[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M74MV68PXPA8MH4S3C0TT6QZ":3,"skill-same:01M74MV68PXPA8MH4S3C0TT6QZ":59},{"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":24,"commitSha":25,"skillDirectory":26,"forksCount":27,"repositoryHtmlUrl":28,"repositoryHomepageUrl":29,"ownerHtmlUrl":30,"ownerBlogUrl":6,"ownerDescription":31,"updatedAt":32,"install":33,"resources":46},"01M74MV68PXPA8MH4S3C0TT6QZ","ncbi-sequence-fetch",null,"Retrieve protein and nucleotide sequences from NCBI databases using E-utilities. Supports direct accession lookup, CDS translation, gene+organism search, locus lookup, PubMed-linked sequences, patent protein extraction, and organism+length fallback search. Use when you need to fetch biological sequences by accession, gene name, locus tag, PubMed ID, or patent number.","pengqianhan\u002FAI-Human-Research-OS","pengqianhan","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F4286531?v=4","01M74M3DT9HNZ6HPAK8TX69EX9","PengqianHan","01M74M3DTVSN2GXW0JH2W396FK",3,"MIT","https:\u002F\u002Fgithub.com\u002Fpengqianhan\u002FAI-Human-Research-OS\u002Fblob\u002Fmain\u002Fresearch-skills-hub\u002Fscience-skills\u002Fncbi_sequence_fetch\u002FSKILL.md",[],[],"2026-11-11 15:11:14",false,"---\nname: ncbi-sequence-fetch\ndescription: >\n  Retrieve protein and nucleotide sequences from NCBI databases using\n  E-utilities. Supports direct accession lookup, CDS translation, gene+organism\n  search, locus lookup, PubMed-linked sequences, patent protein extraction, and\n  organism+length fallback search. Use when you need to fetch biological\n  sequences by accession, gene name, locus tag, PubMed ID, or patent number.\n---\n\n# NCBI Sequence Fetch\n\n## Prerequisites\n\n1.  **`uv`**: Read the `uv` skill and follow its Setup instructions to ensure\n    `uv` is installed and on PATH.\n2.  **User Notification**: If .licenses\u002Fncbi_sequence_fetch_LICENSE.txt does not\n    already exist in the workspace root directory then (1) prominently notify\n    the user to check the terms at https:\u002F\u002Fwww.ncbi.nlm.nih.gov\u002F and\n    https:\u002F\u002Fwww.ncbi.nlm.nih.gov\u002Fhome\u002Fabout\u002Fpolicies\u002F, then (2) create the file\n    recording the notification text and timestamp.\n3.  **`.env` file**: Make sure the `.env` file exists in your home directory.\n    Create one if it does not exist.\n4.  **`NCBI_API_KEY`** (optional): Raises the NCBI rate limit from 3 to 10\n    requests\u002Fsecond. The skill works without it, but a key is recommended if the\n    user plans many queries or encounters a 429 error. You can register for a\n    key for free at https:\u002F\u002Fwww.ncbi.nlm.nih.gov\u002Faccount\u002Fsettings\u002F. You **MUST**\n    use the safe credentials protocol in the `credentials` skill to check for\n    and request this key if this skill looks relevant to the user's request.\n\n## Core Rules\n\n-   **Use the Wrapper**: ALWAYS execute the provided helper scripts to query the\n    database rather than accessing the database directly. The scripts\n    automatically enforce the required rate limit gracefully.\n-   **API Key Support**: If the user provides an `NCBI_API_KEY` in their\n    environment, the query speed limits are automatically increased\n    significantly.\n-   **Notification**: If this skill is used, ensure this is mentioned in the\n    output.\n\n## Overview\n\nWraps NCBI's Entrez E-utilities (efetch, esearch, elink, esummary) for\nretrieving protein and nucleotide sequences. Provides 10 subcommands covering\nthe full range of sequence retrieval workflows:\n\n-   `fetch-protein` — Direct protein accession lookup (GenPept, RefSeq)\n-   `fetch-nucleotide` — Direct nucleotide accession lookup\n-   `cds-translate` — Fetch CDS and translate to protein (3 methods)\n-   `search` — Free-text search of any NCBI database\n-   `elink` — Follow cross-database links (PubMed→Protein, etc.)\n-   `gene-protein` — Search protein by gene name + organism\n-   `locus-protein` — Search protein by locus tag + organism\n-   `pubmed-proteins` — Find proteins linked to a PubMed article\n-   `patent-search` — Extract protein sequences from patents\n-   `organism-length` — Last-resort search by organism + exact AA length\n\n## Utility Scripts\n\n**`scripts\u002Fncbi_fetch.py`** — Single script with subcommands.\n\nAll subcommands write structured JSON output. Use `--output FILE` to save to a\nfile, or omit it to print to stdout. A human-readable summary is always printed\nto stdout.\n\n### 1. Fetch Protein by Accession\n\nFetches protein FASTA from NCBI by accession (XP_, NP_, GenPept, etc.)\n\n```bash\nuv run scripts\u002Fncbi_fetch.py fetch-protein XP_022033624 -o \u002Ftmp\u002Fresult.json\nuv run scripts\u002Fncbi_fetch.py fetch-protein NP_001234567 ABC12345.1\n```\n\n### 2. Fetch Nucleotide by Accession\n\nFetches nucleotide FASTA from NCBI by accession.\n\n```bash\nuv run scripts\u002Fncbi_fetch.py fetch-nucleotide MK034466 -o \u002Ftmp\u002Fresult.json\n```\n\n### 3. CDS Translate\n\nFetches a CDS\u002Fnucleotide accession and translates to protein sequence. Tries\nthree approaches in order: 1. NCBI's pre-translated CDS protein (`fasta_cds_aa`)\n\n2. GenBank XML CDS annotation translations 3. Raw nucleotide → 6-frame ORF\nfinding\n\n```bash\nuv run scripts\u002Fncbi_fetch.py cds-translate MK034466 -o \u002Ftmp\u002Fresult.json\nuv run scripts\u002Fncbi_fetch.py cds-translate HQ662330 --target-length 1043\n```\n\nIf the accession is a **genomic record** (not mRNA\u002FCDS), the tool will report\n`is_genomic: true` so you can fall back to a homology-based approach instead.\n\n### 4. Search Any Database\n\nFree-text search using Entrez query syntax. Supports all NCBI databases.\n\n```bash\n# Search protein database\nuv run scripts\u002Fncbi_fetch.py search \"WRR4B[Gene Name] AND Arabidopsis[Organism]\" \\\n  --database protein --retmax 5 --fetch-sequences\n\n# Search nucleotide database\nuv run scripts\u002Fncbi_fetch.py search \"Rz2[Gene Name] AND Beta vulgaris[Organism]\" \\\n  --database nuccore --retmax 10\n\n# Search with patent filter\nuv run scripts\u002Fncbi_fetch.py search \"disease resistance AND Solanum[Organism] AND patent[Properties]\" \\\n  --database protein --fetch-sequences\n\n# Search by sequence length\nuv run scripts\u002Fncbi_fetch.py search '\"Oryza sativa\"[Organism] AND 1043[SLEN]' \\\n  --database protein --fetch-sequences --retmax 50\n```\n\n### 5. Cross-Database Links (elink)\n\nFollow NCBI's cross-database links (e.g., PubMed article → linked proteins).\n\n```bash\nuv run scripts\u002Fncbi_fetch.py elink 24896089 --dbfrom pubmed --db protein \\\n  --fetch-sequences -o \u002Ftmp\u002Flinked.json\n```\n\n### 6. Gene + Organism Search\n\nSearches for protein sequences by gene name and organism. Searches NCBI Protein\nwith `[Gene Name]` and `[Organism]` qualifiers.\n\n```bash\nuv run scripts\u002Fncbi_fetch.py gene-protein WRR4B --organism \"Arabidopsis thaliana\"\nuv run scripts\u002Fncbi_fetch.py gene-protein Pikh-2 --organism \"Oryza sativa\" \\\n  --target-length 1043 -o \u002Ftmp\u002Fresult.json\n```\n\n### 7. Locus Tag Search\n\nSearches by locus tag in both NCBI Protein and Nuccore databases. Extracts CDS\ntranslations from GenBank XML when direct protein hits aren't available.\n\n```bash\nuv run scripts\u002Fncbi_fetch.py locus-protein At1g56540 --organism \"Arabidopsis thaliana\"\nuv run scripts\u002Fncbi_fetch.py locus-protein Niben101Scf02422g02015.1 \\\n  --organism \"Nicotiana benthamiana\" -o \u002Ftmp\u002Fresult.json\n```\n\n### 8. PubMed-Linked Proteins\n\nFinds protein sequences linked to a PubMed article. Searches NCBI Protein by\nPMID, follows elink PubMed→Protein, and extracts CDS translations from linked\nNuccore records.\n\n```bash\nuv run scripts\u002Fncbi_fetch.py pubmed-proteins 30692254 --identifier WRR4B\nuv run scripts\u002Fncbi_fetch.py pubmed-proteins 24896089 --identifier \"K2\" \\\n  -o \u002Ftmp\u002Fresult.json\n```\n\n### 9. Patent Sequence Search\n\nTwo modes:\n\n**By patent number** — fetches all protein sequences from a specific patent:\n`bash uv run scripts\u002Fncbi_fetch.py patent-search --patent-number US10123456 -o\n\u002Ftmp\u002Fpatent.json`\n\n**By keywords** — searches NCBI Protein with `patent[Properties]` filter: `bash\nuv run scripts\u002Fncbi_fetch.py patent-search --keywords WRR4B Albugo --organism\n\"Arabidopsis thaliana\" -o \u002Ftmp\u002Fpatent.json`\n\n> [!IMPORTANT] **Patent convention**: In molecular biology patents, SEQ ID NO: 1\n> is typically the DNA sequence and SEQ ID NO: 2 is the primary protein. Higher\n> SEQ ID NOs are variants or related sequences. Prefer Sequence 2 when selecting\n> the primary protein of interest.\n\n### 10. Organism + Length Search\n\nLast-resort search when only organism and expected protein length are known.\nUses NCBI's `[SLEN]` filter for exact length matching.\n\n```bash\nuv run scripts\u002Fncbi_fetch.py organism-length \\\n  --organism \"Arabidopsis thaliana\" --length 1048 --retmax 50 \\\n  -o \u002Ftmp\u002Fresult.json\n```\n\n> [!NOTE] This often returns multiple candidates. Use the JSON output headers to\n> identify the correct protein.\n\n## Workflow\n\n### Standard Sequence Retrieval Cascade\n\nWhen trying to find a protein sequence, follow this priority order:\n\n1.  **Direct accession** — `fetch-protein` with GenPept\u002FRefSeq accession\n2.  **CDS translation** — `cds-translate` with nucleotide\u002FCDS accession\n3.  **PubMed-linked** — `pubmed-proteins` with PMID + gene name\n4.  **Locus lookup** — `locus-protein` with locus tag + organism\n5.  **Gene + organism** — `gene-protein` with gene name + organism\n6.  **Patent search** — `patent-search` with patent number or keywords\n7.  **Organism + length** — `organism-length` as last resort\n\n### Interpreting Results\n\n-   All subcommands return JSON with a `results` array\n-   Each result has `sequence` (AA string), `length`, and `header`\u002Fmetadata\n-   When multiple results are returned, select by:\n    -   Closest match to expected length (`target_length`)\n    -   Header relevance (matching gene name, \"disease resistance\" keywords)\n    -   Source priority (RefSeq > GenPept > patent)\n\n## Reference\n\n-   **NCBI E-utilities docs**: https:\u002F\u002Fwww.ncbi.nlm.nih.gov\u002Fbooks\u002FNBK25499\u002F\n-   **Entrez search syntax**: https:\u002F\u002Fwww.ncbi.nlm.nih.gov\u002Fbooks\u002FNBK49540\u002F\n-   **Database list**: protein, nuccore, gene, pubmed, pmc, biosample, etc.\n-   **Common accession formats**:\n    -   `XP_` \u002F `NP_` — NCBI RefSeq protein\n    -   `AAA` to `AZZ` + digits — GenPept (translated GenBank)\n    -   `MK`, `MN`, `HQ`, etc. + digits — GenBank nucleotide\n    -   `ENSG`, `ENST`, `ENSP` — Ensembl (use `ensembl-database` skill instead)\n    -   `Q`, `P`, `O` + digits — UniProt (use `uniprot-database` skill instead)\n","# NCBI Sequence Fetch\n\n## Prerequisites\n\n1.  **`uv`**: Read the `uv` skill and follow its Setup instructions to ensure\n    `uv` is installed and on PATH.\n2.  **User Notification**: If .licenses\u002Fncbi_sequence_fetch_LICENSE.txt does not\n    already exist in the workspace root directory then (1) prominently notify\n    the user to check the terms at https:\u002F\u002Fwww.ncbi.nlm.nih.gov\u002F and\n    https:\u002F\u002Fwww.ncbi.nlm.nih.gov\u002Fhome\u002Fabout\u002Fpolicies\u002F, then (2) create the file\n    recording the notification text and timestamp.\n3.  **`.env` file**: Make sure the `.env` file exists in your home directory.\n    Create one if it does not exist.\n4.  **`NCBI_API_KEY`** (optional): Raises the NCBI rate limit from 3 to 10\n    requests\u002Fsecond. The skill works without it, but a key is recommended if the\n    user plans many queries or encounters a 429 error. You can register for a\n    key for free at https:\u002F\u002Fwww.ncbi.nlm.nih.gov\u002Faccount\u002Fsettings\u002F. You **MUST**\n    use the safe credentials protocol in the `credentials` skill to check for\n    and request this key if this skill looks relevant to the user's request.\n\n## Core Rules\n\n-   **Use the Wrapper**: ALWAYS execute the provided helper scripts to query the\n    database rather than accessing the database directly. The scripts\n    automatically enforce the required rate limit gracefully.\n-   **API Key Support**: If the user provides an `NCBI_API_KEY` in their\n    environment, the query speed limits are automatically increased\n    significantly.\n-   **Notification**: If this skill is used, ensure this is mentioned in the\n    output.\n\n## Overview\n\nWraps NCBI's Entrez E-utilities (efetch, esearch, elink, esummary) for\nretrieving protein and nucleotide sequences. Provides 10 subcommands covering\nthe full range of sequence retrieval workflows:\n\n-   `fetch-protein` — Direct protein accession lookup (GenPept, RefSeq)\n-   `fetch-nucleotide` — Direct nucleotide accession lookup\n-   `cds-translate` — Fetch CDS and translate to protein (3 methods)\n-   `search` — Free-text search of any NCBI database\n-   `elink` — Follow cross-database links (PubMed→Protein, etc.)\n-   `gene-protein` — Search protein by gene name + organism\n-   `locus-protein` — Search protein by locus tag + organism\n-   `pubmed-proteins` — Find proteins linked to a PubMed article\n-   `patent-search` — Extract protein sequences from patents\n-   `organism-length` — Last-resort search by organism + exact AA length\n\n## Utility Scripts\n\n**`scripts\u002Fncbi_fetch.py`** — Single script with subcommands.\n\nAll subcommands write structured JSON output. Use `--output FILE` to save to a\nfile, or omit it to print to stdout. A human-readable summary is always printed\nto stdout.\n\n### 1. Fetch Protein by Accession\n\nFetches protein FASTA from NCBI by accession (XP_, NP_, GenPept, etc.)\n\n```bash\nuv run scripts\u002Fncbi_fetch.py fetch-protein XP_022033624 -o \u002Ftmp\u002Fresult.json\nuv run scripts\u002Fncbi_fetch.py fetch-protein NP_001234567 ABC12345.1\n```\n\n### 2. Fetch Nucleotide by Accession\n\nFetches nucleotide FASTA from NCBI by accession.\n\n```bash\nuv run scripts\u002Fncbi_fetch.py fetch-nucleotide MK034466 -o \u002Ftmp\u002Fresult.json\n```\n\n### 3. CDS Translate\n\nFetches a CDS\u002Fnucleotide accession and translates to protein sequence. Tries\nthree approaches in order: 1. NCBI's pre-translated CDS protein (`fasta_cds_aa`)\n\n2. GenBank XML CDS annotation translations 3. Raw nucleotide → 6-frame ORF\nfinding\n\n```bash\nuv run scripts\u002Fncbi_fetch.py cds-translate MK034466 -o \u002Ftmp\u002Fresult.json\nuv run scripts\u002Fncbi_fetch.py cds-translate HQ662330 --target-length 1043\n```\n\nIf the accession is a **genomic record** (not mRNA\u002FCDS), the tool will report\n`is_genomic: true` so you can fall back to a homology-based approach instead.\n\n### 4. Search Any Database\n\nFree-text search using Entrez query syntax. Supports all NCBI databases.\n\n```bash\n# Search protein database\nuv run scripts\u002Fncbi_fetch.py search \"WRR4B[Gene Name] AND Arabidopsis[Organism]\" \\\n  --database protein --retmax 5 --fetch-sequences\n\n# Search nucleotide database\nuv run scripts\u002Fncbi_fetch.py search \"Rz2[Gene Name] AND Beta vulgaris[Organism]\" \\\n  --database nuccore --retmax 10\n\n# Search with patent filter\nuv run scripts\u002Fncbi_fetch.py search \"disease resistance AND Solanum[Organism] AND patent[Properties]\" \\\n  --database protein --fetch-sequences\n\n# Search by sequence length\nuv run scripts\u002Fncbi_fetch.py search '\"Oryza sativa\"[Organism] AND 1043[SLEN]' \\\n  --database protein --fetch-sequences --retmax 50\n```\n\n### 5. Cross-Database Links (elink)\n\nFollow NCBI's cross-database links (e.g., PubMed article → linked proteins).\n\n```bash\nuv run scripts\u002Fncbi_fetch.py elink 24896089 --dbfrom pubmed --db protein \\\n  --fetch-sequences -o \u002Ftmp\u002Flinked.json\n```\n\n### 6. Gene + Organism Search\n\nSearches for protein sequences by gene name and organism. Searches NCBI Protein\nwith `[Gene Name]` and `[Organism]` qualifiers.\n\n```bash\nuv run scripts\u002Fncbi_fetch.py gene-protein WRR4B --organism \"Arabidopsis thaliana\"\nuv run scripts\u002Fncbi_fetch.py gene-protein Pikh-2 --organism \"Oryza sativa\" \\\n  --target-length 1043 -o \u002Ftmp\u002Fresult.json\n```\n\n### 7. Locus Tag Search\n\nSearches by locus tag in both NCBI Protein and Nuccore databases. Extracts CDS\ntranslations from GenBank XML when direct protein hits aren't available.\n\n```bash\nuv run scripts\u002Fncbi_fetch.py locus-protein At1g56540 --organism \"Arabidopsis thaliana\"\nuv run scripts\u002Fncbi_fetch.py locus-protein Niben101Scf02422g02015.1 \\\n  --organism \"Nicotiana benthamiana\" -o \u002Ftmp\u002Fresult.json\n```\n\n### 8. PubMed-Linked Proteins\n\nFinds protein sequences linked to a PubMed article. Searches NCBI Protein by\nPMID, follows elink PubMed→Protein, and extracts CDS translations from linked\nNuccore records.\n\n```bash\nuv run scripts\u002Fncbi_fetch.py pubmed-proteins 30692254 --identifier WRR4B\nuv run scripts\u002Fncbi_fetch.py pubmed-proteins 24896089 --identifier \"K2\" \\\n  -o \u002Ftmp\u002Fresult.json\n```\n\n### 9. Patent Sequence Search\n\nTwo modes:\n\n**By patent number** — fetches all protein sequences from a specific patent:\n`bash uv run scripts\u002Fncbi_fetch.py patent-search --patent-number US10123456 -o\n\u002Ftmp\u002Fpatent.json`\n\n**By keywords** — searches NCBI Protein with `patent[Properties]` filter: `bash\nuv run scripts\u002Fncbi_fetch.py patent-search --keywords WRR4B Albugo --organism\n\"Arabidopsis thaliana\" -o \u002Ftmp\u002Fpatent.json`\n\n> [!IMPORTANT] **Patent convention**: In molecular biology patents, SEQ ID NO: 1\n> is typically the DNA sequence and SEQ ID NO: 2 is the primary protein. Higher\n> SEQ ID NOs are variants or related sequences. Prefer Sequence 2 when selecting\n> the primary protein of interest.\n\n### 10. Organism + Length Search\n\nLast-resort search when only organism and expected protein length are known.\nUses NCBI's `[SLEN]` filter for exact length matching.\n\n```bash\nuv run scripts\u002Fncbi_fetch.py organism-length \\\n  --organism \"Arabidopsis thaliana\" --length 1048 --retmax 50 \\\n  -o \u002Ftmp\u002Fresult.json\n```\n\n> [!NOTE] This often returns multiple candidates. Use the JSON output headers to\n> identify the correct protein.\n\n## Workflow\n\n### Standard Sequence Retrieval Cascade\n\nWhen trying to find a protein sequence, follow this priority order:\n\n1.  **Direct accession** — `fetch-protein` with GenPept\u002FRefSeq accession\n2.  **CDS translation** — `cds-translate` with nucleotide\u002FCDS accession\n3.  **PubMed-linked** — `pubmed-proteins` with PMID + gene name\n4.  **Locus lookup** — `locus-protein` with locus tag + organism\n5.  **Gene + organism** — `gene-protein` with gene name + organism\n6.  **Patent search** — `patent-search` with patent number or keywords\n7.  **Organism + length** — `organism-length` as last resort\n\n### Interpreting Results\n\n-   All subcommands return JSON with a `results` array\n-   Each result has `sequence` (AA string), `length`, and `header`\u002Fmetadata\n-   When multiple results are returned, select by:\n    -   Closest match to expected length (`target_length`)\n    -   Header relevance (matching gene name, \"disease resistance\" keywords)\n    -   Source priority (RefSeq > GenPept > patent)\n\n## Reference\n\n-   **NCBI E-utilities docs**: https:\u002F\u002Fwww.ncbi.nlm.nih.gov\u002Fbooks\u002FNBK25499\u002F\n-   **Entrez search syntax**: https:\u002F\u002Fwww.ncbi.nlm.nih.gov\u002Fbooks\u002FNBK49540\u002F\n-   **Database list**: protein, nuccore, gene, pubmed, pmc, biosample, etc.\n-   **Common accession formats**:\n    -   `XP_` \u002F `NP_` — NCBI RefSeq protein\n    -   `AAA` to `AZZ` + digits — GenPept (translated GenBank)\n    -   `MK`, `MN`, `HQ`, etc. + digits — GenBank nucleotide\n    -   `ENSG`, `ENST`, `ENSP` — Ensembl (use `ensembl-database` skill instead)\n    -   `Q`, `P`, `O` + digits — UniProt (use `uniprot-database` skill instead)\n",{"name":5,"description":7},"main","e71245365df78e06cd166602744bf2491f79910e","research-skills-hub\u002Fscience-skills\u002Fncbi_sequence_fetch",0,"https:\u002F\u002Fgithub.com\u002Fpengqianhan\u002FAI-Human-Research-OS","https:\u002F\u002Fpengqianhan.github.io\u002FAI-Human-Research-OS\u002F","https:\u002F\u002Fgithub.com\u002Fpengqianhan","Ph.D. candidate of The University of Auckland, New Zealand","2026-11-14 18:08:16",{"source":8,"skillName":5,"commands":34,"prompt":44,"zipAvailable":45},[35,38,41],{"tool":36,"command":37},"npx","npx skills add pengqianhan\u002FAI-Human-Research-OS --skill ncbi-sequence-fetch",{"tool":39,"command":40},"bunx","bunx skills add pengqianhan\u002FAI-Human-Research-OS --skill ncbi-sequence-fetch",{"tool":42,"command":43},"pnpm","pnpm dlx skills add pengqianhan\u002FAI-Human-Research-OS --skill ncbi-sequence-fetch","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fpengqianhan\u002FAI-Human-Research-OS\u002Fblob\u002Fmain\u002Fresearch-skills-hub\u002Fscience-skills\u002Fncbi_sequence_fetch\u002FSKILL.md",true,[47,53],{"path":48,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":51,"sourceHtmlUrl":52},"references\u002Fcitation.bib","REFERENCE","参考文档",1809,"https:\u002F\u002Fgithub.com\u002Fpengqianhan\u002FAI-Human-Research-OS\u002Fblob\u002Fmain\u002Fresearch-skills-hub\u002Fscience-skills\u002Fncbi_sequence_fetch\u002Freferences\u002Fcitation.bib",{"path":54,"resourceType":55,"resourceTypeDesc":56,"sizeBytes":57,"sourceHtmlUrl":58},"scripts\u002Fncbi_fetch.py","SCRIPT","脚本",35657,"https:\u002F\u002Fgithub.com\u002Fpengqianhan\u002FAI-Human-Research-OS\u002Fblob\u002Fmain\u002Fresearch-skills-hub\u002Fscience-skills\u002Fncbi_sequence_fetch\u002Fscripts\u002Fncbi_fetch.py",[60,67,74,81,88,95],{"skillNo":61,"name":62,"nameZh":6,"description":63,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":64,"categories":65,"keywords":66,"publishedAt":19},"01M74MWYTHT498SVMN823896T7","workflow-skill-creator","Distills a completed user workflow or interaction into a reusable agent skill. Use when the user asks to turn their workflow, interaction, or multi-step process into a skill, or when they say \"make this a skill\", \"create a skill from what we just did\", \"package this workflow\" or similar. Do not use for creating skills from scratch without an existing workflow (use a generic skill-creator for that).","https:\u002F\u002Fgithub.com\u002Fpengqianhan\u002FAI-Human-Research-OS\u002Fblob\u002Fmain\u002Fresearch-skills-hub\u002Fscience-skills\u002Fworkflow_skill_creator\u002FSKILL.md",[],[],{"skillNo":68,"name":69,"nameZh":6,"description":70,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":71,"categories":72,"keywords":73,"publishedAt":19},"01M74MWWVCFZ8HQS8840F1V1FT","uv","Checks whether the uv Python package manager is installed and installs it if missing. Ensures uv is on PATH. Use when another skill requires uv as a prerequisite.","https:\u002F\u002Fgithub.com\u002Fpengqianhan\u002FAI-Human-Research-OS\u002Fblob\u002Fmain\u002Fresearch-skills-hub\u002Fscience-skills\u002Fuv\u002FSKILL.md",[],[],{"skillNo":75,"name":76,"nameZh":6,"description":77,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":78,"categories":79,"keywords":80,"publishedAt":19},"01M74MWRH5BTSWZ2C5PCTD5FV9","uniprot-database","Access protein metadata, function, taxonomy, and sequences across UniProtKB, UniParc, and UniRef. Use when searching for proteins, mapping identifiers, or retrieving functional annotations and publications. Don't use for sequence alignment, protein folding, or sequence similarity search (use specialized skills for those tasks).","https:\u002F\u002Fgithub.com\u002Fpengqianhan\u002FAI-Human-Research-OS\u002Fblob\u002Fmain\u002Fresearch-skills-hub\u002Fscience-skills\u002Funiprot_database\u002FSKILL.md",[],[],{"skillNo":82,"name":83,"nameZh":6,"description":84,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":85,"categories":86,"keywords":87,"publishedAt":19},"01M74MWN1D3ER9F1FZPWH8HQC1","unibind-database","Queries the UniBind database for experimentally validated transcription factor (TF) binding sites. Use when retrieving direct TF-DNA interaction datasets, downloading binding site coordinates (BED\u002FFASTA) for local analysis, or listing available datasets by species, cell line, or TF name. Don't use to query specific intervals, locations, genes, motif models or expression data.","https:\u002F\u002Fgithub.com\u002Fpengqianhan\u002FAI-Human-Research-OS\u002Fblob\u002Fmain\u002Fresearch-skills-hub\u002Fscience-skills\u002Funibind_database\u002FSKILL.md",[],[],{"skillNo":89,"name":90,"nameZh":6,"description":91,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":92,"categories":93,"keywords":94,"publishedAt":19},"01M74MWHHB5QZY3NR2FYA1EK4N","ucsc-conservation-and-tfbs","Fetch Evolutionary Conservation scores (phyloP, phastCons) and Transcription Factor Binding Sites (TFBS) from the UCSC Genome Browser. Use when analyzing whether genomic variants or regions are evolutionarily conserved, functionally important, or bounded by TF regulators across major projects (ENCODE, JASPAR, ReMap).","https:\u002F\u002Fgithub.com\u002Fpengqianhan\u002FAI-Human-Research-OS\u002Fblob\u002Fmain\u002Fresearch-skills-hub\u002Fscience-skills\u002Fucsc_conservation_and_tfbs\u002FSKILL.md",[],[],{"skillNo":96,"name":97,"nameZh":6,"description":98,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":99,"categories":100,"keywords":101,"publishedAt":19},"01M74MWERYHSY87P21FDMVE6BA","string-database","Query the STRING database for protein-protein interactions (PPIs), functional enrichment, and homology. Use when the user asks about interactions between specific proteins, interaction evidence, confidence scores, protein interaction partners, or pathway enrichments.","https:\u002F\u002Fgithub.com\u002Fpengqianhan\u002FAI-Human-Research-OS\u002Fblob\u002Fmain\u002Fresearch-skills-hub\u002Fscience-skills\u002Fstring_database\u002FSKILL.md",[],[]]