[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7FD7NK0QWH4EP19V4WZC3K6":3,"skill-same:01M7FD7NK0QWH4EP19V4WZC3K6":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},"01M7FD7NK0QWH4EP19V4WZC3K6","prior-art-search",null,"Search patent databases and academic literature for prior art relevant to an invention. Use when user says \"现有技术检索\", \"prior art search\", \"专利检索\", \"check patents\", or wants to find relevant prior art.","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\u002Fprior-art-search\u002FSKILL.md",[],[],"2026-11-16 10:05:34",false,"---\nname: prior-art-search\ndescription: \"Search patent databases and academic literature for prior art relevant to an invention. Use when user says \\\"现有技术检索\\\", \\\"prior art search\\\", \\\"专利检索\\\", \\\"check patents\\\", or wants to find relevant prior art.\"\nargument-hint: \"[invention-description-or-path]\"\nallowed-tools: Bash(*), Read, Glob, Grep, WebSearch, WebFetch, Write\n---\n\n# Prior Art Search\n\nSearch patents and literature for prior art relevant to: **$ARGUMENTS**\n\nAdapted from `\u002Fresearch-lit` for patent-specific searching.\n\n## Constants\n\n- `MAX_PATENT_RESULTS = 20` — Maximum patent documents to analyze in detail\n- `MAX_PAPER_RESULTS = 15` — Maximum academic papers to analyze in detail\n- `SEARCH_YEARS = 10` — How many years back to search\n- `PATENT_DATABASES = \"google-patents, espacenet\"` — Patent databases to search\n\n## Inputs\n\nRead the invention description from:\n1. `$ARGUMENTS` if it contains technical details\n2. `patent\u002FINVENTION_BRIEF.md` if it exists\n3. `INVENTION_BRIEF.md` if it exists at project root\n\n## Shared References\n\nLoad `..\u002Fshared-references\u002Fprior-art-databases.md` for search strategy templates and IPC\u002FCPC classification guidance.\n\n## Workflow\n\n### Step 1: Extract Search Concepts\n\nFrom the invention description, identify:\n1. **Core inventive concept**: The primary technical contribution (1-2 sentences)\n2. **Technical problem**: What problem it solves\n3. **Key technical features**: 4-6 specific technical elements that define the invention\n4. **IPC\u002FCPC classes**: Predict relevant classification codes (e.g., G06N, G06F)\n\n### Step 2: Patent Search\n\nFor EACH search concept, search via:\n\n**Google Patents** (via WebSearch):\n```\nWebSearch: \"site:patents.google.com [keywords]\"\nWebSearch: \"[keywords] patent\"\n```\n- Try primary keywords + technical problem keywords\n- Search in English regardless of target jurisdiction\n- For CN inventions, also search Chinese keywords via WebSearch\n\n**Espacenet** (via WebFetch):\n- WebFetch worldwide.espacenet.com\u002Fsearch results for key queries\n- Search by predicted IPC\u002FCPC classes\n\n**Assignee\u002FInventor Search**:\n- If known companies\u002Funiversities work in this area, search their patent portfolios\n- WebSearch: \"[assignee name] patent [technical area]\"\n\nFor each potentially relevant patent found:\n- WebFetch the patent page to extract: title, abstract, representative claims, filing date, assignee, current status\n- Record IPC\u002FCPC classification codes\n\n### Step 3: Academic Literature Search\n\nSearch the same concepts in academic databases:\n\n1. **Google Scholar** (via WebSearch): `WebSearch \"[keywords] site:scholar.google.com\"`\n2. **arXiv** (via `\u002Farxiv` if available, or WebSearch): Search for preprints\n3. **Semantic Scholar** (via `\u002Fsemantic-scholar` if API key set, or WebSearch)\n\nFor each relevant paper found:\n- Extract title, authors, venue, year, key contribution\n\n### Step 4: Classification and Analysis\n\nFor each reference found, assess:\n\n1. **Relevance**: How closely does it relate to the invention?\n2. **Overlap Risk**: Does it disclose the same or similar technical solution?\n   - HIGH: Anticipates one or more claim elements\n   - MEDIUM: Discloses a related but different approach\n   - LOW: Same general field, different approach\n3. **Relationship**: Is it anticipating, relevant, or merely background?\n\nOrganize results by IPC\u002FCPC classification to see the technical landscape.\n\n### Step 5: Freedom-to-Operate Assessment (Preliminary)\n\nBased on the search results:\n- Identify patents with claims that potentially cover the invention\n- Note any expired patents (public domain)\n- Flag areas where claim scope overlap is significant\n\n**Disclaimer**: This is a preliminary assessment only. A professional freedom-to-operate analysis by a patent attorney is recommended before filing.\n\n### Step 6: Output\n\nWrite `patent\u002FPRIOR_ART_REPORT.md` with:\n\n```markdown\n## Prior Art Search Report\n\n### Invention Summary\n[1-2 sentence description of the searched invention]\n\n### Search Strategy\n- Keywords used: [...]\n- IPC\u002FCPC classes searched: [...]\n- Databases searched: Google Patents, Espacenet, Google Scholar, arXiv\n- Date range: [year] to present\n\n### Patent References Found\n\n| # | Patent No. | Title | Date | Assignee | IPC\u002FCPC | Key Teaching | Overlap Risk |\n|---|-----------|-------|------|----------|---------|-------------|-------------|\n| 1 | CN... \u002F US... | [title] | [date] | [assignee] | [codes] | [2-3 sentences] | HIGH\u002FMEDIUM\u002FLOW |\n\n### Non-Patent Literature Found\n\n| # | Reference | Title | Authors\u002FVenue | Year | Key Contribution | Relevance |\n|---|-----------|-------|--------------|------|-----------------|-----------|\n| 1 | [DOI\u002Flink] | [title] | [authors] | [year] | [1-2 sentences] | HIGH\u002FMEDIUM\u002FLOW |\n\n### Prior Art Landscape\n[Organized by technical approach or IPC class, not just chronological]\n\n### Freedom-to-Operate Preliminary Assessment\n[Which existing patents might block the invention? What is the risk level?]\n\n### Recommendations\n- Suggested claim scope adjustments based on prior art\n- Areas where novelty appears strongest\n- References to watch during prosecution\n```\n\n## Key Rules\n\n- Never fabricate patent numbers or citations. Mark uncertain references with `[VERIFY]`.\n- Search in English AND the target jurisdiction language (Chinese for CN).\n- Patent prior art includes everything published before the priority date, not just patents.\n- Academic papers are valid prior art for both novelty and inventive step.\n- Include expired patents -- they are public domain but still relevant for novelty.\n","# Prior Art Search\n\nSearch patents and literature for prior art relevant to: **$ARGUMENTS**\n\nAdapted from `\u002Fresearch-lit` for patent-specific searching.\n\n## Constants\n\n- `MAX_PATENT_RESULTS = 20` — Maximum patent documents to analyze in detail\n- `MAX_PAPER_RESULTS = 15` — Maximum academic papers to analyze in detail\n- `SEARCH_YEARS = 10` — How many years back to search\n- `PATENT_DATABASES = \"google-patents, espacenet\"` — Patent databases to search\n\n## Inputs\n\nRead the invention description from:\n1. `$ARGUMENTS` if it contains technical details\n2. `patent\u002FINVENTION_BRIEF.md` if it exists\n3. `INVENTION_BRIEF.md` if it exists at project root\n\n## Shared References\n\nLoad `..\u002Fshared-references\u002Fprior-art-databases.md` for search strategy templates and IPC\u002FCPC classification guidance.\n\n## Workflow\n\n### Step 1: Extract Search Concepts\n\nFrom the invention description, identify:\n1. **Core inventive concept**: The primary technical contribution (1-2 sentences)\n2. **Technical problem**: What problem it solves\n3. **Key technical features**: 4-6 specific technical elements that define the invention\n4. **IPC\u002FCPC classes**: Predict relevant classification codes (e.g., G06N, G06F)\n\n### Step 2: Patent Search\n\nFor EACH search concept, search via:\n\n**Google Patents** (via WebSearch):\n```\nWebSearch: \"site:patents.google.com [keywords]\"\nWebSearch: \"[keywords] patent\"\n```\n- Try primary keywords + technical problem keywords\n- Search in English regardless of target jurisdiction\n- For CN inventions, also search Chinese keywords via WebSearch\n\n**Espacenet** (via WebFetch):\n- WebFetch worldwide.espacenet.com\u002Fsearch results for key queries\n- Search by predicted IPC\u002FCPC classes\n\n**Assignee\u002FInventor Search**:\n- If known companies\u002Funiversities work in this area, search their patent portfolios\n- WebSearch: \"[assignee name] patent [technical area]\"\n\nFor each potentially relevant patent found:\n- WebFetch the patent page to extract: title, abstract, representative claims, filing date, assignee, current status\n- Record IPC\u002FCPC classification codes\n\n### Step 3: Academic Literature Search\n\nSearch the same concepts in academic databases:\n\n1. **Google Scholar** (via WebSearch): `WebSearch \"[keywords] site:scholar.google.com\"`\n2. **arXiv** (via `\u002Farxiv` if available, or WebSearch): Search for preprints\n3. **Semantic Scholar** (via `\u002Fsemantic-scholar` if API key set, or WebSearch)\n\nFor each relevant paper found:\n- Extract title, authors, venue, year, key contribution\n\n### Step 4: Classification and Analysis\n\nFor each reference found, assess:\n\n1. **Relevance**: How closely does it relate to the invention?\n2. **Overlap Risk**: Does it disclose the same or similar technical solution?\n   - HIGH: Anticipates one or more claim elements\n   - MEDIUM: Discloses a related but different approach\n   - LOW: Same general field, different approach\n3. **Relationship**: Is it anticipating, relevant, or merely background?\n\nOrganize results by IPC\u002FCPC classification to see the technical landscape.\n\n### Step 5: Freedom-to-Operate Assessment (Preliminary)\n\nBased on the search results:\n- Identify patents with claims that potentially cover the invention\n- Note any expired patents (public domain)\n- Flag areas where claim scope overlap is significant\n\n**Disclaimer**: This is a preliminary assessment only. A professional freedom-to-operate analysis by a patent attorney is recommended before filing.\n\n### Step 6: Output\n\nWrite `patent\u002FPRIOR_ART_REPORT.md` with:\n\n```markdown\n## Prior Art Search Report\n\n### Invention Summary\n[1-2 sentence description of the searched invention]\n\n### Search Strategy\n- Keywords used: [...]\n- IPC\u002FCPC classes searched: [...]\n- Databases searched: Google Patents, Espacenet, Google Scholar, arXiv\n- Date range: [year] to present\n\n### Patent References Found\n\n| # | Patent No. | Title | Date | Assignee | IPC\u002FCPC | Key Teaching | Overlap Risk |\n|---|-----------|-------|------|----------|---------|-------------|-------------|\n| 1 | CN... \u002F US... | [title] | [date] | [assignee] | [codes] | [2-3 sentences] | HIGH\u002FMEDIUM\u002FLOW |\n\n### Non-Patent Literature Found\n\n| # | Reference | Title | Authors\u002FVenue | Year | Key Contribution | Relevance |\n|---|-----------|-------|--------------|------|-----------------|-----------|\n| 1 | [DOI\u002Flink] | [title] | [authors] | [year] | [1-2 sentences] | HIGH\u002FMEDIUM\u002FLOW |\n\n### Prior Art Landscape\n[Organized by technical approach or IPC class, not just chronological]\n\n### Freedom-to-Operate Preliminary Assessment\n[Which existing patents might block the invention? What is the risk level?]\n\n### Recommendations\n- Suggested claim scope adjustments based on prior art\n- Areas where novelty appears strongest\n- References to watch during prosecution\n```\n\n## Key Rules\n\n- Never fabricate patent numbers or citations. Mark uncertain references with `[VERIFY]`.\n- Search in English AND the target jurisdiction language (Chinese for CN).\n- Patent prior art includes everything published before the priority date, not just patents.\n- Academic papers are valid prior art for both novelty and inventive step.\n- Include expired patents -- they are public domain but still relevant for novelty.\n",{"name":5,"description":7,"allowed-tools":24,"argument-hint":25},"Bash(*), Read, Glob, Grep, WebSearch, WebFetch, Write","[invention-description-or-path]","main","18193d71ea3441d7c033dbf195b8a7c75ac96f75","packages\u002Fskill\u002Fskill-science\u002Fassets\u002Fsources\u002Faris\u002Fskills\u002Fprior-art-search",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 prior-art-search",{"tool":40,"command":41},"bunx","bunx skills add CZX-LBJ\u002Fdeepseek-science --skill prior-art-search",{"tool":43,"command":44},"pnpm","pnpm dlx skills add CZX-LBJ\u002Fdeepseek-science --skill prior-art-search","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\u002Fprior-art-search\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",[],[]]