[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7FEB8H9YVG2K7C0N64J2BFQ":3,"skill-same:01M7FEB8H9YVG2K7C0N64J2BFQ":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},"01M7FEB8H9YVG2K7C0N64J2BFQ","specification-writing",null,"Write the full patent specification from claims and invention disclosure. Use when user says \"撰写说明书\", \"write specification\", \"写说明书\", \"patent description\", or wants to draft the complete patent specification.","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\u002Fspecification-writing\u002FSKILL.md",[],[],"2026-11-16 10:05:34",false,"---\nname: specification-writing\ndescription: \"Write the full patent specification from claims and invention disclosure. Use when user says \\\"撰写说明书\\\", \\\"write specification\\\", \\\"写说明书\\\", \\\"patent description\\\", or wants to draft the complete patent specification.\"\nargument-hint: \"[claims-path]\"\nallowed-tools: Bash(*), Read, Write, Edit, Grep, Glob, Skill, WebSearch, WebFetch, mcp__codex__codex, mcp__codex__codex-reply\n---\n\n# Specification Writing: Section-by-Section Patent Description\n\nWrite the patent specification based on: **$ARGUMENTS**\n\nAdapted from `\u002Fpaper-write` for patent specifications. The specification supports the claims -- it is not a paper.\n\n## Constants\n\n- `REVIEWER_MODEL = gpt-6-astra` — External reviewer for specification quality\n- `JURISDICTION = \"auto\"` — Inherit from pipeline or detect from args; `CN`, `US`, `EP`, `ALL`\n- `OUTPUT_FORMAT = \"markdown\"` — Markdown drafts; converted to filing format by `\u002Fjurisdiction-format`\n- `OUTPUT_DIR = \"patent\u002F\"` — Base output directory\n- `LANGUAGE = \"auto\"` — Auto from jurisdiction: CN->Chinese, US\u002FEP->English\n\n## Inputs\n\n1. `patent\u002FCLAIMS.md` — the drafted claims (primary source)\n2. `patent\u002FINVENTION_DISCLOSURE.md` — invention decomposition\n3. `patent\u002FPRIOR_ART_REPORT.md` — for background section\n4. User-provided figures (if any)\n\n## Shared References\n\nLoad `..\u002Fshared-references\u002Fpatent-writing-principles.md` for specification writing rules, language guidelines, and reference numeral conventions.\nLoad `..\u002Fshared-references\u002Fpatent-format-cn.md` or `patent-format-us.md` or `patent-format-ep.md` based on jurisdiction.\n\n## Workflow\n\n### Step 1: Initialize Specification Structure\n\nCreate the output directory and section files:\n\n```\npatent\u002Fspecification\u002F\n├── title.md\n├── technical_field.md\n├── background.md\n├── summary.md\n├── drawings_description.md\n├── detailed_description.md\n└── abstract.md\n```\n\n### Step 2: Write Title (发明名称)\n\n- Must match the broadest claim scope\n- No trademarks, no \"improved\" or \"new\" or \"novel\"\n- CN format: \"一种[领域]的[技术主题]\" or \"[领域]的[技术主题]装置\"\n- US\u002FEP format: \"[Technical topic] for [purpose]\" or \"[Technical topic] and method thereof\"\n- Keep concise (CN: typically under 25 characters; US: under 500 characters)\n\n### Step 3: Write Technical Field (技术领域)\n\n1-2 paragraphs identifying the technical domain:\n- \"The present invention relates to [broad field], and more particularly to [specific area].\"\n- CN: \"本发明涉及[技术领域]，具体涉及[具体领域]。\"\n\n### Step 4: Write Background (背景技术)\n\nThis is NOT a literature review. It directly sets up the problem.\n\nStructure:\n1. Describe the closest prior art approaches (2-3 paragraphs)\n2. Identify specific technical deficiencies of each approach\n3. The deficiencies must be technical, not commercial or social\n4. DO NOT admit the prior art is \"superior\" or \"better\"\n5. DO NOT cite specific patent numbers unless they are known prior art (citations go in IDS for US, or Background section for CN)\n\nCN format: \"背景技术\" section describing existing technology and its shortcomings.\n\n### Step 5: Write Summary (发明内容)\n\nThree parts, directly mirroring INVENTION_DISCLOSURE.md:\n\n**Technical Problem (要解决的技术问题)**:\n- State the problem derived from background deficiencies\n- CN: \"本发明要解决的技术问题是...\"\n\n**Technical Solution (技术方案)**:\n- Describe how the invention solves the problem\n- Must provide support for ALL claim elements\n- Start from the broadest claim and describe the core inventive concept\n- CN: \"为解决上述技术问题，本发明采用的技术方案是：...\"\n- **NO formulas, NO mathematical derivations, NO circuit models** — these belong in 具体实施方式, not 发明内容\n\n**Advantages (有益效果)**:\n- Benefits derived from the structural\u002Ftechnical features (qualitative reasoning)\n- CN: \"本发明的有益效果是：...\"\n- **NO specific numerical results** (e.g., \"detection limit 70μm\", \"response time 105ms\") — these are experimental findings, not invention properties\n- Frame advantages structurally: \"由于采用了...结构，因此具有...效果\"\n\n### Step 6: Write Brief Description of Drawings (附图说明)\n\nInvoke `\u002Ffigure-description` as a sub-skill if user has provided figures:\n```\n\u002Ffigure-description \"patent\u002Ffigures\u002F\"\n```\n\nIf no user figures, describe what figures should exist based on the claims.\n\nFormat:\n- CN: \"图1是...的示意图；图2是...的流程图；\"\n- US: \"FIG. 1 is a block diagram showing...; FIG. 2 is a flowchart illustrating...\"\n\n### Step 7: Write Detailed Description (具体实施方式)\n\nInvoke `\u002Fembodiment-description` as a sub-skill:\n```\n\u002Fembodiment-description \"patent\u002FCLAIMS.md\"\n```\n\nThis section must:\n- Describe at least one complete embodiment with reference numerals\n- Enable a POSITA to make and use the invention\n- Support every claim element with explicit description\n- Include variations and alternatives for broader claim interpretation\n\n### Step 8: Write Abstract (摘要)\n\nJurisdiction-specific word limits:\n\n| Jurisdiction | Word Limit | Notes |\n|-------------|-----------|-------|\n| CN | 300 words (Chinese characters) | Include most representative claim reference |\n| US | 150 words (2500 characters) | Enable efficient searching, no legal phrases |\n| EP | ~150 words | No statements on merits or value |\n\nThe abstract summarizes:\n1. The technical field\n2. The problem being solved\n3. The technical solution (core features)\n4. Key advantages\n\n### Step 9: Claim Support Verification\n\nVerify every claim element finds support in the specification:\n\n| Claim | Element | Specification Section | Paragraph(s) | Reference Numeral |\n|-------|---------|----------------------|-------------|-------------------|\n| 1 | step a | detailed_description | ¶3 | 202 |\n| 1 | step b | detailed_description | ¶4 | 204 |\n| X | component A | detailed_description | ¶2 | 102 |\n\nIf any element lacks support, add the necessary description before proceeding.\n\n### Step 10: Cross-Model Review\n\nCall `REVIEWER_MODEL` via `mcp__codex__codex` with xhigh reasoning:\n\n```\nmcp__codex__codex:\n  model: gpt-6-astra\n  config: {\"model_reasoning_effort\": \"xhigh\"}\n  prompt: |\n    You are a patent examiner reviewing a specification for completeness.\n    CLAIMS: [all claims]\n    SPECIFICATION: [all specification sections]\n\n    Check for:\n    1. Written description support: Does every claim element have explicit or inherent support?\n    2. Enablement: Can a POSITA practice the invention from this specification?\n    3. Consistency: Do reference numerals match across figures and specification?\n    4. Language quality: Any subjective terms, relative terms without definition, or result-to-be-achieved language?\n    5. Missing embodiments: Are there claim features that need additional embodiments?\n    6. Background deficiencies: Are they technical and specific enough?\n```\n\n### Step 11: Output\n\nAll specification sections are in `patent\u002Fspecification\u002F`.\n\nSummary file: `patent\u002Fspecification\u002FSPECIFICATION_INDEX.md` with:\n```markdown\n## Patent Specification\n\n### Sections\n| Section | File | Word Count | Status |\n|---------|------|-----------|--------|\n| Title | title.md | | Complete |\n| Technical Field | technical_field.md | | Complete |\n| Background | background.md | | Complete |\n| Summary | summary.md | | Complete |\n| Drawings Description | drawings_description.md | | Complete |\n| Detailed Description | detailed_description.md | | Complete |\n| Abstract | abstract.md | | Complete |\n\n### Claim Support Status\n| Claim | Elements Supported | Elements Missing |\n|-------|-------------------|-----------------|\n| 1 | All | None |\n| X | All | None |\n```\n\n## Key Rules\n\n- The specification supports the claims, not the other way around. Every claim element must have support.\n- Use consistent terminology -- same word for the same concept throughout.\n- DO NOT include experimental results, accuracy metrics, or empirical evaluations.\n- DO NOT use subjective language (\"excellent\", \"surprising\", \"superior\").\n- Reference numerals must be consistent: same component, same numeral, everywhere.\n- Background section describes specific deficiencies, not general \"need for improvement.\"\n- Multiple embodiments strengthen the specification but are not always required.\n- Large file handling: if a Write operation fails, retry with Bash `cat \u003C\u003C'EOF'` heredoc.\n- If `mcp__codex__codex` is not available, skip cross-model review and note it in the output.\n","# Specification Writing: Section-by-Section Patent Description\n\nWrite the patent specification based on: **$ARGUMENTS**\n\nAdapted from `\u002Fpaper-write` for patent specifications. The specification supports the claims -- it is not a paper.\n\n## Constants\n\n- `REVIEWER_MODEL = gpt-6-astra` — External reviewer for specification quality\n- `JURISDICTION = \"auto\"` — Inherit from pipeline or detect from args; `CN`, `US`, `EP`, `ALL`\n- `OUTPUT_FORMAT = \"markdown\"` — Markdown drafts; converted to filing format by `\u002Fjurisdiction-format`\n- `OUTPUT_DIR = \"patent\u002F\"` — Base output directory\n- `LANGUAGE = \"auto\"` — Auto from jurisdiction: CN->Chinese, US\u002FEP->English\n\n## Inputs\n\n1. `patent\u002FCLAIMS.md` — the drafted claims (primary source)\n2. `patent\u002FINVENTION_DISCLOSURE.md` — invention decomposition\n3. `patent\u002FPRIOR_ART_REPORT.md` — for background section\n4. User-provided figures (if any)\n\n## Shared References\n\nLoad `..\u002Fshared-references\u002Fpatent-writing-principles.md` for specification writing rules, language guidelines, and reference numeral conventions.\nLoad `..\u002Fshared-references\u002Fpatent-format-cn.md` or `patent-format-us.md` or `patent-format-ep.md` based on jurisdiction.\n\n## Workflow\n\n### Step 1: Initialize Specification Structure\n\nCreate the output directory and section files:\n\n```\npatent\u002Fspecification\u002F\n├── title.md\n├── technical_field.md\n├── background.md\n├── summary.md\n├── drawings_description.md\n├── detailed_description.md\n└── abstract.md\n```\n\n### Step 2: Write Title (发明名称)\n\n- Must match the broadest claim scope\n- No trademarks, no \"improved\" or \"new\" or \"novel\"\n- CN format: \"一种[领域]的[技术主题]\" or \"[领域]的[技术主题]装置\"\n- US\u002FEP format: \"[Technical topic] for [purpose]\" or \"[Technical topic] and method thereof\"\n- Keep concise (CN: typically under 25 characters; US: under 500 characters)\n\n### Step 3: Write Technical Field (技术领域)\n\n1-2 paragraphs identifying the technical domain:\n- \"The present invention relates to [broad field], and more particularly to [specific area].\"\n- CN: \"本发明涉及[技术领域]，具体涉及[具体领域]。\"\n\n### Step 4: Write Background (背景技术)\n\nThis is NOT a literature review. It directly sets up the problem.\n\nStructure:\n1. Describe the closest prior art approaches (2-3 paragraphs)\n2. Identify specific technical deficiencies of each approach\n3. The deficiencies must be technical, not commercial or social\n4. DO NOT admit the prior art is \"superior\" or \"better\"\n5. DO NOT cite specific patent numbers unless they are known prior art (citations go in IDS for US, or Background section for CN)\n\nCN format: \"背景技术\" section describing existing technology and its shortcomings.\n\n### Step 5: Write Summary (发明内容)\n\nThree parts, directly mirroring INVENTION_DISCLOSURE.md:\n\n**Technical Problem (要解决的技术问题)**:\n- State the problem derived from background deficiencies\n- CN: \"本发明要解决的技术问题是...\"\n\n**Technical Solution (技术方案)**:\n- Describe how the invention solves the problem\n- Must provide support for ALL claim elements\n- Start from the broadest claim and describe the core inventive concept\n- CN: \"为解决上述技术问题，本发明采用的技术方案是：...\"\n- **NO formulas, NO mathematical derivations, NO circuit models** — these belong in 具体实施方式, not 发明内容\n\n**Advantages (有益效果)**:\n- Benefits derived from the structural\u002Ftechnical features (qualitative reasoning)\n- CN: \"本发明的有益效果是：...\"\n- **NO specific numerical results** (e.g., \"detection limit 70μm\", \"response time 105ms\") — these are experimental findings, not invention properties\n- Frame advantages structurally: \"由于采用了...结构，因此具有...效果\"\n\n### Step 6: Write Brief Description of Drawings (附图说明)\n\nInvoke `\u002Ffigure-description` as a sub-skill if user has provided figures:\n```\n\u002Ffigure-description \"patent\u002Ffigures\u002F\"\n```\n\nIf no user figures, describe what figures should exist based on the claims.\n\nFormat:\n- CN: \"图1是...的示意图；图2是...的流程图；\"\n- US: \"FIG. 1 is a block diagram showing...; FIG. 2 is a flowchart illustrating...\"\n\n### Step 7: Write Detailed Description (具体实施方式)\n\nInvoke `\u002Fembodiment-description` as a sub-skill:\n```\n\u002Fembodiment-description \"patent\u002FCLAIMS.md\"\n```\n\nThis section must:\n- Describe at least one complete embodiment with reference numerals\n- Enable a POSITA to make and use the invention\n- Support every claim element with explicit description\n- Include variations and alternatives for broader claim interpretation\n\n### Step 8: Write Abstract (摘要)\n\nJurisdiction-specific word limits:\n\n| Jurisdiction | Word Limit | Notes |\n|-------------|-----------|-------|\n| CN | 300 words (Chinese characters) | Include most representative claim reference |\n| US | 150 words (2500 characters) | Enable efficient searching, no legal phrases |\n| EP | ~150 words | No statements on merits or value |\n\nThe abstract summarizes:\n1. The technical field\n2. The problem being solved\n3. The technical solution (core features)\n4. Key advantages\n\n### Step 9: Claim Support Verification\n\nVerify every claim element finds support in the specification:\n\n| Claim | Element | Specification Section | Paragraph(s) | Reference Numeral |\n|-------|---------|----------------------|-------------|-------------------|\n| 1 | step a | detailed_description | ¶3 | 202 |\n| 1 | step b | detailed_description | ¶4 | 204 |\n| X | component A | detailed_description | ¶2 | 102 |\n\nIf any element lacks support, add the necessary description before proceeding.\n\n### Step 10: Cross-Model Review\n\nCall `REVIEWER_MODEL` via `mcp__codex__codex` with xhigh reasoning:\n\n```\nmcp__codex__codex:\n  model: gpt-6-astra\n  config: {\"model_reasoning_effort\": \"xhigh\"}\n  prompt: |\n    You are a patent examiner reviewing a specification for completeness.\n    CLAIMS: [all claims]\n    SPECIFICATION: [all specification sections]\n\n    Check for:\n    1. Written description support: Does every claim element have explicit or inherent support?\n    2. Enablement: Can a POSITA practice the invention from this specification?\n    3. Consistency: Do reference numerals match across figures and specification?\n    4. Language quality: Any subjective terms, relative terms without definition, or result-to-be-achieved language?\n    5. Missing embodiments: Are there claim features that need additional embodiments?\n    6. Background deficiencies: Are they technical and specific enough?\n```\n\n### Step 11: Output\n\nAll specification sections are in `patent\u002Fspecification\u002F`.\n\nSummary file: `patent\u002Fspecification\u002FSPECIFICATION_INDEX.md` with:\n```markdown\n## Patent Specification\n\n### Sections\n| Section | File | Word Count | Status |\n|---------|------|-----------|--------|\n| Title | title.md | | Complete |\n| Technical Field | technical_field.md | | Complete |\n| Background | background.md | | Complete |\n| Summary | summary.md | | Complete |\n| Drawings Description | drawings_description.md | | Complete |\n| Detailed Description | detailed_description.md | | Complete |\n| Abstract | abstract.md | | Complete |\n\n### Claim Support Status\n| Claim | Elements Supported | Elements Missing |\n|-------|-------------------|-----------------|\n| 1 | All | None |\n| X | All | None |\n```\n\n## Key Rules\n\n- The specification supports the claims, not the other way around. Every claim element must have support.\n- Use consistent terminology -- same word for the same concept throughout.\n- DO NOT include experimental results, accuracy metrics, or empirical evaluations.\n- DO NOT use subjective language (\"excellent\", \"surprising\", \"superior\").\n- Reference numerals must be consistent: same component, same numeral, everywhere.\n- Background section describes specific deficiencies, not general \"need for improvement.\"\n- Multiple embodiments strengthen the specification but are not always required.\n- Large file handling: if a Write operation fails, retry with Bash `cat \u003C\u003C'EOF'` heredoc.\n- If `mcp__codex__codex` is not available, skip cross-model review and note it in the output.\n",{"name":5,"description":7,"allowed-tools":24,"argument-hint":25},"Bash(*), Read, Write, Edit, Grep, Glob, Skill, WebSearch, WebFetch, mcp__codex__codex, mcp__codex__codex-reply","[claims-path]","main","18193d71ea3441d7c033dbf195b8a7c75ac96f75","packages\u002Fskill\u002Fskill-science\u002Fassets\u002Fsources\u002Faris\u002Fskills\u002Fspecification-writing",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 specification-writing",{"tool":40,"command":41},"bunx","bunx skills add CZX-LBJ\u002Fdeepseek-science --skill specification-writing",{"tool":43,"command":44},"pnpm","pnpm dlx skills add CZX-LBJ\u002Fdeepseek-science --skill specification-writing","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\u002Fspecification-writing\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},"01M7FED69GFB54FRF7AV5066DN","writing-systems-papers","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.","https:\u002F\u002Fgithub.com\u002FCZX-LBJ\u002Fdeepseek-science\u002Fblob\u002Fmain\u002Fpackages\u002Fskill\u002Fskill-science\u002Fassets\u002Fsources\u002Faris\u002Fskills\u002Fwriting-systems-papers\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},"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":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},"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",[],[]]