[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7FDP4P85844H04HW1RR01ZB":3,"skill-same:01M7FDP4P85844H04HW1RR01ZB":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},"01M7FDP4P85844H04HW1RR01ZB","gemini-search",null,"Search research papers via Gemini for broad literature discovery. Use when user says \"gemini search\", \"gemini papers\", \"search with gemini\", or wants AI-powered literature discovery beyond arXiv\u002FSemantic Scholar indexes.","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\u002Fskills-codex\u002Fgemini-search\u002FSKILL.md",[],[],"2026-11-16 10:05:34",false,"---\nname: gemini-search\ndescription: Search research papers via Gemini for broad literature discovery. Use when user says \"gemini search\", \"gemini papers\", \"search with gemini\", or wants AI-powered literature discovery beyond arXiv\u002FSemantic Scholar indexes.\nargument-hint: \"[search-query]\"\nallowed-tools: Bash(*), Read, Write, mcp__gemini-cli__*\n---\n\n# Gemini Literature Search\n\nSearch query: $ARGUMENTS\n\n## Role & Positioning\n\nThis skill uses Gemini as a **broad literature discovery** source:\n\n| Skill | Source | Best for |\n|-------|--------|----------|\n| `\u002Farxiv` | arXiv API | Latest preprints, cutting-edge unrefereed work |\n| `\u002Fsemantic-scholar` | Semantic Scholar API | Published venue papers (IEEE, ACM, Springer) with citation counts |\n| `\u002Fdeepxiv` | DeepXiv CLI | Layered reading: search, brief, section map, section reads |\n| `\u002Fexa-search` | Exa API | Broad web search: blogs, docs, news, companies, research papers |\n| `\u002Fgemini-search` | Gemini MCP \u002F CLI | **AI-powered broad literature discovery** — searches across multiple angles, aliases, and sub-problems |\n\nUse Gemini when you want AI-driven discovery that goes beyond keyword matching — Gemini decomposes topics into sub-problems, explores naming variants, and surfaces papers that traditional API searches may miss.\n\n## Constants\n\n- **MAX_RESULTS = 15** — Target number of papers Gemini should find.\n- **MIN_YEAR = 2022** — Default minimum publication year. Override with `— year: 2020-`.\n- **DEFAULT_MODEL = auto-gemini-3** — Auto-routes within the Gemini 3 family (Pro \u002F Flash) by server-side capacity. Required by `mcp__gemini-cli__ask-gemini` and `gemini-cli` v0.40+; explicit `gemini-3-pro-preview` can be silently downgraded to `gemini-2.5-pro` on OAuth-personal \u002F Google One AI Pro accounts when capacity is exhausted. Override with `— model: gemini-3-flash-preview` (Gemini 3 Flash explicit, faster, higher quota), or `— model: gemini-2.5-pro` \u002F `gemini-2.5-flash` (legacy, only for users on older `gemini-cli` \u003C v0.40). The MCP tool accepts all of these verbatim.\n\n> Overrides (append to arguments):\n> - `\u002Fgemini-search \"topic\" — max: 20` — request up to 20 papers\n> - `\u002Fgemini-search \"topic\" — year: 2020-` — papers from 2020 onward\n> - `\u002Fgemini-search \"topic\" — code-only` — only papers with open-source code\n> - `\u002Fgemini-search \"topic\" — venues: NeurIPS,ICML,ICLR` — focus on specific venues\n> - `\u002Fgemini-search \"topic\" — model: gemini-3-flash-preview` — Gemini 3 Flash (faster, higher quota, less capable than Pro)\n> - `\u002Fgemini-search \"topic\" — model: auto-gemini-3` — auto-routes within the Gemini 3 family by load\n> - `\u002Fgemini-search \"topic\" — model: gemini-2.5-pro` — legacy (only if your `gemini-cli` \u003C v0.40)\n\n## Environment & Setup\n\n### Prerequisites\n\n1. **Node.js** v16.0.0+\n2. **Google Gemini CLI** — installed and authenticated\n   ```bash\n   npm install -g @google\u002Fgemini-cli\n   gemini auth\n   ```\n3. **gemini-mcp-tool** — MCP bridge for Codex CLI ([jamubc\u002Fgemini-mcp-tool](https:\u002F\u002Fgithub.com\u002Fjamubc\u002Fgemini-mcp-tool))\n   ```bash\n   npm install -g gemini-mcp-tool\n   ```\n\n### MCP Configuration\n\nRegister the Gemini bridge in Codex CLI:\n\n```bash\ncodex mcp add gemini-cli -- npx -y gemini-mcp-tool\n```\n\n### Authentication\n\nGemini CLI uses your Google account or an API key. Export the key in your shell or project environment:\n\n```bash\nexport GEMINI_API_KEY=your-key-here\n```\n\n- Free key from [Google AI Studio](https:\u002F\u002Faistudio.google.com\u002Fapikey)\n- Flash model (`gemini-2.5-flash`) has a generous free tier (500 req\u002Fmin)\n\n### Available MCP Tools\n\n| Tool | Parameters | Description |\n|------|-----------|-------------|\n| `mcp__gemini-cli__ask-gemini` | `prompt` (required), `model` (optional), `sandbox` (optional) | Ask Gemini for analysis or research; supports `@file` syntax |\n| `mcp__gemini-cli__sandbox-test` | `prompt` (required), `model` (optional) | Safe code execution in sandbox |\n| `mcp__gemini-cli__ping` | — | Connection test |\n| `mcp__gemini-cli__help` | — | Show Gemini CLI help |\n\n### Verify Setup\n\n```bash\ngemini --version\n```\n\n## Workflow\n\n### Step 1: Parse Arguments\n\nParse `$ARGUMENTS` for:\n- **query**: The research topic (required)\n- **max**: Override MAX_RESULTS\n- **year**: Minimum publication year (e.g., `2020-`)\n- **code-only**: Only include papers with open-source code\n- **venues**: Comma-separated venue filter\n- **model**: Override DEFAULT_MODEL\n\n### Step 2: Execute Search (MCP Priority)\n\n**Priority 1 — Gemini MCP** (preferred):\n\nTry calling `mcp__gemini-cli__ask-gemini` with the search prompt:\n\n```\nmcp__gemini-cli__ask-gemini({\n  prompt: 'You are a research literature scout. Search comprehensively for papers on: \"QUERY\"\n\nIMPORTANT CONSTRAINTS:\n1. Search from MULTIPLE angles — do not just use the exact query. Decompose the topic into sub-problems, aliases, neighboring tasks, and common benchmark\u002Fsettings variants.\n2. Prefer papers that are genuinely relevant, not merely keyword-adjacent.\n3. Include top venues, journals, surveys, recent preprints, and papers with code when available.\n4. Focus on papers from MIN_YEAR onward unless older foundational work is necessary.\n\nFor EACH paper found, provide ALL of the following in this exact format:\n- Title: [exact title]\n- Authors: [full author list]\n- Year: [publication year]\n- Venue: [exact conference\u002Fjournal name + year, or \"arXiv preprint\" if not published]\n- arXiv ID: [format 2401.12345, or \"N\u002FA\"]\n- DOI: [if available, or \"N\u002FA\"]\n- Code URL: [GitHub\u002FGitLab link if available, or \"No code\"]\n- Summary: [one-sentence core contribution]\n\nFind at least MAX_RESULTS papers with good coverage across:\n- strong recent papers from top venues\n- surveys\u002Freviews if they exist\n- papers with open-source code\n- closely related variants of the topic\n\nFormat as a numbered list with all fields for each paper.',\n  model: 'auto-gemini-3'\n})\n```\n\n**Priority 2 — Gemini CLI fallback** (if MCP unavailable):\n\nIf `mcp__gemini-cli__ask-gemini` fails or is not configured, fall back to CLI:\n\n```bash\ngemini -p 'You are a research literature scout. Search comprehensively for papers on: \"QUERY\"\n...same prompt as above...' 2>\u002Fdev\u002Fnull\n```\n\n- **Timeout**: 120 seconds\n- **Stderr**: Pipe to `\u002Fdev\u002Fnull` — contains hook warnings, not part of the response\n\n**When to use which:**\n- MCP is preferred because it integrates natively with Claude Code's tool system, handles model selection, and avoids shell escaping issues.\n- CLI fallback ensures the skill works even when MCP is not configured or the MCP server process has crashed.\n\n### Step 3: Parse Results\n\nExtract structured paper information from Gemini's response. For each paper, normalize to:\n\n```\n{\n  title, authors, year, venue,\n  arxiv_id,    \u002F\u002F \"N\u002FA\" if not available\n  doi,         \u002F\u002F \"N\u002FA\" if not available\n  code_url,    \u002F\u002F \"No code\" if not available\n  summary      \u002F\u002F one-sentence contribution\n}\n```\n\nIf Gemini returns fewer papers than requested, note this but do not re-query.\n\n### Step 4: Present Results\n\nFormat results as a structured table:\n\n```\n| # | Title | Venue | Year | Code | Summary |\n|---|-------|-------|------|------|---------|\n| 1 | ... | NeurIPS 2024 | 2024 | [GitHub](url) | ... |\n| 2 | ... | IEEE TWC | 2023 | No | ... |\n```\n\nFor each paper, also show:\n- **arXiv ID**: if available (for cross-reference with `\u002Farxiv`)\n- **DOI**: if available (canonical link for published papers)\n- **Code**: GitHub\u002FGitLab link or \"No\"\n\n### Step 5: Offer Follow-up\n\nAfter presenting results, suggest:\n\n```text\n\u002Fsemantic-scholar \"topic\"    — search published venue papers with citation counts\n\u002Farxiv \"arXiv:XXXX.XXXXX\"   — fetch specific preprint details\n\u002Fresearch-lit \"topic\" — sources: gemini, semantic-scholar  — combined multi-source review\n\u002Fnovelty-check \"idea\"       — verify novelty against literature\n```\n\n## Key Rules\n\n- **MCP first, CLI second.** Always try `mcp__gemini-cli__ask-gemini` before falling back to `gemini -p`.\n- **Gemini is a discovery source, not a database.** Its results may include papers it \"knows about\" from training data. Always cross-verify critical details (exact titles, venues, years) via `\u002Fsemantic-scholar` or `\u002Farxiv` when precision matters.\n- **Do not use Gemini for citation counts.** It may hallucinate citation numbers. Use Semantic Scholar for authoritative citation data.\n- **Pipe stderr to `\u002Fdev\u002Fnull` in CLI mode** — Gemini CLI emits hook warnings on stderr.\n- **Timeout generously in CLI mode** — Gemini's thorough search can take 30-60 seconds. Set timeout to 120s.\n- If both MCP and CLI are unreachable, suggest using `\u002Fsemantic-scholar`, `\u002Farxiv`, or `\u002Fresearch-lit \"topic\" — sources: web` as alternatives.\n","# Gemini Literature Search\n\nSearch query: $ARGUMENTS\n\n## Role & Positioning\n\nThis skill uses Gemini as a **broad literature discovery** source:\n\n| Skill | Source | Best for |\n|-------|--------|----------|\n| `\u002Farxiv` | arXiv API | Latest preprints, cutting-edge unrefereed work |\n| `\u002Fsemantic-scholar` | Semantic Scholar API | Published venue papers (IEEE, ACM, Springer) with citation counts |\n| `\u002Fdeepxiv` | DeepXiv CLI | Layered reading: search, brief, section map, section reads |\n| `\u002Fexa-search` | Exa API | Broad web search: blogs, docs, news, companies, research papers |\n| `\u002Fgemini-search` | Gemini MCP \u002F CLI | **AI-powered broad literature discovery** — searches across multiple angles, aliases, and sub-problems |\n\nUse Gemini when you want AI-driven discovery that goes beyond keyword matching — Gemini decomposes topics into sub-problems, explores naming variants, and surfaces papers that traditional API searches may miss.\n\n## Constants\n\n- **MAX_RESULTS = 15** — Target number of papers Gemini should find.\n- **MIN_YEAR = 2022** — Default minimum publication year. Override with `— year: 2020-`.\n- **DEFAULT_MODEL = auto-gemini-3** — Auto-routes within the Gemini 3 family (Pro \u002F Flash) by server-side capacity. Required by `mcp__gemini-cli__ask-gemini` and `gemini-cli` v0.40+; explicit `gemini-3-pro-preview` can be silently downgraded to `gemini-2.5-pro` on OAuth-personal \u002F Google One AI Pro accounts when capacity is exhausted. Override with `— model: gemini-3-flash-preview` (Gemini 3 Flash explicit, faster, higher quota), or `— model: gemini-2.5-pro` \u002F `gemini-2.5-flash` (legacy, only for users on older `gemini-cli` \u003C v0.40). The MCP tool accepts all of these verbatim.\n\n> Overrides (append to arguments):\n> - `\u002Fgemini-search \"topic\" — max: 20` — request up to 20 papers\n> - `\u002Fgemini-search \"topic\" — year: 2020-` — papers from 2020 onward\n> - `\u002Fgemini-search \"topic\" — code-only` — only papers with open-source code\n> - `\u002Fgemini-search \"topic\" — venues: NeurIPS,ICML,ICLR` — focus on specific venues\n> - `\u002Fgemini-search \"topic\" — model: gemini-3-flash-preview` — Gemini 3 Flash (faster, higher quota, less capable than Pro)\n> - `\u002Fgemini-search \"topic\" — model: auto-gemini-3` — auto-routes within the Gemini 3 family by load\n> - `\u002Fgemini-search \"topic\" — model: gemini-2.5-pro` — legacy (only if your `gemini-cli` \u003C v0.40)\n\n## Environment & Setup\n\n### Prerequisites\n\n1. **Node.js** v16.0.0+\n2. **Google Gemini CLI** — installed and authenticated\n   ```bash\n   npm install -g @google\u002Fgemini-cli\n   gemini auth\n   ```\n3. **gemini-mcp-tool** — MCP bridge for Codex CLI ([jamubc\u002Fgemini-mcp-tool](https:\u002F\u002Fgithub.com\u002Fjamubc\u002Fgemini-mcp-tool))\n   ```bash\n   npm install -g gemini-mcp-tool\n   ```\n\n### MCP Configuration\n\nRegister the Gemini bridge in Codex CLI:\n\n```bash\ncodex mcp add gemini-cli -- npx -y gemini-mcp-tool\n```\n\n### Authentication\n\nGemini CLI uses your Google account or an API key. Export the key in your shell or project environment:\n\n```bash\nexport GEMINI_API_KEY=your-key-here\n```\n\n- Free key from [Google AI Studio](https:\u002F\u002Faistudio.google.com\u002Fapikey)\n- Flash model (`gemini-2.5-flash`) has a generous free tier (500 req\u002Fmin)\n\n### Available MCP Tools\n\n| Tool | Parameters | Description |\n|------|-----------|-------------|\n| `mcp__gemini-cli__ask-gemini` | `prompt` (required), `model` (optional), `sandbox` (optional) | Ask Gemini for analysis or research; supports `@file` syntax |\n| `mcp__gemini-cli__sandbox-test` | `prompt` (required), `model` (optional) | Safe code execution in sandbox |\n| `mcp__gemini-cli__ping` | — | Connection test |\n| `mcp__gemini-cli__help` | — | Show Gemini CLI help |\n\n### Verify Setup\n\n```bash\ngemini --version\n```\n\n## Workflow\n\n### Step 1: Parse Arguments\n\nParse `$ARGUMENTS` for:\n- **query**: The research topic (required)\n- **max**: Override MAX_RESULTS\n- **year**: Minimum publication year (e.g., `2020-`)\n- **code-only**: Only include papers with open-source code\n- **venues**: Comma-separated venue filter\n- **model**: Override DEFAULT_MODEL\n\n### Step 2: Execute Search (MCP Priority)\n\n**Priority 1 — Gemini MCP** (preferred):\n\nTry calling `mcp__gemini-cli__ask-gemini` with the search prompt:\n\n```\nmcp__gemini-cli__ask-gemini({\n  prompt: 'You are a research literature scout. Search comprehensively for papers on: \"QUERY\"\n\nIMPORTANT CONSTRAINTS:\n1. Search from MULTIPLE angles — do not just use the exact query. Decompose the topic into sub-problems, aliases, neighboring tasks, and common benchmark\u002Fsettings variants.\n2. Prefer papers that are genuinely relevant, not merely keyword-adjacent.\n3. Include top venues, journals, surveys, recent preprints, and papers with code when available.\n4. Focus on papers from MIN_YEAR onward unless older foundational work is necessary.\n\nFor EACH paper found, provide ALL of the following in this exact format:\n- Title: [exact title]\n- Authors: [full author list]\n- Year: [publication year]\n- Venue: [exact conference\u002Fjournal name + year, or \"arXiv preprint\" if not published]\n- arXiv ID: [format 2401.12345, or \"N\u002FA\"]\n- DOI: [if available, or \"N\u002FA\"]\n- Code URL: [GitHub\u002FGitLab link if available, or \"No code\"]\n- Summary: [one-sentence core contribution]\n\nFind at least MAX_RESULTS papers with good coverage across:\n- strong recent papers from top venues\n- surveys\u002Freviews if they exist\n- papers with open-source code\n- closely related variants of the topic\n\nFormat as a numbered list with all fields for each paper.',\n  model: 'auto-gemini-3'\n})\n```\n\n**Priority 2 — Gemini CLI fallback** (if MCP unavailable):\n\nIf `mcp__gemini-cli__ask-gemini` fails or is not configured, fall back to CLI:\n\n```bash\ngemini -p 'You are a research literature scout. Search comprehensively for papers on: \"QUERY\"\n...same prompt as above...' 2>\u002Fdev\u002Fnull\n```\n\n- **Timeout**: 120 seconds\n- **Stderr**: Pipe to `\u002Fdev\u002Fnull` — contains hook warnings, not part of the response\n\n**When to use which:**\n- MCP is preferred because it integrates natively with Claude Code's tool system, handles model selection, and avoids shell escaping issues.\n- CLI fallback ensures the skill works even when MCP is not configured or the MCP server process has crashed.\n\n### Step 3: Parse Results\n\nExtract structured paper information from Gemini's response. For each paper, normalize to:\n\n```\n{\n  title, authors, year, venue,\n  arxiv_id,    \u002F\u002F \"N\u002FA\" if not available\n  doi,         \u002F\u002F \"N\u002FA\" if not available\n  code_url,    \u002F\u002F \"No code\" if not available\n  summary      \u002F\u002F one-sentence contribution\n}\n```\n\nIf Gemini returns fewer papers than requested, note this but do not re-query.\n\n### Step 4: Present Results\n\nFormat results as a structured table:\n\n```\n| # | Title | Venue | Year | Code | Summary |\n|---|-------|-------|------|------|---------|\n| 1 | ... | NeurIPS 2024 | 2024 | [GitHub](url) | ... |\n| 2 | ... | IEEE TWC | 2023 | No | ... |\n```\n\nFor each paper, also show:\n- **arXiv ID**: if available (for cross-reference with `\u002Farxiv`)\n- **DOI**: if available (canonical link for published papers)\n- **Code**: GitHub\u002FGitLab link or \"No\"\n\n### Step 5: Offer Follow-up\n\nAfter presenting results, suggest:\n\n```text\n\u002Fsemantic-scholar \"topic\"    — search published venue papers with citation counts\n\u002Farxiv \"arXiv:XXXX.XXXXX\"   — fetch specific preprint details\n\u002Fresearch-lit \"topic\" — sources: gemini, semantic-scholar  — combined multi-source review\n\u002Fnovelty-check \"idea\"       — verify novelty against literature\n```\n\n## Key Rules\n\n- **MCP first, CLI second.** Always try `mcp__gemini-cli__ask-gemini` before falling back to `gemini -p`.\n- **Gemini is a discovery source, not a database.** Its results may include papers it \"knows about\" from training data. Always cross-verify critical details (exact titles, venues, years) via `\u002Fsemantic-scholar` or `\u002Farxiv` when precision matters.\n- **Do not use Gemini for citation counts.** It may hallucinate citation numbers. Use Semantic Scholar for authoritative citation data.\n- **Pipe stderr to `\u002Fdev\u002Fnull` in CLI mode** — Gemini CLI emits hook warnings on stderr.\n- **Timeout generously in CLI mode** — Gemini's thorough search can take 30-60 seconds. Set timeout to 120s.\n- If both MCP and CLI are unreachable, suggest using `\u002Fsemantic-scholar`, `\u002Farxiv`, or `\u002Fresearch-lit \"topic\" — sources: web` as alternatives.\n",{"name":5,"description":7,"allowed-tools":24,"argument-hint":25},"Bash(*), Read, Write, mcp__gemini-cli__*","[search-query]","main","18193d71ea3441d7c033dbf195b8a7c75ac96f75","packages\u002Fskill\u002Fskill-science\u002Fassets\u002Fsources\u002Faris\u002Fskills\u002Fskills-codex\u002Fgemini-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 gemini-search",{"tool":40,"command":41},"bunx","bunx skills add CZX-LBJ\u002Fdeepseek-science --skill gemini-search",{"tool":43,"command":44},"pnpm","pnpm dlx skills add CZX-LBJ\u002Fdeepseek-science --skill gemini-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\u002Fskills-codex\u002Fgemini-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",[],[]]