[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7FCY2JJSXZ1HA7DX0HNGAR7":3,"skill-same:01M7FCY2JJSXZ1HA7DX0HNGAR7":47},{"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":25,"commitSha":26,"skillDirectory":27,"forksCount":28,"repositoryHtmlUrl":29,"repositoryHomepageUrl":6,"ownerHtmlUrl":30,"ownerBlogUrl":6,"ownerDescription":31,"updatedAt":32,"install":33,"resources":46},"01M7FCY2JJSXZ1HA7DX0HNGAR7","comm-lit-review",null,"Communications-domain literature review with Claude-style knowledge-base-first retrieval. Use when the task is about communications, wireless, networking, satellite\u002FNTN, Wi-Fi, cellular, transport protocols, congestion control, routing, scheduling, MAC\u002FPHY, rate adaptation, channel estimation, beamforming, or communication-system research and the user wants papers, related work, a survey, or a landscape summary.","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\u002Fcomm-lit-review\u002FSKILL.md",[],[],"2026-11-16 10:05:34",false,"---\nname: comm-lit-review\ndescription: \"Communications-domain literature review with Claude-style knowledge-base-first retrieval. Use when the task is about communications, wireless, networking, satellite\u002FNTN, Wi-Fi, cellular, transport protocols, congestion control, routing, scheduling, MAC\u002FPHY, rate adaptation, channel estimation, beamforming, or communication-system research and the user wants papers, related work, a survey, or a landscape summary.\"\nallowed-tools: Bash(*), Read, Glob, Grep, WebSearch, WebFetch, Write, mcp__zotero__*, mcp__obsidian-vault__*\n---\n\n# Comm Lit Review Claude Single\n\nResearch topic: $ARGUMENTS\n\n## Purpose\n\nUse this skill for communications-domain literature review when the topic is about:\n\n- wireless communications\n- cellular systems, `4G\u002F5G\u002F6G`, `NR`, `NTN`\n- satellite, `LEO`, `GEO`, integrated space-air-ground systems\n- Wi-Fi, WLAN, mesh, ad hoc, sidelink, V2X\n- routing, scheduling, resource allocation, beamforming\n- rate adaptation, link adaptation, `ACM`, `HARQ`, `CSI` feedback\n- transport protocols and congestion control in communication networks\n- cross-layer optimization for communication systems\n\nIf the center of gravity is generic ML architecture research, pure control theory without communications literature, or software\u002FAPI documentation rather than papers, fall back to a general literature skill.\n\n## Constants\n\n- **PAPER_LIBRARY**: Check local PDFs in this order:\n  1. `papers\u002F` in the current project\n  2. `literature\u002F` in the current project\n  3. Custom path specified by the user in `CLAUDE.md` under `## Paper Library`\n- **MAX_LOCAL_PAPERS = 20**: Maximum number of local PDFs to scan. If there are more, prioritize by filename and first-page relevance.\n\n## Source Selection\n\nParse `$ARGUMENTS` for a `— sources:` directive.\n\n- If `— sources:` is specified, only search the listed sources.\n- If not specified, default to:\n  - `zotero`\n  - `obsidian`\n  - `local`\n  - `ieee`\n  - `sciencedirect`\n  - `acm`\n  - `web`\n\nValid source values:\n\n- `zotero`\n- `obsidian`\n- `local`\n- `ieee`\n- `sciencedirect`\n- `acm`\n- `web`\n- `all`\n\nIf `all` is specified, interpret it as the full default source set.\n\n## Retrieval Order\n\nThis is a knowledge-base-first skill. Search in this order unless the user overrides it:\n\n1. `Zotero`\n2. `Obsidian`\n3. local `papers\u002F` and `literature\u002F`\n4. `IEEE Xplore`\n5. `ScienceDirect`\n6. `ACM Digital Library`\n7. broader web\n\nGraceful degradation rules:\n\n- If a source is unavailable, do not fail.\n- Skip it silently.\n- Continue to the next source.\n\n## External Search Policy\n\nFor external search:\n\n- prefer `IEEE Xplore` first\n- then `ScienceDirect`\n- then `ACM`\n- then broader web only when needed\n\nPublication policy:\n\n- prefer peer-reviewed journals and major conferences\n- label workshop papers as `workshop`\n- label arXiv-only or author-hosted versions as `preprint`\n- if both preprint and formal version exist, cite the formal version first\n\nTime-window policy:\n\n- if the user does not specify a year range, include both a short foundational set and a recent set\n- recommended split:\n  - `foundational`: before 2022\n  - `recent`: 2022 to present\n\n## Venue Priority\n\nWithin each database tier, search venue tiers in this order.\n\n### Tier A\n\nJournals:\n\n- `IEEE Journal on Selected Areas in Communications (JSAC)`\n- `IEEE\u002FACM Transactions on Networking (ToN)`\n- `IEEE Transactions on Wireless Communications (TWC)`\n- `IEEE Transactions on Communications (TCOM)`\n\nConferences:\n\n- `ACM SIGCOMM`\n- `USENIX NSDI`\n- `ACM MobiCom`\n- `ACM CoNEXT`\n- `IEEE INFOCOM`\n\n### Tier B\n\nJournals:\n\n- `IEEE Transactions on Vehicular Technology (TVT)`\n- `IEEE Wireless Communications Letters (WCL)`\n- `IEEE Communications Letters`\n- `Computer Networks`\n- `Computer Communications`\n- `Ad Hoc Networks`\n- `Physical Communication`\n\nConferences:\n\n- `IEEE ICC`\n- `IEEE GLOBECOM`\n- `IEEE WCNC`\n- `IEEE PIMRC`\n- `ACM MobiHoc`\n\n### Tier C\n\n- other relevant IEEE journals and transactions\n- other relevant Elsevier journals\n- other clearly relevant ACM conferences and workshops\n- topic-specific satellite, optical, vehicular, IoT, aerial, or edge communications venues\n\nUsage rules:\n\n- start from Tier A\n- widen to Tier B if needed\n- widen to Tier C if still sparse\n- only then broaden to full web search\n- by default this is a soft priority, not a hard whitelist\n- if the user says `only top venues`, `top journals only`, or `top conferences only`, treat Tier A as a hard filter\n\n## Workflow\n\n### Step 0a: Search Zotero Library\n\nSkip this step if Zotero MCP is not configured or `zotero` is not enabled.\n\nIf available:\n\n1. search by topic\n2. capture title, authors, year, venue\n3. pull user annotations, tags, or collections when present\n4. treat these as high-priority evidence because they reflect the user's existing library\n\n### Step 0b: Search Obsidian Vault\n\nSkip this step if Obsidian MCP is not configured or `obsidian` is not enabled.\n\nIf available:\n\n1. search topic-related notes\n2. collect summaries, wikilinks, tags, and paper references\n3. treat these notes as the user's processed understanding of the topic\n\n### Step 0c: Scan Local Paper Library\n\nRun this step if `local` is enabled.\n\n1. locate PDFs from `papers\u002F**\u002F*.pdf` and `literature\u002F**\u002F*.pdf`\n2. de-duplicate against Zotero hits when possible\n3. read the first pages of relevant PDFs\n4. extract title, authors, year, problem, method, and relevance\n5. use local hits to guide and de-duplicate later external search\n\n### Step 1: Search External Primary Sources\n\nUse a layered search strategy. For communications topics, avoid random blog posts or tertiary summaries.\n\nDatabase ladder:\n\n1. `ieeexplore.ieee.org`\n2. `sciencedirect.com`\n3. `dl.acm.org`\n4. broader web using primary publisher pages, official conference sites, DOI pages, and author-hosted copies of already-identified formal papers\n\nMove to the next database tier only when:\n\n- the higher-priority tier is too sparse\n- the topic clearly publishes elsewhere\n- the user explicitly asks for broader coverage\n\nWithin each database tier:\n\n1. start from Tier A venues\n2. widen to Tier B if needed\n3. widen to Tier C if still sparse\n\n### Step 2: Extract Paper-Level Facts\n\nFor each relevant paper, capture:\n\n- Title\n- Authors\n- Year\n- Venue\n- Layer or system scope\n- Scenario and assumptions\n- Core method\n- Main result or claim\n- Limitation\n- Relevance to the user's topic\n- Source URL\n- Source origin: `zotero`, `obsidian`, `local`, `ieee`, `sciencedirect`, `acm`, or `web`\n\nFavor concrete numbers, assumptions, and problem definitions over generic paraphrases.\n\nDo not collapse transport-layer rate control and PHY\u002FMAC rate adaptation into one bucket without saying so explicitly.\n\n## Synthesis Rules\n\nGroup papers by technical axis rather than by search order. Common groupings:\n\n- `PHY\u002FMAC` adaptation\n- transport and congestion control\n- `NTN` and satellite resource management\n- cross-layer or learning-based control\n- measurement and empirical studies\n\nWhen useful, explicitly separate:\n\n- foundational vs recent work\n- formal publications vs preprints\n- top-tier vs lower-tier venues\n- single-link vs multi-user formulations\n- simulation-only vs deployment-backed work\n- user-owned sources vs newly surfaced external papers\n\nIf evidence is weak, say so instead of smoothing it over.\n\n## Output\n\nUse a literature table with these columns:\n\n| Paper | Venue | Year | Layer | Scenario | Method | Key Result | Limitation | Relevance | Source |\n|---|---|---:|---|---|---|---|---|---|---|\n\n`Source` should indicate where the paper came from first:\n\n- `zotero`\n- `obsidian`\n- `local`\n- `ieee`\n- `sciencedirect`\n- `acm`\n- `web`\n\nAfter the table, summarize in this order:\n\n1. what the field is mostly trying to solve\n2. how papers cluster into `2-4` approaches\n3. what the user already had vs what was newly surfaced\n4. where the evidence is strong vs weak\n5. what research gap remains\n\nEnd with `Practical Takeaway`:\n\n- dominant current approach\n- likely saturated direction\n- promising open direction\n\n## Key Rules\n\n- Never fail because Zotero or Obsidian MCP is missing.\n- Prefer user-owned sources first when available, but do not let them replace external validation.\n- Prefer primary formal sources over summaries or tertiary commentary.\n- Prefer `IEEE` and `ScienceDirect` first, `ACM` second, and only then broader web search unless the user asks otherwise.\n- Search venue tiers from top to broad within each database tier.\n- Treat venue tiers as soft ranking by default and hard constraint only when the user explicitly asks for top-only search.\n- Do not pretend a preprint is peer reviewed.\n- If the topic spans multiple layers, say that the literature itself is split across layers.\n","# Comm Lit Review Claude Single\n\nResearch topic: $ARGUMENTS\n\n## Purpose\n\nUse this skill for communications-domain literature review when the topic is about:\n\n- wireless communications\n- cellular systems, `4G\u002F5G\u002F6G`, `NR`, `NTN`\n- satellite, `LEO`, `GEO`, integrated space-air-ground systems\n- Wi-Fi, WLAN, mesh, ad hoc, sidelink, V2X\n- routing, scheduling, resource allocation, beamforming\n- rate adaptation, link adaptation, `ACM`, `HARQ`, `CSI` feedback\n- transport protocols and congestion control in communication networks\n- cross-layer optimization for communication systems\n\nIf the center of gravity is generic ML architecture research, pure control theory without communications literature, or software\u002FAPI documentation rather than papers, fall back to a general literature skill.\n\n## Constants\n\n- **PAPER_LIBRARY**: Check local PDFs in this order:\n  1. `papers\u002F` in the current project\n  2. `literature\u002F` in the current project\n  3. Custom path specified by the user in `CLAUDE.md` under `## Paper Library`\n- **MAX_LOCAL_PAPERS = 20**: Maximum number of local PDFs to scan. If there are more, prioritize by filename and first-page relevance.\n\n## Source Selection\n\nParse `$ARGUMENTS` for a `— sources:` directive.\n\n- If `— sources:` is specified, only search the listed sources.\n- If not specified, default to:\n  - `zotero`\n  - `obsidian`\n  - `local`\n  - `ieee`\n  - `sciencedirect`\n  - `acm`\n  - `web`\n\nValid source values:\n\n- `zotero`\n- `obsidian`\n- `local`\n- `ieee`\n- `sciencedirect`\n- `acm`\n- `web`\n- `all`\n\nIf `all` is specified, interpret it as the full default source set.\n\n## Retrieval Order\n\nThis is a knowledge-base-first skill. Search in this order unless the user overrides it:\n\n1. `Zotero`\n2. `Obsidian`\n3. local `papers\u002F` and `literature\u002F`\n4. `IEEE Xplore`\n5. `ScienceDirect`\n6. `ACM Digital Library`\n7. broader web\n\nGraceful degradation rules:\n\n- If a source is unavailable, do not fail.\n- Skip it silently.\n- Continue to the next source.\n\n## External Search Policy\n\nFor external search:\n\n- prefer `IEEE Xplore` first\n- then `ScienceDirect`\n- then `ACM`\n- then broader web only when needed\n\nPublication policy:\n\n- prefer peer-reviewed journals and major conferences\n- label workshop papers as `workshop`\n- label arXiv-only or author-hosted versions as `preprint`\n- if both preprint and formal version exist, cite the formal version first\n\nTime-window policy:\n\n- if the user does not specify a year range, include both a short foundational set and a recent set\n- recommended split:\n  - `foundational`: before 2022\n  - `recent`: 2022 to present\n\n## Venue Priority\n\nWithin each database tier, search venue tiers in this order.\n\n### Tier A\n\nJournals:\n\n- `IEEE Journal on Selected Areas in Communications (JSAC)`\n- `IEEE\u002FACM Transactions on Networking (ToN)`\n- `IEEE Transactions on Wireless Communications (TWC)`\n- `IEEE Transactions on Communications (TCOM)`\n\nConferences:\n\n- `ACM SIGCOMM`\n- `USENIX NSDI`\n- `ACM MobiCom`\n- `ACM CoNEXT`\n- `IEEE INFOCOM`\n\n### Tier B\n\nJournals:\n\n- `IEEE Transactions on Vehicular Technology (TVT)`\n- `IEEE Wireless Communications Letters (WCL)`\n- `IEEE Communications Letters`\n- `Computer Networks`\n- `Computer Communications`\n- `Ad Hoc Networks`\n- `Physical Communication`\n\nConferences:\n\n- `IEEE ICC`\n- `IEEE GLOBECOM`\n- `IEEE WCNC`\n- `IEEE PIMRC`\n- `ACM MobiHoc`\n\n### Tier C\n\n- other relevant IEEE journals and transactions\n- other relevant Elsevier journals\n- other clearly relevant ACM conferences and workshops\n- topic-specific satellite, optical, vehicular, IoT, aerial, or edge communications venues\n\nUsage rules:\n\n- start from Tier A\n- widen to Tier B if needed\n- widen to Tier C if still sparse\n- only then broaden to full web search\n- by default this is a soft priority, not a hard whitelist\n- if the user says `only top venues`, `top journals only`, or `top conferences only`, treat Tier A as a hard filter\n\n## Workflow\n\n### Step 0a: Search Zotero Library\n\nSkip this step if Zotero MCP is not configured or `zotero` is not enabled.\n\nIf available:\n\n1. search by topic\n2. capture title, authors, year, venue\n3. pull user annotations, tags, or collections when present\n4. treat these as high-priority evidence because they reflect the user's existing library\n\n### Step 0b: Search Obsidian Vault\n\nSkip this step if Obsidian MCP is not configured or `obsidian` is not enabled.\n\nIf available:\n\n1. search topic-related notes\n2. collect summaries, wikilinks, tags, and paper references\n3. treat these notes as the user's processed understanding of the topic\n\n### Step 0c: Scan Local Paper Library\n\nRun this step if `local` is enabled.\n\n1. locate PDFs from `papers\u002F**\u002F*.pdf` and `literature\u002F**\u002F*.pdf`\n2. de-duplicate against Zotero hits when possible\n3. read the first pages of relevant PDFs\n4. extract title, authors, year, problem, method, and relevance\n5. use local hits to guide and de-duplicate later external search\n\n### Step 1: Search External Primary Sources\n\nUse a layered search strategy. For communications topics, avoid random blog posts or tertiary summaries.\n\nDatabase ladder:\n\n1. `ieeexplore.ieee.org`\n2. `sciencedirect.com`\n3. `dl.acm.org`\n4. broader web using primary publisher pages, official conference sites, DOI pages, and author-hosted copies of already-identified formal papers\n\nMove to the next database tier only when:\n\n- the higher-priority tier is too sparse\n- the topic clearly publishes elsewhere\n- the user explicitly asks for broader coverage\n\nWithin each database tier:\n\n1. start from Tier A venues\n2. widen to Tier B if needed\n3. widen to Tier C if still sparse\n\n### Step 2: Extract Paper-Level Facts\n\nFor each relevant paper, capture:\n\n- Title\n- Authors\n- Year\n- Venue\n- Layer or system scope\n- Scenario and assumptions\n- Core method\n- Main result or claim\n- Limitation\n- Relevance to the user's topic\n- Source URL\n- Source origin: `zotero`, `obsidian`, `local`, `ieee`, `sciencedirect`, `acm`, or `web`\n\nFavor concrete numbers, assumptions, and problem definitions over generic paraphrases.\n\nDo not collapse transport-layer rate control and PHY\u002FMAC rate adaptation into one bucket without saying so explicitly.\n\n## Synthesis Rules\n\nGroup papers by technical axis rather than by search order. Common groupings:\n\n- `PHY\u002FMAC` adaptation\n- transport and congestion control\n- `NTN` and satellite resource management\n- cross-layer or learning-based control\n- measurement and empirical studies\n\nWhen useful, explicitly separate:\n\n- foundational vs recent work\n- formal publications vs preprints\n- top-tier vs lower-tier venues\n- single-link vs multi-user formulations\n- simulation-only vs deployment-backed work\n- user-owned sources vs newly surfaced external papers\n\nIf evidence is weak, say so instead of smoothing it over.\n\n## Output\n\nUse a literature table with these columns:\n\n| Paper | Venue | Year | Layer | Scenario | Method | Key Result | Limitation | Relevance | Source |\n|---|---|---:|---|---|---|---|---|---|---|\n\n`Source` should indicate where the paper came from first:\n\n- `zotero`\n- `obsidian`\n- `local`\n- `ieee`\n- `sciencedirect`\n- `acm`\n- `web`\n\nAfter the table, summarize in this order:\n\n1. what the field is mostly trying to solve\n2. how papers cluster into `2-4` approaches\n3. what the user already had vs what was newly surfaced\n4. where the evidence is strong vs weak\n5. what research gap remains\n\nEnd with `Practical Takeaway`:\n\n- dominant current approach\n- likely saturated direction\n- promising open direction\n\n## Key Rules\n\n- Never fail because Zotero or Obsidian MCP is missing.\n- Prefer user-owned sources first when available, but do not let them replace external validation.\n- Prefer primary formal sources over summaries or tertiary commentary.\n- Prefer `IEEE` and `ScienceDirect` first, `ACM` second, and only then broader web search unless the user asks otherwise.\n- Search venue tiers from top to broad within each database tier.\n- Treat venue tiers as soft ranking by default and hard constraint only when the user explicitly asks for top-only search.\n- Do not pretend a preprint is peer reviewed.\n- If the topic spans multiple layers, say that the literature itself is split across layers.\n",{"name":5,"description":7,"allowed-tools":24},"Bash(*), Read, Glob, Grep, WebSearch, WebFetch, Write, mcp__zotero__*, mcp__obsidian-vault__*","main","18193d71ea3441d7c033dbf195b8a7c75ac96f75","packages\u002Fskill\u002Fskill-science\u002Fassets\u002Fsources\u002Faris\u002Fskills\u002Fcomm-lit-review",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":34,"prompt":44,"zipAvailable":45},[35,38,41],{"tool":36,"command":37},"npx","npx skills add CZX-LBJ\u002Fdeepseek-science --skill comm-lit-review",{"tool":39,"command":40},"bunx","bunx skills add CZX-LBJ\u002Fdeepseek-science --skill comm-lit-review",{"tool":42,"command":43},"pnpm","pnpm dlx skills add CZX-LBJ\u002Fdeepseek-science --skill comm-lit-review","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\u002Fcomm-lit-review\u002FSKILL.md",true,[],[48,55,62,69,76,83],{"skillNo":49,"name":50,"nameZh":6,"description":51,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":52,"categories":53,"keywords":54,"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":56,"name":57,"nameZh":6,"description":58,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":59,"categories":60,"keywords":61,"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":63,"name":64,"nameZh":6,"description":65,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":66,"categories":67,"keywords":68,"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":70,"name":71,"nameZh":6,"description":72,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":73,"categories":74,"keywords":75,"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":77,"name":78,"nameZh":6,"description":79,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":80,"categories":81,"keywords":82,"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":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":89,"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",[],[]]