S3 Design (3–4 pages)\n\n1. **Architecture overview** (~0.5p) — Diagram first (Yi Ding: \"draw a picture first\")\n2. **Module details** (~2–2.5p) — Per module: choice, alternatives, why\n3. **Trade-offs** (~0.5–1p) — Summary of design decisions\n\nRule: \"Every design choice must discuss alternatives\" (Irene Zhang).\n\n### S4 Implementation (0.5–1 page)\n\nLanguage, LOC, framework, key engineering decisions. Keep concise.\n\n### S5 Evaluation (3–4 pages)\n\n1. **Setup** (~0.5p) — Hardware, baselines, workloads, metrics\n2. **End-to-end** (~1–1.5p) — X vs baselines for Y on Z\n3. **Ablation** (~1–1.5p) — Remove each component, measure impact\n4. **Scalability** (~0.5p) — Behavior at increasing scale\n\n**Three-statement rule** (Irene Zhang): Every conclusion stated as:\n- Hypothesis (section opening)\n- Conclusion (section closing)\n- Caption (figure caption)\n\n### S6 Related Work (1 page)\n\nGroup by methodology. For each group: what they do, limitation, how we differ.\n\n### S7 Conclusion (0.5 page)\n\nThree sentences: problem, solution, result. No new information.\n\n---\n\n## Writing Patterns\n\n### Pattern 1: Gap Analysis\nEnumerate G1–Gn in intro → A1–An in design → verify in evaluation.\n*Example*: Lucid (ASPLOS'23) — 5 gaps mapped to 5 answers.\n\n### Pattern 2: Observation-Driven\nO1–O3 from production data → insights → design components.\n*Example*: GFS (arXiv 2025) — 3 observations drive 3 components.\n\n### Pattern 3: Contribution List\nNumbered contributions in intro, each with §N cross-reference.\n*Example*: Blox (EuroSys'24) — 7 contributions; Sia (SOSP'23) — 5 contributions.\n\n### Pattern 4: Thesis Formula\n\"X is better for Y in Z\" structures the entire paper.\nCombine with other patterns for maximum impact.\n\n---\n\n## Conference Differences\n\n> Always verify against current CFP — rules change yearly.\n\n| Venue | Format | Pages | Camera-Ready |\n|-------|--------|-------|-------------|\n| OSDI | USENIX | 12 | 14 |\n| NSDI | USENIX | 12 | 14 |\n| SOSP | ACM SIGOPS | 12 | — |\n| ASPLOS | ACM SIGPLAN | 11 | 13 |\n| EuroSys | ACM | 12 | — |\n\nBased on 2025\u002F2026 CFPs.\n\n---\n\n## Workflow\n\n```text\n1. Determine venue and page limit\n2. Choose writing pattern (Gap\u002FObservation\u002FContribution\u002FThesis)\n3. Allocate pages per section using the table above\n4. Draft Abstract following 5-sentence template\n5. Draft Introduction: Problem → Gap → Insight → Contributions\n6. Draft Motivation with production observations (if available)\n7. Draw architecture figure, then write Design\n8. Draft Implementation (concise)\n9. Draft Evaluation: setup → E2E → ablation → scalability\n10. Draft Related Work by methodology groups\n11. Draft Conclusion: 3 sentences\n12. Run pre-submission checklist\n13. Hand off to \u002Fpaper-write for LaTeX generation and citation verification\n```\n\n---\n\n## Quick Self-Check\n\n- [ ] Thesis follows \"X is better for Y in Z\"\n- [ ] 3–5 numbered contributions with §N references\n- [ ] Design discusses alternatives for every major choice\n- [ ] Eval conclusions stated 3 times (hypothesis, result, caption)\n- [ ] Related work grouped by methodology\n- [ ] Page budget within venue limits\n- [ ] No fabricated observations, traces, or results\n- [ ] All citations verified (delegate to \u002Fpaper-write)\n\n---\n\n## Academic Integrity\n\n- Never fabricate observations, traces, or experimental results\n- Never generate citations from memory — use \u002Fpaper-write citation workflow\n- Disclose LLM use per venue policy\n- This blueprint provides structural guidance, not copy-paste text\n\n---\n\n## Authoritative Sources\n\n1. Levin & Redell — \"How (and How Not) to Write a Good Systems Paper\" (USENIX)\n2. Irene Zhang — \"Hints on how to write an SOSP paper\"\n3. Gernot Heiser — Style Guide + Paper Writing Talk\n4. Timothy Roscoe — \"Writing reviews for systems conferences\"\n5. Yi Ding — \"How to write good systems papers?\"\n6. hzwer & DingXiaoH — WritingAIPaper (GitHub)\n","# Writing Systems Papers: Paragraph-Level Blueprint\n\nStructural guidance for **$ARGUMENTS**\n\n## Relationship to Other ARIS Skills\n\n- **paper-write**: General paper generation workflow with citation verification. This skill complements it with systems-specific structural blueprints.\n- **paper-slides**: Conference presentation generation (Beamer+PPTX). Already covers talks — no overlap.\n- **paper-plan**: Research outline creation. Use paper-plan first, then this skill for paragraph-level structure.\n\n**Boundary**: paper-write handles the generation workflow (LaTeX output, DBLP verification, section-by-section drafting). This skill provides the **structural skeleton** — page budgets, paragraph roles, and writing patterns specific to systems venues.\n\n---\n\n## Page Allocation: 12-Page Systems Paper\n\n| Section | Pages | Key Content |\n|---------|-------|-------------|\n| Abstract | ~0.25 | 150–250 words, 5 sentences |\n| S1 Introduction | 1.5–2 | Problem → Gap → Insight → Contributions |\n| S2 Background & Motivation | 1–1.5 | Terms + Production observations |\n| S3 Design | 3–4 | Architecture + Modules + Alternatives |\n| S4 Implementation | 0.5–1 | Prototype, LOC, engineering |\n| S5 Evaluation | 3–4 | Setup + E2E + Ablation + Scalability |\n| S6 Related Work | 1 | By methodology, explicit comparison |\n| S7 Conclusion | 0.5 | 3-sentence summary |\n\n---\n\n## Section Blueprints\n\n### Abstract (5 sentences)\n\n```text\nS1: Problem context and importance\nS2: Gap in existing approaches\nS3: Thesis — \"X is better for Y in environment Z\" (Irene Zhang formula)\nS4: Approach summary + headline results\nS5: Impact or availability\n```\n\nSources: Levin & Redell — \"Can you state the new idea concisely?\"; Irene Zhang — \"abstract cannot use terms introduced in the paper.\"\n\n### S1 Introduction (1.5–2 pages)\n\n1. **Problem** (~0.5p) — Domain + concrete numbers + why it matters\n2. **Gap analysis** (~0.5p) — G1–Gn: specific shortcomings with evidence\n3. **Key insight** (1 para) — Thesis: \"X is better for Y in Z\"\n4. **Contributions** (~0.5p) — 3–5 numbered, testable claims with §N references\n\nPattern: hzwer Move 1 (territory) → Move 2 (niche) → Move 3 (occupy).\n\n### S2 Background & Motivation (1–1.5 pages)\n\n1. **Technical background** (~0.5p) — Define-before-use (Gernot Heiser)\n2. **Observations** (~0.5–1p) — O1, O2, O3 from production data → design insights\n\n### S3 Design (3–4 pages)\n\n1. **Architecture overview** (~0.5p) — Diagram first (Yi Ding: \"draw a picture first\")\n2. **Module details** (~2–2.5p) — Per module: choice, alternatives, why\n3. **Trade-offs** (~0.5–1p) — Summary of design decisions\n\nRule: \"Every design choice must discuss alternatives\" (Irene Zhang).\n\n### S4 Implementation (0.5–1 page)\n\nLanguage, LOC, framework, key engineering decisions. Keep concise.\n\n### S5 Evaluation (3–4 pages)\n\n1. **Setup** (~0.5p) — Hardware, baselines, workloads, metrics\n2. **End-to-end** (~1–1.5p) — X vs baselines for Y on Z\n3. **Ablation** (~1–1.5p) — Remove each component, measure impact\n4. **Scalability** (~0.5p) — Behavior at increasing scale\n\n**Three-statement rule** (Irene Zhang): Every conclusion stated as:\n- Hypothesis (section opening)\n- Conclusion (section closing)\n- Caption (figure caption)\n\n### S6 Related Work (1 page)\n\nGroup by methodology. For each group: what they do, limitation, how we differ.\n\n### S7 Conclusion (0.5 page)\n\nThree sentences: problem, solution, result. No new information.\n\n---\n\n## Writing Patterns\n\n### Pattern 1: Gap Analysis\nEnumerate G1–Gn in intro → A1–An in design → verify in evaluation.\n*Example*: Lucid (ASPLOS'23) — 5 gaps mapped to 5 answers.\n\n### Pattern 2: Observation-Driven\nO1–O3 from production data → insights → design components.\n*Example*: GFS (arXiv 2025) — 3 observations drive 3 components.\n\n### Pattern 3: Contribution List\nNumbered contributions in intro, each with §N cross-reference.\n*Example*: Blox (EuroSys'24) — 7 contributions; Sia (SOSP'23) — 5 contributions.\n\n### Pattern 4: Thesis Formula\n\"X is better for Y in Z\" structures the entire paper.\nCombine with other patterns for maximum impact.\n\n---\n\n## Conference Differences\n\n> Always verify against current CFP — rules change yearly.\n\n| Venue | Format | Pages | Camera-Ready |\n|-------|--------|-------|-------------|\n| OSDI | USENIX | 12 | 14 |\n| NSDI | USENIX | 12 | 14 |\n| SOSP | ACM SIGOPS | 12 | — |\n| ASPLOS | ACM SIGPLAN | 11 | 13 |\n| EuroSys | ACM | 12 | — |\n\nBased on 2025\u002F2026 CFPs.\n\n---\n\n## Workflow\n\n```text\n1. Determine venue and page limit\n2. Choose writing pattern (Gap\u002FObservation\u002FContribution\u002FThesis)\n3. Allocate pages per section using the table above\n4. Draft Abstract following 5-sentence template\n5. Draft Introduction: Problem → Gap → Insight → Contributions\n6. Draft Motivation with production observations (if available)\n7. Draw architecture figure, then write Design\n8. Draft Implementation (concise)\n9. Draft Evaluation: setup → E2E → ablation → scalability\n10. Draft Related Work by methodology groups\n11. Draft Conclusion: 3 sentences\n12. Run pre-submission checklist\n13. Hand off to \u002Fpaper-write for LaTeX generation and citation verification\n```\n\n---\n\n## Quick Self-Check\n\n- [ ] Thesis follows \"X is better for Y in Z\"\n- [ ] 3–5 numbered contributions with §N references\n- [ ] Design discusses alternatives for every major choice\n- [ ] Eval conclusions stated 3 times (hypothesis, result, caption)\n- [ ] Related work grouped by methodology\n- [ ] Page budget within venue limits\n- [ ] No fabricated observations, traces, or results\n- [ ] All citations verified (delegate to \u002Fpaper-write)\n\n---\n\n## Academic Integrity\n\n- Never fabricate observations, traces, or experimental results\n- Never generate citations from memory — use \u002Fpaper-write citation workflow\n- Disclose LLM use per venue policy\n- This blueprint provides structural guidance, not copy-paste text\n\n---\n\n## Authoritative Sources\n\n1. Levin & Redell — \"How (and How Not) to Write a Good Systems Paper\" (USENIX)\n2. Irene Zhang — \"Hints on how to write an SOSP paper\"\n3. Gernot Heiser — Style Guide + Paper Writing Talk\n4. Timothy Roscoe — \"Writing reviews for systems conferences\"\n5. Yi Ding — \"How to write good systems papers?\"\n6. hzwer & DingXiaoH — WritingAIPaper (GitHub)\n",{"name":5,"description":7,"allowed-tools":24,"argument-hint":25},"Bash(*), Read, Write, Edit, Grep, Glob, WebSearch, WebFetch, mcp__codex__codex, mcp__codex__codex-reply","[venue-or-section]","main","18193d71ea3441d7c033dbf195b8a7c75ac96f75","packages\u002Fskill\u002Fskill-science\u002Fassets\u002Fsources\u002Faris\u002Fskills\u002Fwriting-systems-papers",0,"https:\u002F\u002Fgithub.com\u002FCZX-LBJ\u002Fdeepseek-science","https:\u002F\u002Fgithub.com\u002FCZX-LBJ","一个没事喜欢随便写点代码的小菜鸡\r\n","2026-10-22 09:48:04",{"source":8,"skillName":5,"commands":35,"prompt":45,"zipAvailable":46},[36,39,42],{"tool":37,"command":38},"npx","npx skills add CZX-LBJ\u002Fdeepseek-science --skill writing-systems-papers",{"tool":40,"command":41},"bunx","bunx skills add CZX-LBJ\u002Fdeepseek-science --skill writing-systems-papers",{"tool":43,"command":44},"pnpm","pnpm dlx skills add CZX-LBJ\u002Fdeepseek-science --skill writing-systems-papers","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FCZX-LBJ\u002Fdeepseek-science\u002Fblob\u002Fmain\u002Fpackages\u002Fskill\u002Fskill-science\u002Fassets\u002Fsources\u002Faris\u002Fskills\u002Fwriting-systems-papers\u002FSKILL.md",true,[],[49,56,63,70,77,84],{"skillNo":50,"name":51,"nameZh":6,"description":52,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":53,"categories":54,"keywords":55,"publishedAt":19},"01M7FEEKSNMRMKW6JEK93PFDFY","bio-free-energy-calculations","Performs alchemical free-energy calculations including relative binding free energy (RBFE \u002F FEP+) and absolute binding free energy (ABFE) via OpenFE, FEP+, GROMACS, AMBER pmemd, and OpenMM with explicit lambda scheduling, soft-core potentials, MBAR\u002FBAR analysis, cycle-closure validation, and protocol-appropriate enhanced sampling. Compares ML alternatives (Boltz-2 affinity, DeepDock). Use when ranking analogs by binding affinity beyond docking accuracy, performing prospective lead optimization, or validating SAR predictions.","https:\u002F\u002Fgithub.com\u002FCZX-LBJ\u002Fdeepseek-science\u002Fblob\u002Fmain\u002Fpackages\u002Fskill\u002Fskill-science\u002Fassets\u002Fsources\u002Fbioskills\u002Fchemoinformatics\u002Ffree-energy-calculations\u002FSKILL.md",[],[],{"skillNo":57,"name":58,"nameZh":6,"description":59,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":60,"categories":61,"keywords":62,"publishedAt":19},"01M7FEE5CTE5QK55CEMXNNVWY9","bio-conformer-generation","Generates 3D conformer ensembles using RDKit ETKDGv3 with knowledge-enhanced distance geometry, MMFF94\u002FUFF force-field optimization, CREST + GFN2-xTB semi-empirical refinement, and macrocycle-aware torsion preferences. Provides explicit decision rules for single vs ensemble conformer use, RMSD pruning, energy windows, conformer count, and force-field choice. Use when preparing 3D ligands for docking, generating descriptor input for 3D QSAR, or sampling macrocycle\u002Fpeptide conformational ensembles.","https:\u002F\u002Fgithub.com\u002FCZX-LBJ\u002Fdeepseek-science\u002Fblob\u002Fmain\u002Fpackages\u002Fskill\u002Fskill-science\u002Fassets\u002Fsources\u002Fbioskills\u002Fchemoinformatics\u002Fconformer-generation\u002FSKILL.md",[],[],{"skillNo":64,"name":65,"nameZh":6,"description":66,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":67,"categories":68,"keywords":69,"publishedAt":19},"01M7FEDNGFEMFWD1MSEDR5H7CY","bio-admet-prediction","Predicts ADMET properties using ADMETlab 3.0 (119 platform features, including 77 prediction models with modeled-endpoint uncertainty), ADMET-AI, DeepChem MolNet, and chemprop D-MPNN with explicit handling of OECD QSAR principles, applicability domain assessment, calibration, hERG\u002FCYP\u002FAMES endpoints, and PAINS \u002F Lipinski \u002F Ro5 \u002F Veber \u002F BBB druglikeness filters. Use when filtering compounds for drug-likeness, prioritizing leads by predicted safety, or building an in-house ADMET QSAR model.","https:\u002F\u002Fgithub.com\u002FCZX-LBJ\u002Fdeepseek-science\u002Fblob\u002Fmain\u002Fpackages\u002Fskill\u002Fskill-science\u002Fassets\u002Fsources\u002Fbioskills\u002Fchemoinformatics\u002Fadmet-prediction\u002FSKILL.md",[],[],{"skillNo":71,"name":72,"nameZh":6,"description":73,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":74,"categories":75,"keywords":76,"publishedAt":19},"01M7FECVVDWZ0X0VEDTCE4B4DZ","wiki-enrich","Fill in the per-paper TODO sections of research-wiki\u002Fpapers\u002F\u003Cslug>.md pages that literature-ingest skills leave as bare scaffolds. Use when user says 'enrich wiki', 'fill paper TODOs', 'wiki body 補完', '把 paper 摘要寫進 wiki', 'research-wiki 自動填', or after a batch ingest that left papers\u002F as TODO scaffolds.","https:\u002F\u002Fgithub.com\u002FCZX-LBJ\u002Fdeepseek-science\u002Fblob\u002Fmain\u002Fpackages\u002Fskill\u002Fskill-science\u002Fassets\u002Fsources\u002Faris\u002Fskills\u002Fwiki-enrich\u002FSKILL.md",[],[],{"skillNo":78,"name":79,"nameZh":6,"description":80,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":81,"categories":82,"keywords":83,"publishedAt":19},"01M7FECD4BCJ2MTSBDDSE3ZAJ5","web-debug-search","Search GitHub, Stack Exchange, Chinese technical communities, official documentation, and general developer web sources for software errors, compatibility problems, API usage questions, and real-world workarounds. Use for debugging and discovery only; results are not paper-citation evidence.","https:\u002F\u002Fgithub.com\u002FCZX-LBJ\u002Fdeepseek-science\u002Fblob\u002Fmain\u002Fpackages\u002Fskill\u002Fskill-science\u002Fassets\u002Fsources\u002Faris\u002Fskills\u002Fweb-debug-search\u002FSKILL.md",[],[],{"skillNo":85,"name":86,"nameZh":6,"description":87,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":88,"categories":89,"keywords":90,"publishedAt":19},"01M7FEC86Z33BDCMRPD0WK6SZ7","vast-gpu","Rent, manage, and destroy GPU instances on vast.ai. Use when user says \"rent gpu\", \"vast.ai\", \"rent a server\", \"cloud gpu\", or needs on-demand GPU without owning hardware.","https:\u002F\u002Fgithub.com\u002FCZX-LBJ\u002Fdeepseek-science\u002Fblob\u002Fmain\u002Fpackages\u002Fskill\u002Fskill-science\u002Fassets\u002Fsources\u002Faris\u002Fskills\u002Fvast-gpu\u002FSKILL.md",[],[]]