[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M74MBCR9S35BJYJDJN2XD2DH":3,"skill-same:01M74MBCR9S35BJYJDJN2XD2DH":82},{"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":30,"ownerHtmlUrl":31,"ownerBlogUrl":6,"ownerDescription":32,"updatedAt":33,"install":34,"resources":47},"01M74MBCR9S35BJYJDJN2XD2DH","indication-dossier",null,"Generate a therapeutic indication dossier. Covers the patient population, epidemiology, disease biology, standard of care, regulatory precedent, and landmark clinical trials.","pengqianhan\u002FAI-Human-Research-OS","pengqianhan","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F4286531?v=4","01M74M3DT9HNZ6HPAK8TX69EX9","PengqianHan","01M74M3DTVSN2GXW0JH2W396FK",3,"Apache-2.0","https:\u002F\u002Fgithub.com\u002Fpengqianhan\u002FAI-Human-Research-OS\u002Fblob\u002Fmain\u002Fresearch-skills-hub\u002Fclaude-science-skills\u002Fskills\u002Findication-dossier\u002FSKILL.md",[],[],"2026-11-11 15:11:14",false,"---\nname: indication-dossier\ndescription: >\n  Generate a therapeutic indication dossier. Covers the patient population,\n  epidemiology, disease biology, standard of care, regulatory precedent, and\n  landmark clinical trials.\nlicense: Apache-2.0\n---\n\n# Indication Dossier\n\nProduces a structured research dossier on a single indication, framed as a\npatient population: who they are, what's wrong, how they're treated today,\nand how clinical trials can be designed to help them. Runs as five phases\nthat write resumable waypoint files; after a brief identity check at the end\nof Phase 1, the remaining phases run straight through.\n\n## Framing\n\n**Think of an indication as a patient population.** Frame everything\nfrom the patient perspective: \"Who are these patients?\" not \"What is this\ndisease?\"; \"How are these patients identified and managed?\" not \"What causes\nthis condition?\"; population nesting: \"all patients in {child} are patients\nin {parent}\".\n\nSome indications don't map to ICD codes or standard disease definitions:\n\"immunosenescence\" is a biological state, not a billable diagnosis; \"ageing\"\nis not an FDA-accepted indication; \"GLP-1 induced sarcopenia\" is an\niatrogenic population. Note these distinctions explicitly. They matter for\nregulatory path and trial design.\n\n## Inputs\n\n- **`indication`** (required) — indication name (e.g., \"sarcopenia\",\n  \"idiopathic pulmonary fibrosis\").\n- **`additional_context`** (optional) — areas to focus on, parent\n  indication, or other framing.\n- **`workdir`** (optional) — where to write waypoints and the final report.\n  Defaults to `.\u002Fdo_not_commit\u002Findication-dossier-\u003Cslug>\u002F`.\n\n## Tools this skill expects\n\n| Purpose | Tool |\n|---|---|\n| ClinicalTrials.gov | `clinical-trials` MCP |\n| Literature | `pubmed` MCP |\n| Web | `WebSearch`, `WebFetch` — FDA guidance, treatment guidelines (NCCN, AASLD, specialty societies), CDC\u002FWHO epidemiology data |\n| Documents | `WebFetch` for remote PDFs; `Read` for local PDFs |\n| Subagents | `Agent` for parallel evidence gathering |\n\nIf a listed MCP isn't connected, say so and fall back to `WebSearch` against\nthe underlying public source (clinicaltrials.gov, pubmed.ncbi.nlm.nih.gov).\n\n## Output layout\n\n```\n\u003Cworkdir>\u002F\n└── waypoints\u002F\n    ├── progress.json                 # loop control\n    ├── meta.json                     # phase 1\n    ├── epidemiology.json             # phase 2\n    ├── biology_soc.json              # phase 3\n    ├── regulatory_trials.json        # phase 4\n    ├── sources_evaluated.json\n    ├── research_output.json          # phase 5 — structured output\n    └── indication_dossier_report.md  # phase 5 — the deliverable\n```\n\nSchemas for every waypoint file are in `references\u002Fwaypoint-schemas.md`.\nWaypoints are the resumable state. If the workdir already has waypoints, read\nthem, summarize what's done, and ask which phase to resume from.\n\n## Before starting\n\nRead `references\u002F00-research-standards.md`. It governs sourcing and the\nanti-fabrication rules for every phase. Then create `\u003Cworkdir>\u002Fwaypoints\u002F`.\n\n## Workflow\n\nThe dossier is built in five phases. After each phase, write the waypoint\nfile and emit a ≤200-word summary of what you found and what's uncertain,\nthen proceed directly to the next phase. The one exception is Phase 1: after\nwriting `meta.json`, show the resolved indication identity and call\n`ask_user` with options **Proceed** \u002F **Revise identity** \u002F **Stop**, so a\nmisread indication name can be caught before the expensive phases run. If\n`ask_user` is unavailable, state \"proceeding on this interpretation;\ninterrupt now to correct it\" and continue.\n\n### Phase 1 — Meta initialization\n\nRead `references\u002F01-meta-initialization.md`. Resolve the indication identity:\nclinical definition, ICD codes, aliases, parent indication, and whether it's\na recognized diagnostic entity. Run a quick CT.gov landscape scan. Stand up\n`waypoints\u002Fmeta.json`.\n\n### Phase 2 — Epidemiology research\n\nRead `references\u002F02-epidemiology-research.md`. Characterize the population:\ndiagnostic criteria, prevalence and incidence, demographics and risk factors,\nnatural history. Use parallel subagents to search PubMed and the web\nsimultaneously. Write `waypoints\u002Fepidemiology.json`.\n\n### Phase 3 — Biology & standard-of-care research\n\nRead `references\u002F03-biology-soc-research.md`. Establish pathophysiology,\nbiomarkers, approved therapies, treatment guidelines, and unmet need. Use\nparallel subagents: PubMed for biology, web for guidelines, FDA for\napprovals. Write `waypoints\u002Fbiology_soc.json`.\n\n### Phase 4 — Regulatory & trials research\n\nRead `references\u002F04-regulatory-trials-research.md`. Establish FDA\u002FEMA\naccepted endpoints, regulatory precedents, typical trial design parameters,\nlandmark trials, and notable failures. Use parallel subagents: FDA for\nguidance\u002Fapprovals, CT.gov for trial patterns, PubMed for trial-history\nreviews. Write `waypoints\u002Fregulatory_trials.json`.\n\n### Phase 5 — Synthesis\n\nRead `references\u002F05-synthesis.md` and `references\u002F06-writing-style.md`. Read\nall four consolidated waypoint files. Write\n`waypoints\u002Findication_dossier_report.md` — narrative sections in the order\nthe synthesis reference specifies, with inline citations per the style guide\n— and `waypoints\u002Fresearch_output.json`. No new research threads in this\nphase. Targeted gap-fills are allowed: a single fetch to resolve a specific\nmissing value in an existing waypoint field (an approval year, an NCT ID, a\nfigure from a sponsor pipeline page). Anything broader than that, name as a\ngap rather than filling it.\n\n## Resuming\n\nIf invoked with a `workdir` that already contains waypoints: list which phases\nare complete (waypoint file exists and is non-empty), show the meta summary,\nand ask the user which phase to run next. Never overwrite an existing waypoint\nwithout confirmation.\n","# Indication Dossier\n\nProduces a structured research dossier on a single indication, framed as a\npatient population: who they are, what's wrong, how they're treated today,\nand how clinical trials can be designed to help them. Runs as five phases\nthat write resumable waypoint files; after a brief identity check at the end\nof Phase 1, the remaining phases run straight through.\n\n## Framing\n\n**Think of an indication as a patient population.** Frame everything\nfrom the patient perspective: \"Who are these patients?\" not \"What is this\ndisease?\"; \"How are these patients identified and managed?\" not \"What causes\nthis condition?\"; population nesting: \"all patients in {child} are patients\nin {parent}\".\n\nSome indications don't map to ICD codes or standard disease definitions:\n\"immunosenescence\" is a biological state, not a billable diagnosis; \"ageing\"\nis not an FDA-accepted indication; \"GLP-1 induced sarcopenia\" is an\niatrogenic population. Note these distinctions explicitly. They matter for\nregulatory path and trial design.\n\n## Inputs\n\n- **`indication`** (required) — indication name (e.g., \"sarcopenia\",\n  \"idiopathic pulmonary fibrosis\").\n- **`additional_context`** (optional) — areas to focus on, parent\n  indication, or other framing.\n- **`workdir`** (optional) — where to write waypoints and the final report.\n  Defaults to `.\u002Fdo_not_commit\u002Findication-dossier-\u003Cslug>\u002F`.\n\n## Tools this skill expects\n\n| Purpose | Tool |\n|---|---|\n| ClinicalTrials.gov | `clinical-trials` MCP |\n| Literature | `pubmed` MCP |\n| Web | `WebSearch`, `WebFetch` — FDA guidance, treatment guidelines (NCCN, AASLD, specialty societies), CDC\u002FWHO epidemiology data |\n| Documents | `WebFetch` for remote PDFs; `Read` for local PDFs |\n| Subagents | `Agent` for parallel evidence gathering |\n\nIf a listed MCP isn't connected, say so and fall back to `WebSearch` against\nthe underlying public source (clinicaltrials.gov, pubmed.ncbi.nlm.nih.gov).\n\n## Output layout\n\n```\n\u003Cworkdir>\u002F\n└── waypoints\u002F\n    ├── progress.json                 # loop control\n    ├── meta.json                     # phase 1\n    ├── epidemiology.json             # phase 2\n    ├── biology_soc.json              # phase 3\n    ├── regulatory_trials.json        # phase 4\n    ├── sources_evaluated.json\n    ├── research_output.json          # phase 5 — structured output\n    └── indication_dossier_report.md  # phase 5 — the deliverable\n```\n\nSchemas for every waypoint file are in `references\u002Fwaypoint-schemas.md`.\nWaypoints are the resumable state. If the workdir already has waypoints, read\nthem, summarize what's done, and ask which phase to resume from.\n\n## Before starting\n\nRead `references\u002F00-research-standards.md`. It governs sourcing and the\nanti-fabrication rules for every phase. Then create `\u003Cworkdir>\u002Fwaypoints\u002F`.\n\n## Workflow\n\nThe dossier is built in five phases. After each phase, write the waypoint\nfile and emit a ≤200-word summary of what you found and what's uncertain,\nthen proceed directly to the next phase. The one exception is Phase 1: after\nwriting `meta.json`, show the resolved indication identity and call\n`ask_user` with options **Proceed** \u002F **Revise identity** \u002F **Stop**, so a\nmisread indication name can be caught before the expensive phases run. If\n`ask_user` is unavailable, state \"proceeding on this interpretation;\ninterrupt now to correct it\" and continue.\n\n### Phase 1 — Meta initialization\n\nRead `references\u002F01-meta-initialization.md`. Resolve the indication identity:\nclinical definition, ICD codes, aliases, parent indication, and whether it's\na recognized diagnostic entity. Run a quick CT.gov landscape scan. Stand up\n`waypoints\u002Fmeta.json`.\n\n### Phase 2 — Epidemiology research\n\nRead `references\u002F02-epidemiology-research.md`. Characterize the population:\ndiagnostic criteria, prevalence and incidence, demographics and risk factors,\nnatural history. Use parallel subagents to search PubMed and the web\nsimultaneously. Write `waypoints\u002Fepidemiology.json`.\n\n### Phase 3 — Biology & standard-of-care research\n\nRead `references\u002F03-biology-soc-research.md`. Establish pathophysiology,\nbiomarkers, approved therapies, treatment guidelines, and unmet need. Use\nparallel subagents: PubMed for biology, web for guidelines, FDA for\napprovals. Write `waypoints\u002Fbiology_soc.json`.\n\n### Phase 4 — Regulatory & trials research\n\nRead `references\u002F04-regulatory-trials-research.md`. Establish FDA\u002FEMA\naccepted endpoints, regulatory precedents, typical trial design parameters,\nlandmark trials, and notable failures. Use parallel subagents: FDA for\nguidance\u002Fapprovals, CT.gov for trial patterns, PubMed for trial-history\nreviews. Write `waypoints\u002Fregulatory_trials.json`.\n\n### Phase 5 — Synthesis\n\nRead `references\u002F05-synthesis.md` and `references\u002F06-writing-style.md`. Read\nall four consolidated waypoint files. Write\n`waypoints\u002Findication_dossier_report.md` — narrative sections in the order\nthe synthesis reference specifies, with inline citations per the style guide\n— and `waypoints\u002Fresearch_output.json`. No new research threads in this\nphase. Targeted gap-fills are allowed: a single fetch to resolve a specific\nmissing value in an existing waypoint field (an approval year, an NCT ID, a\nfigure from a sponsor pipeline page). Anything broader than that, name as a\ngap rather than filling it.\n\n## Resuming\n\nIf invoked with a `workdir` that already contains waypoints: list which phases\nare complete (waypoint file exists and is non-empty), show the meta summary,\nand ask the user which phase to run next. Never overwrite an existing waypoint\nwithout confirmation.\n",{"name":5,"license":15,"description":24},"Generate a therapeutic indication dossier. Covers the patient population, epidemiology, disease biology, standard of care, regulatory precedent, and landmark clinical trials.\n","main","e71245365df78e06cd166602744bf2491f79910e","research-skills-hub\u002Fclaude-science-skills\u002Fskills\u002Findication-dossier",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":35,"prompt":45,"zipAvailable":46},[36,39,42],{"tool":37,"command":38},"npx","npx skills add pengqianhan\u002FAI-Human-Research-OS --skill indication-dossier",{"tool":40,"command":41},"bunx","bunx skills add pengqianhan\u002FAI-Human-Research-OS --skill indication-dossier",{"tool":43,"command":44},"pnpm","pnpm dlx skills add pengqianhan\u002FAI-Human-Research-OS --skill indication-dossier","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fpengqianhan\u002FAI-Human-Research-OS\u002Fblob\u002Fmain\u002Fresearch-skills-hub\u002Fclaude-science-skills\u002Fskills\u002Findication-dossier\u002FSKILL.md",true,[48,54,58,62,66,70,74,78],{"path":49,"resourceType":50,"resourceTypeDesc":51,"sizeBytes":52,"sourceHtmlUrl":53},"references\u002F00-research-standards.md","REFERENCE","参考文档",3101,"https:\u002F\u002Fgithub.com\u002Fpengqianhan\u002FAI-Human-Research-OS\u002Fblob\u002Fmain\u002Fresearch-skills-hub\u002Fclaude-science-skills\u002Fskills\u002Findication-dossier\u002Freferences\u002F00-research-standards.md",{"path":55,"resourceType":50,"resourceTypeDesc":51,"sizeBytes":56,"sourceHtmlUrl":57},"references\u002F01-meta-initialization.md",1724,"https:\u002F\u002Fgithub.com\u002Fpengqianhan\u002FAI-Human-Research-OS\u002Fblob\u002Fmain\u002Fresearch-skills-hub\u002Fclaude-science-skills\u002Fskills\u002Findication-dossier\u002Freferences\u002F01-meta-initialization.md",{"path":59,"resourceType":50,"resourceTypeDesc":51,"sizeBytes":60,"sourceHtmlUrl":61},"references\u002F02-epidemiology-research.md",2109,"https:\u002F\u002Fgithub.com\u002Fpengqianhan\u002FAI-Human-Research-OS\u002Fblob\u002Fmain\u002Fresearch-skills-hub\u002Fclaude-science-skills\u002Fskills\u002Findication-dossier\u002Freferences\u002F02-epidemiology-research.md",{"path":63,"resourceType":50,"resourceTypeDesc":51,"sizeBytes":64,"sourceHtmlUrl":65},"references\u002F03-biology-soc-research.md",2368,"https:\u002F\u002Fgithub.com\u002Fpengqianhan\u002FAI-Human-Research-OS\u002Fblob\u002Fmain\u002Fresearch-skills-hub\u002Fclaude-science-skills\u002Fskills\u002Findication-dossier\u002Freferences\u002F03-biology-soc-research.md",{"path":67,"resourceType":50,"resourceTypeDesc":51,"sizeBytes":68,"sourceHtmlUrl":69},"references\u002F04-regulatory-trials-research.md",3154,"https:\u002F\u002Fgithub.com\u002Fpengqianhan\u002FAI-Human-Research-OS\u002Fblob\u002Fmain\u002Fresearch-skills-hub\u002Fclaude-science-skills\u002Fskills\u002Findication-dossier\u002Freferences\u002F04-regulatory-trials-research.md",{"path":71,"resourceType":50,"resourceTypeDesc":51,"sizeBytes":72,"sourceHtmlUrl":73},"references\u002F05-synthesis.md",5323,"https:\u002F\u002Fgithub.com\u002Fpengqianhan\u002FAI-Human-Research-OS\u002Fblob\u002Fmain\u002Fresearch-skills-hub\u002Fclaude-science-skills\u002Fskills\u002Findication-dossier\u002Freferences\u002F05-synthesis.md",{"path":75,"resourceType":50,"resourceTypeDesc":51,"sizeBytes":76,"sourceHtmlUrl":77},"references\u002F06-writing-style.md",1746,"https:\u002F\u002Fgithub.com\u002Fpengqianhan\u002FAI-Human-Research-OS\u002Fblob\u002Fmain\u002Fresearch-skills-hub\u002Fclaude-science-skills\u002Fskills\u002Findication-dossier\u002Freferences\u002F06-writing-style.md",{"path":79,"resourceType":50,"resourceTypeDesc":51,"sizeBytes":80,"sourceHtmlUrl":81},"references\u002Fwaypoint-schemas.md",2923,"https:\u002F\u002Fgithub.com\u002Fpengqianhan\u002FAI-Human-Research-OS\u002Fblob\u002Fmain\u002Fresearch-skills-hub\u002Fclaude-science-skills\u002Fskills\u002Findication-dossier\u002Freferences\u002Fwaypoint-schemas.md",[83,91,98,105,112,119],{"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":87,"licenseFileUrl":6,"sourceHtmlUrl":88,"categories":89,"keywords":90,"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).","MIT","https:\u002F\u002Fgithub.com\u002Fpengqianhan\u002FAI-Human-Research-OS\u002Fblob\u002Fmain\u002Fresearch-skills-hub\u002Fscience-skills\u002Fworkflow_skill_creator\u002FSKILL.md",[],[],{"skillNo":92,"name":93,"nameZh":6,"description":94,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":87,"licenseFileUrl":6,"sourceHtmlUrl":95,"categories":96,"keywords":97,"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":99,"name":100,"nameZh":6,"description":101,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":87,"licenseFileUrl":6,"sourceHtmlUrl":102,"categories":103,"keywords":104,"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":106,"name":107,"nameZh":6,"description":108,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":87,"licenseFileUrl":6,"sourceHtmlUrl":109,"categories":110,"keywords":111,"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":113,"name":114,"nameZh":6,"description":115,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":87,"licenseFileUrl":6,"sourceHtmlUrl":116,"categories":117,"keywords":118,"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":120,"name":121,"nameZh":6,"description":122,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":87,"licenseFileUrl":6,"sourceHtmlUrl":123,"categories":124,"keywords":125,"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",[],[]]