[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill-openai-research-router-skill":3,"mdc--hgfysx-key":36,"related-repo-openai-research-router-skill":833,"related-org-openai-research-router-skill":955},{"slug":4,"name":4,"fn":5,"description":6,"org":7,"tags":11,"stars":25,"repoUrl":26,"updatedAt":27,"license":28,"forks":29,"topics":30,"repo":31,"sourceUrl":34,"mdContent":35},"research-router-skill","route life-sciences research requests","Route broad or ambiguous life-sciences research requests to the right skills, normalize core entities, optionally parallelize independent evidence gathering with subagents when available, and synthesize a concise evidence-backed answer. Use when a user asks a general life-sciences question that could span multiple sources or analysis types.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},"openai","OpenAI","https:\u002F\u002Fpexgzepcugksgbtrxkhf.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Forg-logos\u002Fopenai.png",[12,16,19,22],{"name":13,"slug":14,"type":15},"Research","research","tag",{"name":17,"slug":18,"type":15},"Summarization","summarization",{"name":20,"slug":21,"type":15},"Life Sciences","life-sciences",{"name":23,"slug":24,"type":15},"Agents","agents",3992,"https:\u002F\u002Fgithub.com\u002Fopenai\u002Fplugins","2026-04-10T05:12:39.484701",null,465,[],{"repoUrl":26,"stars":25,"forks":29,"topics":32,"description":33},[],"OpenAI Plugins","https:\u002F\u002Fgithub.com\u002Fopenai\u002Fplugins\u002Ftree\u002FHEAD\u002Fplugins\u002Flife-science-research\u002Fskills\u002Fresearch-router-skill","---\nname: research-router-skill\ndescription: Route broad or ambiguous life-sciences research requests to the right skills, normalize core entities, optionally parallelize independent evidence gathering with subagents when available, and synthesize a concise evidence-backed answer. Use when a user asks a general life-sciences question that could span multiple sources or analysis types.\n---\n\n## Research Router\n\nUse this skill as the default orchestration layer for broad life-sciences research requests.\n\nDo not use it for narrow single-source lookups when a more specific skill already matches the request cleanly.\n\n## Primary Responsibility\n\nTurn an open-ended research question into a small, defensible retrieval plan:\n\n1. understand the research objective\n2. normalize the main entities\n3. select the minimum useful set of downstream skills\n4. gather evidence\n5. synthesize the answer for the user\n\nThe router owns the framing and the final synthesis. It should not dump raw source payloads unless the user explicitly asks for them.\n\n## When To Use This Skill\n\nUse this skill when any of the following are true:\n\n- the user asks a broad question such as `what is known about ...`\n- the question could require more than one evidence type\n- the right source is unclear at the start\n- the request mixes entities, for example gene plus disease, variant plus phenotype, protein plus ligand, or pathway plus dataset\n- the user wants a synthesized answer rather than a single database lookup\n\n## Research Task Classification\n\nStart by classifying the request into one or more lanes:\n\n- human genetics and variant interpretation\n- locus-to-gene prioritization\n- expression, tissue, or cell-type context\n- pathway, network, or functional biology\n- protein structure and mechanism\n- chemistry, ligands, and pharmacology\n- clinical, translational, or cancer evidence\n- literature, preprints, and public dataset discovery\n- metabolomics, proteomics, or microbiome context\n\nPrefer 1 to 3 lanes. Only expand further if the user explicitly asks for a broad landscape review.\n\n## Entity Normalization\n\nNormalize the key entities before deep retrieval.\n\nCommon patterns:\n\n- gene or protein: `ncbi-clinicaltables-skill`, `ensembl-skill`, `uniprot-skill`\n- disease or phenotype: `efo-ontology-skill`, `opentargets-skill`\n- variant: `clinvar-variation-skill`, `ensembl-skill`, cohort-specific PheWAS skills\n- compound or metabolite: `chembl-skill`, `pubchem-pug-skill`, `chebi-skill`, `hmdb-skill`\n- pathway or function: `reactome-skill`, `quickgo-skill`, `string-skill`\n- accession or dataset identifier: `ncbi-datasets-skill`, `biostudies-arrayexpress-skill`, `pride-skill`, `metabolights-skill`\n\nDo not start broad evidence collection until the important entities are stable enough to route correctly.\n\n## Skill Selection Heuristics\n\nChoose the smallest set of skills that can answer the question well.\n\nExamples:\n\n- target or disease evidence review:\n  `opentargets-skill`, `gwas-catalog-skill`, `gtex-eqtl-skill`, `human-protein-atlas-skill`\n- variant interpretation:\n  `clinvar-variation-skill`, `gnomad-graphql-skill`, `ensembl-skill`, one or more cohort PheWAS skills\n- locus-to-gene mapping:\n  `locus-to-gene-mapper-skill`, or its component genetics skills when the user wants a custom workflow\n- structure and mechanism:\n  `alphafold-skill`, `rcsb-pdb-skill`, `uniprot-skill`, `reactome-skill`\n- chemistry and pharmacology:\n  `chembl-skill`, `bindingdb-skill`, `pubchem-pug-skill`, `pharmgkb-skill`\n- clinical and translational:\n  `clinicaltrials-skill`, `cbioportal-skill`, `civic-skill`\n- literature and dataset discovery:\n  `ncbi-entrez-skill`, `ncbi-pmc-skill`, `biorxiv-skill`, `biostudies-arrayexpress-skill`, `ncbi-datasets-skill`\n\nPrefer direct lookups before expensive multi-step chains.\n\n## Subagent And Parallelization Guidance\n\nIf Codex subagents are available, use them only when the work cleanly decomposes into independent lanes.\n\nGood candidates for subagents:\n\n- genetics, expression, structure, chemistry, and clinical evidence can be gathered independently for the same question\n- multiple loci, variants, genes, compounds, or datasets need parallel comparison\n- a broad landscape review requires separate evidence summaries before synthesis\n\nKeep these steps with the coordinating agent:\n\n- initial interpretation of the user request\n- entity normalization and final scope decisions\n- conflict resolution across evidence sources\n- final synthesis and recommendation writing\n\nAvoid subagents when:\n\n- one specific skill already answers the question\n- later steps depend tightly on earlier intermediate outputs\n- the work is mostly identifier resolution or narrow follow-up lookup\n- the extra coordination cost is likely to exceed the retrieval benefit\n\nWhen delegating, give each subagent a bounded read-only objective such as one evidence family or one comparison unit. Each subagent should return:\n\n- what it checked\n- the key findings\n- the main caveats\n- which skills or sources it used\n- any artifact paths it produced\n\nThe coordinating agent is responsible for reconciling overlaps, contradictions, and evidence gaps.\n\n## Output Contract\n\nReturn a concise answer structured around the user's question, not around the tools.\n\nUnless the user asks for a different format, include:\n\n1. direct answer or working conclusion\n2. key evidence by lane\n3. main caveats or unresolved questions\n4. recommended next analyses or follow-up lookups\n\nIf the task is exploratory, explicitly distinguish:\n\n- evidence that supports a conclusion\n- evidence that is only suggestive\n- evidence that is missing or contradictory\n\n## Operating Rules\n\n- prefer concise source-backed synthesis over large raw dumps\n- escalate to multi-skill workflows only when the question requires synthesis\n- state important cohort, ancestry, assay, tissue, and study-design limitations\n- do not overstate causality from association-only evidence\n- if a downstream skill can answer the request directly, hand off to it instead of keeping the router in the foreground\n",{"data":37,"body":38},{"name":4,"description":6},{"type":39,"children":40},"root",[41,50,56,61,67,72,102,107,113,118,154,160,165,213,218,224,229,234,389,394,400,405,410,604,609,615,620,625,643,648,671,676,699,704,732,737,743,748,753,776,781,799,805],{"type":42,"tag":43,"props":44,"children":46},"element","h2",{"id":45},"research-router",[47],{"type":48,"value":49},"text","Research Router",{"type":42,"tag":51,"props":52,"children":53},"p",{},[54],{"type":48,"value":55},"Use this skill as the default orchestration layer for broad life-sciences research requests.",{"type":42,"tag":51,"props":57,"children":58},{},[59],{"type":48,"value":60},"Do not use it for narrow single-source lookups when a more specific skill already matches the request cleanly.",{"type":42,"tag":43,"props":62,"children":64},{"id":63},"primary-responsibility",[65],{"type":48,"value":66},"Primary Responsibility",{"type":42,"tag":51,"props":68,"children":69},{},[70],{"type":48,"value":71},"Turn an open-ended research question into a small, defensible retrieval plan:",{"type":42,"tag":73,"props":74,"children":75},"ol",{},[76,82,87,92,97],{"type":42,"tag":77,"props":78,"children":79},"li",{},[80],{"type":48,"value":81},"understand the research objective",{"type":42,"tag":77,"props":83,"children":84},{},[85],{"type":48,"value":86},"normalize the main entities",{"type":42,"tag":77,"props":88,"children":89},{},[90],{"type":48,"value":91},"select the minimum useful set of downstream skills",{"type":42,"tag":77,"props":93,"children":94},{},[95],{"type":48,"value":96},"gather evidence",{"type":42,"tag":77,"props":98,"children":99},{},[100],{"type":48,"value":101},"synthesize the answer for the user",{"type":42,"tag":51,"props":103,"children":104},{},[105],{"type":48,"value":106},"The router owns the framing and the final synthesis. It should not dump raw source payloads unless the user explicitly asks for them.",{"type":42,"tag":43,"props":108,"children":110},{"id":109},"when-to-use-this-skill",[111],{"type":48,"value":112},"When To Use This Skill",{"type":42,"tag":51,"props":114,"children":115},{},[116],{"type":48,"value":117},"Use this skill when any of the following are true:",{"type":42,"tag":119,"props":120,"children":121},"ul",{},[122,134,139,144,149],{"type":42,"tag":77,"props":123,"children":124},{},[125,127],{"type":48,"value":126},"the user asks a broad question such as ",{"type":42,"tag":128,"props":129,"children":131},"code",{"className":130},[],[132],{"type":48,"value":133},"what is known about ...",{"type":42,"tag":77,"props":135,"children":136},{},[137],{"type":48,"value":138},"the question could require more than one evidence type",{"type":42,"tag":77,"props":140,"children":141},{},[142],{"type":48,"value":143},"the right source is unclear at the start",{"type":42,"tag":77,"props":145,"children":146},{},[147],{"type":48,"value":148},"the request mixes entities, for example gene plus disease, variant plus phenotype, protein plus ligand, or pathway plus dataset",{"type":42,"tag":77,"props":150,"children":151},{},[152],{"type":48,"value":153},"the user wants a synthesized answer rather than a single database lookup",{"type":42,"tag":43,"props":155,"children":157},{"id":156},"research-task-classification",[158],{"type":48,"value":159},"Research Task Classification",{"type":42,"tag":51,"props":161,"children":162},{},[163],{"type":48,"value":164},"Start by classifying the request into one or more lanes:",{"type":42,"tag":119,"props":166,"children":167},{},[168,173,178,183,188,193,198,203,208],{"type":42,"tag":77,"props":169,"children":170},{},[171],{"type":48,"value":172},"human genetics and variant interpretation",{"type":42,"tag":77,"props":174,"children":175},{},[176],{"type":48,"value":177},"locus-to-gene prioritization",{"type":42,"tag":77,"props":179,"children":180},{},[181],{"type":48,"value":182},"expression, tissue, or cell-type context",{"type":42,"tag":77,"props":184,"children":185},{},[186],{"type":48,"value":187},"pathway, network, or functional biology",{"type":42,"tag":77,"props":189,"children":190},{},[191],{"type":48,"value":192},"protein structure and mechanism",{"type":42,"tag":77,"props":194,"children":195},{},[196],{"type":48,"value":197},"chemistry, ligands, and pharmacology",{"type":42,"tag":77,"props":199,"children":200},{},[201],{"type":48,"value":202},"clinical, translational, or cancer evidence",{"type":42,"tag":77,"props":204,"children":205},{},[206],{"type":48,"value":207},"literature, preprints, and public dataset discovery",{"type":42,"tag":77,"props":209,"children":210},{},[211],{"type":48,"value":212},"metabolomics, proteomics, or microbiome context",{"type":42,"tag":51,"props":214,"children":215},{},[216],{"type":48,"value":217},"Prefer 1 to 3 lanes. Only expand further if the user explicitly asks for a broad landscape review.",{"type":42,"tag":43,"props":219,"children":221},{"id":220},"entity-normalization",[222],{"type":48,"value":223},"Entity Normalization",{"type":42,"tag":51,"props":225,"children":226},{},[227],{"type":48,"value":228},"Normalize the key entities before deep retrieval.",{"type":42,"tag":51,"props":230,"children":231},{},[232],{"type":48,"value":233},"Common patterns:",{"type":42,"tag":119,"props":235,"children":236},{},[237,263,281,300,332,357],{"type":42,"tag":77,"props":238,"children":239},{},[240,242,248,250,256,257],{"type":48,"value":241},"gene or protein: ",{"type":42,"tag":128,"props":243,"children":245},{"className":244},[],[246],{"type":48,"value":247},"ncbi-clinicaltables-skill",{"type":48,"value":249},", ",{"type":42,"tag":128,"props":251,"children":253},{"className":252},[],[254],{"type":48,"value":255},"ensembl-skill",{"type":48,"value":249},{"type":42,"tag":128,"props":258,"children":260},{"className":259},[],[261],{"type":48,"value":262},"uniprot-skill",{"type":42,"tag":77,"props":264,"children":265},{},[266,268,274,275],{"type":48,"value":267},"disease or phenotype: ",{"type":42,"tag":128,"props":269,"children":271},{"className":270},[],[272],{"type":48,"value":273},"efo-ontology-skill",{"type":48,"value":249},{"type":42,"tag":128,"props":276,"children":278},{"className":277},[],[279],{"type":48,"value":280},"opentargets-skill",{"type":42,"tag":77,"props":282,"children":283},{},[284,286,292,293,298],{"type":48,"value":285},"variant: ",{"type":42,"tag":128,"props":287,"children":289},{"className":288},[],[290],{"type":48,"value":291},"clinvar-variation-skill",{"type":48,"value":249},{"type":42,"tag":128,"props":294,"children":296},{"className":295},[],[297],{"type":48,"value":255},{"type":48,"value":299},", cohort-specific PheWAS skills",{"type":42,"tag":77,"props":301,"children":302},{},[303,305,311,312,318,319,325,326],{"type":48,"value":304},"compound or metabolite: ",{"type":42,"tag":128,"props":306,"children":308},{"className":307},[],[309],{"type":48,"value":310},"chembl-skill",{"type":48,"value":249},{"type":42,"tag":128,"props":313,"children":315},{"className":314},[],[316],{"type":48,"value":317},"pubchem-pug-skill",{"type":48,"value":249},{"type":42,"tag":128,"props":320,"children":322},{"className":321},[],[323],{"type":48,"value":324},"chebi-skill",{"type":48,"value":249},{"type":42,"tag":128,"props":327,"children":329},{"className":328},[],[330],{"type":48,"value":331},"hmdb-skill",{"type":42,"tag":77,"props":333,"children":334},{},[335,337,343,344,350,351],{"type":48,"value":336},"pathway or function: ",{"type":42,"tag":128,"props":338,"children":340},{"className":339},[],[341],{"type":48,"value":342},"reactome-skill",{"type":48,"value":249},{"type":42,"tag":128,"props":345,"children":347},{"className":346},[],[348],{"type":48,"value":349},"quickgo-skill",{"type":48,"value":249},{"type":42,"tag":128,"props":352,"children":354},{"className":353},[],[355],{"type":48,"value":356},"string-skill",{"type":42,"tag":77,"props":358,"children":359},{},[360,362,368,369,375,376,382,383],{"type":48,"value":361},"accession or dataset identifier: ",{"type":42,"tag":128,"props":363,"children":365},{"className":364},[],[366],{"type":48,"value":367},"ncbi-datasets-skill",{"type":48,"value":249},{"type":42,"tag":128,"props":370,"children":372},{"className":371},[],[373],{"type":48,"value":374},"biostudies-arrayexpress-skill",{"type":48,"value":249},{"type":42,"tag":128,"props":377,"children":379},{"className":378},[],[380],{"type":48,"value":381},"pride-skill",{"type":48,"value":249},{"type":42,"tag":128,"props":384,"children":386},{"className":385},[],[387],{"type":48,"value":388},"metabolights-skill",{"type":42,"tag":51,"props":390,"children":391},{},[392],{"type":48,"value":393},"Do not start broad evidence collection until the important entities are stable enough to route correctly.",{"type":42,"tag":43,"props":395,"children":397},{"id":396},"skill-selection-heuristics",[398],{"type":48,"value":399},"Skill Selection Heuristics",{"type":42,"tag":51,"props":401,"children":402},{},[403],{"type":48,"value":404},"Choose the smallest set of skills that can answer the question well.",{"type":42,"tag":51,"props":406,"children":407},{},[408],{"type":48,"value":409},"Examples:",{"type":42,"tag":119,"props":411,"children":412},{},[413,444,469,482,512,542,567],{"type":42,"tag":77,"props":414,"children":415},{},[416,418,423,424,430,431,437,438],{"type":48,"value":417},"target or disease evidence review:\n",{"type":42,"tag":128,"props":419,"children":421},{"className":420},[],[422],{"type":48,"value":280},{"type":48,"value":249},{"type":42,"tag":128,"props":425,"children":427},{"className":426},[],[428],{"type":48,"value":429},"gwas-catalog-skill",{"type":48,"value":249},{"type":42,"tag":128,"props":432,"children":434},{"className":433},[],[435],{"type":48,"value":436},"gtex-eqtl-skill",{"type":48,"value":249},{"type":42,"tag":128,"props":439,"children":441},{"className":440},[],[442],{"type":48,"value":443},"human-protein-atlas-skill",{"type":42,"tag":77,"props":445,"children":446},{},[447,449,454,455,461,462,467],{"type":48,"value":448},"variant interpretation:\n",{"type":42,"tag":128,"props":450,"children":452},{"className":451},[],[453],{"type":48,"value":291},{"type":48,"value":249},{"type":42,"tag":128,"props":456,"children":458},{"className":457},[],[459],{"type":48,"value":460},"gnomad-graphql-skill",{"type":48,"value":249},{"type":42,"tag":128,"props":463,"children":465},{"className":464},[],[466],{"type":48,"value":255},{"type":48,"value":468},", one or more cohort PheWAS skills",{"type":42,"tag":77,"props":470,"children":471},{},[472,474,480],{"type":48,"value":473},"locus-to-gene mapping:\n",{"type":42,"tag":128,"props":475,"children":477},{"className":476},[],[478],{"type":48,"value":479},"locus-to-gene-mapper-skill",{"type":48,"value":481},", or its component genetics skills when the user wants a custom workflow",{"type":42,"tag":77,"props":483,"children":484},{},[485,487,493,494,500,501,506,507],{"type":48,"value":486},"structure and mechanism:\n",{"type":42,"tag":128,"props":488,"children":490},{"className":489},[],[491],{"type":48,"value":492},"alphafold-skill",{"type":48,"value":249},{"type":42,"tag":128,"props":495,"children":497},{"className":496},[],[498],{"type":48,"value":499},"rcsb-pdb-skill",{"type":48,"value":249},{"type":42,"tag":128,"props":502,"children":504},{"className":503},[],[505],{"type":48,"value":262},{"type":48,"value":249},{"type":42,"tag":128,"props":508,"children":510},{"className":509},[],[511],{"type":48,"value":342},{"type":42,"tag":77,"props":513,"children":514},{},[515,517,522,523,529,530,535,536],{"type":48,"value":516},"chemistry and pharmacology:\n",{"type":42,"tag":128,"props":518,"children":520},{"className":519},[],[521],{"type":48,"value":310},{"type":48,"value":249},{"type":42,"tag":128,"props":524,"children":526},{"className":525},[],[527],{"type":48,"value":528},"bindingdb-skill",{"type":48,"value":249},{"type":42,"tag":128,"props":531,"children":533},{"className":532},[],[534],{"type":48,"value":317},{"type":48,"value":249},{"type":42,"tag":128,"props":537,"children":539},{"className":538},[],[540],{"type":48,"value":541},"pharmgkb-skill",{"type":42,"tag":77,"props":543,"children":544},{},[545,547,553,554,560,561],{"type":48,"value":546},"clinical and translational:\n",{"type":42,"tag":128,"props":548,"children":550},{"className":549},[],[551],{"type":48,"value":552},"clinicaltrials-skill",{"type":48,"value":249},{"type":42,"tag":128,"props":555,"children":557},{"className":556},[],[558],{"type":48,"value":559},"cbioportal-skill",{"type":48,"value":249},{"type":42,"tag":128,"props":562,"children":564},{"className":563},[],[565],{"type":48,"value":566},"civic-skill",{"type":42,"tag":77,"props":568,"children":569},{},[570,572,578,579,585,586,592,593,598,599],{"type":48,"value":571},"literature and dataset discovery:\n",{"type":42,"tag":128,"props":573,"children":575},{"className":574},[],[576],{"type":48,"value":577},"ncbi-entrez-skill",{"type":48,"value":249},{"type":42,"tag":128,"props":580,"children":582},{"className":581},[],[583],{"type":48,"value":584},"ncbi-pmc-skill",{"type":48,"value":249},{"type":42,"tag":128,"props":587,"children":589},{"className":588},[],[590],{"type":48,"value":591},"biorxiv-skill",{"type":48,"value":249},{"type":42,"tag":128,"props":594,"children":596},{"className":595},[],[597],{"type":48,"value":374},{"type":48,"value":249},{"type":42,"tag":128,"props":600,"children":602},{"className":601},[],[603],{"type":48,"value":367},{"type":42,"tag":51,"props":605,"children":606},{},[607],{"type":48,"value":608},"Prefer direct lookups before expensive multi-step chains.",{"type":42,"tag":43,"props":610,"children":612},{"id":611},"subagent-and-parallelization-guidance",[613],{"type":48,"value":614},"Subagent And Parallelization Guidance",{"type":42,"tag":51,"props":616,"children":617},{},[618],{"type":48,"value":619},"If Codex subagents are available, use them only when the work cleanly decomposes into independent lanes.",{"type":42,"tag":51,"props":621,"children":622},{},[623],{"type":48,"value":624},"Good candidates for subagents:",{"type":42,"tag":119,"props":626,"children":627},{},[628,633,638],{"type":42,"tag":77,"props":629,"children":630},{},[631],{"type":48,"value":632},"genetics, expression, structure, chemistry, and clinical evidence can be gathered independently for the same question",{"type":42,"tag":77,"props":634,"children":635},{},[636],{"type":48,"value":637},"multiple loci, variants, genes, compounds, or datasets need parallel comparison",{"type":42,"tag":77,"props":639,"children":640},{},[641],{"type":48,"value":642},"a broad landscape review requires separate evidence summaries before synthesis",{"type":42,"tag":51,"props":644,"children":645},{},[646],{"type":48,"value":647},"Keep these steps with the coordinating agent:",{"type":42,"tag":119,"props":649,"children":650},{},[651,656,661,666],{"type":42,"tag":77,"props":652,"children":653},{},[654],{"type":48,"value":655},"initial interpretation of the user request",{"type":42,"tag":77,"props":657,"children":658},{},[659],{"type":48,"value":660},"entity normalization and final scope decisions",{"type":42,"tag":77,"props":662,"children":663},{},[664],{"type":48,"value":665},"conflict resolution across evidence sources",{"type":42,"tag":77,"props":667,"children":668},{},[669],{"type":48,"value":670},"final synthesis and recommendation writing",{"type":42,"tag":51,"props":672,"children":673},{},[674],{"type":48,"value":675},"Avoid subagents when:",{"type":42,"tag":119,"props":677,"children":678},{},[679,684,689,694],{"type":42,"tag":77,"props":680,"children":681},{},[682],{"type":48,"value":683},"one specific skill already answers the question",{"type":42,"tag":77,"props":685,"children":686},{},[687],{"type":48,"value":688},"later steps depend tightly on earlier intermediate outputs",{"type":42,"tag":77,"props":690,"children":691},{},[692],{"type":48,"value":693},"the work is mostly identifier resolution or narrow follow-up lookup",{"type":42,"tag":77,"props":695,"children":696},{},[697],{"type":48,"value":698},"the extra coordination cost is likely to exceed the retrieval benefit",{"type":42,"tag":51,"props":700,"children":701},{},[702],{"type":48,"value":703},"When delegating, give each subagent a bounded read-only objective such as one evidence family or one comparison unit. Each subagent should return:",{"type":42,"tag":119,"props":705,"children":706},{},[707,712,717,722,727],{"type":42,"tag":77,"props":708,"children":709},{},[710],{"type":48,"value":711},"what it checked",{"type":42,"tag":77,"props":713,"children":714},{},[715],{"type":48,"value":716},"the key findings",{"type":42,"tag":77,"props":718,"children":719},{},[720],{"type":48,"value":721},"the main caveats",{"type":42,"tag":77,"props":723,"children":724},{},[725],{"type":48,"value":726},"which skills or sources it used",{"type":42,"tag":77,"props":728,"children":729},{},[730],{"type":48,"value":731},"any artifact paths it produced",{"type":42,"tag":51,"props":733,"children":734},{},[735],{"type":48,"value":736},"The coordinating agent is responsible for reconciling overlaps, contradictions, and evidence gaps.",{"type":42,"tag":43,"props":738,"children":740},{"id":739},"output-contract",[741],{"type":48,"value":742},"Output Contract",{"type":42,"tag":51,"props":744,"children":745},{},[746],{"type":48,"value":747},"Return a concise answer structured around the user's question, not around the tools.",{"type":42,"tag":51,"props":749,"children":750},{},[751],{"type":48,"value":752},"Unless the user asks for a different format, include:",{"type":42,"tag":73,"props":754,"children":755},{},[756,761,766,771],{"type":42,"tag":77,"props":757,"children":758},{},[759],{"type":48,"value":760},"direct answer or working conclusion",{"type":42,"tag":77,"props":762,"children":763},{},[764],{"type":48,"value":765},"key evidence by lane",{"type":42,"tag":77,"props":767,"children":768},{},[769],{"type":48,"value":770},"main caveats or unresolved questions",{"type":42,"tag":77,"props":772,"children":773},{},[774],{"type":48,"value":775},"recommended next analyses or follow-up lookups",{"type":42,"tag":51,"props":777,"children":778},{},[779],{"type":48,"value":780},"If the task is exploratory, explicitly distinguish:",{"type":42,"tag":119,"props":782,"children":783},{},[784,789,794],{"type":42,"tag":77,"props":785,"children":786},{},[787],{"type":48,"value":788},"evidence that supports a conclusion",{"type":42,"tag":77,"props":790,"children":791},{},[792],{"type":48,"value":793},"evidence that is only suggestive",{"type":42,"tag":77,"props":795,"children":796},{},[797],{"type":48,"value":798},"evidence that is missing or contradictory",{"type":42,"tag":43,"props":800,"children":802},{"id":801},"operating-rules",[803],{"type":48,"value":804},"Operating Rules",{"type":42,"tag":119,"props":806,"children":807},{},[808,813,818,823,828],{"type":42,"tag":77,"props":809,"children":810},{},[811],{"type":48,"value":812},"prefer concise source-backed synthesis over large raw dumps",{"type":42,"tag":77,"props":814,"children":815},{},[816],{"type":48,"value":817},"escalate to multi-skill workflows only when the question requires synthesis",{"type":42,"tag":77,"props":819,"children":820},{},[821],{"type":48,"value":822},"state important cohort, ancestry, assay, tissue, and study-design limitations",{"type":42,"tag":77,"props":824,"children":825},{},[826],{"type":48,"value":827},"do not overstate causality from association-only evidence",{"type":42,"tag":77,"props":829,"children":830},{},[831],{"type":48,"value":832},"if a downstream skill can answer the request directly, hand off to it instead of keeping the router in the foreground",{"items":834,"total":954},[835,854,868,880,900,922,942],{"slug":836,"name":836,"fn":837,"description":838,"org":839,"tags":840,"stars":25,"repoUrl":26,"updatedAt":853},"accessibility-and-inclusive-visualization","make data visualizations accessible","Make data visualizations accessible and inclusive. Use when the user needs chart or diagram accessibility guidance, text alternatives for complex visuals, color and contrast review, keyboard support, reduced-motion behavior for animation or parallax, or an accessibility QA workflow for exported figures, UML-like diagrams, and dashboards.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[841,844,847,850],{"name":842,"slug":843,"type":15},"Accessibility","accessibility",{"name":845,"slug":846,"type":15},"Charts","charts",{"name":848,"slug":849,"type":15},"Data Visualization","data-visualization",{"name":851,"slug":852,"type":15},"Design","design","2026-06-30T19:00:57.102",{"slug":855,"name":855,"fn":856,"description":857,"org":858,"tags":859,"stars":25,"repoUrl":26,"updatedAt":867},"agent-browser","automate browser interactions for agents","Browser automation CLI for AI agents. Use when the user needs to interact with websites, verify dev server output, test web apps, navigate pages, fill forms, click buttons, take screenshots, extract data, or automate any browser task. Also triggers when a dev server starts so you can verify it visually.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[860,861,864],{"name":23,"slug":24,"type":15},{"name":862,"slug":863,"type":15},"Browser Automation","browser-automation",{"name":865,"slug":866,"type":15},"Testing","testing","2026-04-06T18:41:03.44016",{"slug":869,"name":869,"fn":870,"description":871,"org":872,"tags":873,"stars":25,"repoUrl":26,"updatedAt":879},"agent-browser-verify","verify dev server output with automated browser","Automated browser verification for dev servers. Triggers when a dev server starts to run a visual gut-check with agent-browser — verifies the page loads, checks for console errors, validates key UI elements, and reports pass\u002Ffail before continuing.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[874,875,878],{"name":862,"slug":863,"type":15},{"name":876,"slug":877,"type":15},"Local Development","local-development",{"name":865,"slug":866,"type":15},"2026-04-06T18:41:17.526867",{"slug":881,"name":881,"fn":882,"description":883,"org":884,"tags":885,"stars":25,"repoUrl":26,"updatedAt":899},"agents-sdk","build AI agents on Cloudflare Workers","Build AI agents on Cloudflare Workers using the Agents SDK. Load when creating stateful agents, durable workflows, real-time WebSocket apps, scheduled tasks, MCP servers, or chat applications. Covers Agent class, state management, callable RPC, Workflows integration, and React hooks. Biases towards retrieval from Cloudflare docs over pre-trained knowledge.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[886,887,890,893,896],{"name":23,"slug":24,"type":15},{"name":888,"slug":889,"type":15},"Cloudflare Workers","cloudflare-workers",{"name":891,"slug":892,"type":15},"SDK","sdk",{"name":894,"slug":895,"type":15},"Serverless","serverless",{"name":897,"slug":898,"type":15},"WebSockets","websockets","2026-04-06T18:39:51.717063",{"slug":901,"name":901,"fn":902,"description":903,"org":904,"tags":905,"stars":25,"repoUrl":26,"updatedAt":921},"ai-elements","build chat UIs with AI Elements","AI Elements component library guidance — pre-built React components for AI interfaces built on shadcn\u002Fui. Use when building chat UIs, message displays, tool call rendering, streaming responses, reasoning panels, or any AI-native interface with the AI SDK.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[906,909,912,915,918],{"name":907,"slug":908,"type":15},"Frontend","frontend",{"name":910,"slug":911,"type":15},"React","react",{"name":913,"slug":914,"type":15},"shadcn\u002Fui","shadcn-ui",{"name":916,"slug":917,"type":15},"UI Components","ui-components",{"name":919,"slug":920,"type":15},"Vercel","vercel","2026-04-06T18:40:59.619419",{"slug":923,"name":923,"fn":924,"description":925,"org":926,"tags":927,"stars":25,"repoUrl":26,"updatedAt":941},"ai-gateway","configure Vercel AI Gateway","Vercel AI Gateway expert guidance. Use when configuring model routing, provider failover, cost tracking, or managing multiple AI providers through a unified API.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[928,931,934,937,940],{"name":929,"slug":930,"type":15},"AI Infrastructure","ai-infrastructure",{"name":932,"slug":933,"type":15},"Cost Optimization","cost-optimization",{"name":935,"slug":936,"type":15},"LLM","llm",{"name":938,"slug":939,"type":15},"Performance","performance",{"name":919,"slug":920,"type":15},"2026-04-06T18:40:44.377464",{"slug":943,"name":943,"fn":944,"description":945,"org":946,"tags":947,"stars":25,"repoUrl":26,"updatedAt":953},"ai-generation-persistence","implement persistence patterns for AI generations","AI generation persistence patterns — unique IDs, addressable URLs, database storage, and cost tracking for every LLM generation",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[948,949,952],{"name":932,"slug":933,"type":15},{"name":950,"slug":951,"type":15},"Database","database",{"name":935,"slug":936,"type":15},"2026-04-06T18:41:08.513425",600,{"items":956,"total":1153},[957,978,1001,1018,1034,1051,1070,1082,1096,1110,1122,1137],{"slug":958,"name":958,"fn":959,"description":960,"org":961,"tags":962,"stars":975,"repoUrl":976,"updatedAt":977},"prior-auth-packet-builder","build healthcare prior authorization packets","Build a concise prior authorization packet from local case files and payer policy docs.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[963,966,969,972],{"name":964,"slug":965,"type":15},"Documents","documents",{"name":967,"slug":968,"type":15},"Healthcare","healthcare",{"name":970,"slug":971,"type":15},"Insurance","insurance",{"name":973,"slug":974,"type":15},"Regulatory Compliance","regulatory-compliance",28169,"https:\u002F\u002Fgithub.com\u002Fopenai\u002Fopenai-agents-python","2026-04-16T05:11:39.180399",{"slug":979,"name":979,"fn":980,"description":981,"org":982,"tags":983,"stars":998,"repoUrl":999,"updatedAt":1000},"aspnet-core","build ASP.NET Core web applications","Build, review, refactor, or architect ASP.NET Core web applications using current official guidance for .NET web development. Use when working on Blazor Web Apps, Razor Pages, MVC, Minimal APIs, controller-based Web APIs, SignalR, gRPC, middleware, dependency injection, configuration, authentication, authorization, testing, performance, deployment, or ASP.NET Core upgrades.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[984,987,989,992,995],{"name":985,"slug":986,"type":15},".NET","dotnet",{"name":988,"slug":979,"type":15},"ASP.NET Core",{"name":990,"slug":991,"type":15},"Blazor","blazor",{"name":993,"slug":994,"type":15},"C#","csharp",{"name":996,"slug":997,"type":15},"Web Development","web-development",23787,"https:\u002F\u002Fgithub.com\u002Fopenai\u002Fskills","2026-04-12T05:07:02.819491",{"slug":1002,"name":1002,"fn":1003,"description":1004,"org":1005,"tags":1006,"stars":998,"repoUrl":999,"updatedAt":1017},"chatgpt-apps","build ChatGPT Apps SDK applications","Build, scaffold, refactor, and troubleshoot ChatGPT Apps SDK applications that combine an MCP server and widget UI. Use when Codex needs to design tools, register UI resources, wire the MCP Apps bridge or ChatGPT compatibility APIs, apply Apps SDK metadata or CSP or domain settings, or produce a docs-aligned project scaffold. Prefer a docs-first workflow by invoking the openai-docs skill or OpenAI developer docs MCP tools before generating code.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[1007,1010,1013,1016],{"name":1008,"slug":1009,"type":15},"Apps SDK","apps-sdk",{"name":1011,"slug":1012,"type":15},"ChatGPT","chatgpt",{"name":1014,"slug":1015,"type":15},"MCP","mcp",{"name":9,"slug":8,"type":15},"2026-04-12T05:07:05.468097",{"slug":1019,"name":1019,"fn":1020,"description":1021,"org":1022,"tags":1023,"stars":998,"repoUrl":999,"updatedAt":1033},"cli-creator","build CLIs from API docs","Build a composable CLI for Codex from API docs, an OpenAPI spec, existing curl examples, an SDK, a web app, an admin tool, or a local script. Use when the user wants Codex to create a command-line tool that can run from any repo, expose composable read\u002Fwrite commands, return stable JSON, manage auth, and pair with a companion skill.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[1024,1027,1030],{"name":1025,"slug":1026,"type":15},"API Development","api-development",{"name":1028,"slug":1029,"type":15},"CLI","cli",{"name":1031,"slug":1032,"type":15},"Codex","codex","2026-04-12T05:07:04.132762",{"slug":1035,"name":1035,"fn":1036,"description":1037,"org":1038,"tags":1039,"stars":998,"repoUrl":999,"updatedAt":1050},"cloudflare-deploy","deploy projects to Cloudflare","Deploy applications and infrastructure to Cloudflare using Workers, Pages, and related platform services. Use when the user asks to deploy, host, publish, or set up a project on Cloudflare.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[1040,1043,1046,1047],{"name":1041,"slug":1042,"type":15},"Cloudflare","cloudflare",{"name":1044,"slug":1045,"type":15},"Cloudflare Pages","cloudflare-pages",{"name":888,"slug":889,"type":15},{"name":1048,"slug":1049,"type":15},"Deployment","deployment","2026-04-12T05:07:14.275118",{"slug":1052,"name":1052,"fn":1053,"description":1054,"org":1055,"tags":1056,"stars":998,"repoUrl":999,"updatedAt":1069},"define-goal","define and set measurable project goals","Help the user define a concrete, measurable goal before starting work, especially when they ask to use the goal tool, create a goal, set an objective, clarify success criteria, or turn a fuzzy intention into a quantitative outcome. Use this skill for goal creation and goal refinement only; it does not manage durable snapshots, decision logs, or long-running execution artifacts.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[1057,1060,1063,1066],{"name":1058,"slug":1059,"type":15},"Productivity","productivity",{"name":1061,"slug":1062,"type":15},"Project Management","project-management",{"name":1064,"slug":1065,"type":15},"Strategy","strategy",{"name":1067,"slug":1068,"type":15},"Task Management","task-management","2026-05-23T06:17:16.870838",{"slug":1071,"name":1071,"fn":1072,"description":1073,"org":1074,"tags":1075,"stars":998,"repoUrl":999,"updatedAt":1081},"figma","translate Figma designs into code","Use the Figma MCP server to fetch design context, screenshots, variables, and assets from Figma, and to translate Figma nodes into production code. Trigger when a task involves Figma URLs, node IDs, design-to-code implementation, or Figma MCP setup and troubleshooting.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[1076,1077,1079,1080],{"name":851,"slug":852,"type":15},{"name":1078,"slug":1071,"type":15},"Figma",{"name":907,"slug":908,"type":15},{"name":1014,"slug":1015,"type":15},"2026-04-12T05:06:47.939943",{"slug":1083,"name":1083,"fn":1084,"description":1085,"org":1086,"tags":1087,"stars":998,"repoUrl":999,"updatedAt":1095},"figma-code-connect-components","connect Figma designs to code components","Connects Figma design components to code components using Code Connect mapping tools. Use when user says \"code connect\", \"connect this component to code\", \"map this component\", \"link component to code\", \"create code connect mapping\", or wants to establish mappings between Figma designs and code implementations. For canvas writes via `use_figma`, use `figma-use`.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[1088,1089,1092,1093,1094],{"name":851,"slug":852,"type":15},{"name":1090,"slug":1091,"type":15},"Design System","design-system",{"name":1078,"slug":1071,"type":15},{"name":907,"slug":908,"type":15},{"name":916,"slug":917,"type":15},"2026-05-10T05:59:52.971881",{"slug":1097,"name":1097,"fn":1098,"description":1099,"org":1100,"tags":1101,"stars":998,"repoUrl":999,"updatedAt":1109},"figma-create-design-system-rules","generate design system rules from Figma","Generates custom design system rules for the user's codebase. Use when user says \"create design system rules\", \"generate rules for my project\", \"set up design rules\", \"customize design system guidelines\", or wants to establish project-specific conventions for Figma-to-code workflows. Requires Figma MCP server connection.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[1102,1103,1104,1107,1108],{"name":851,"slug":852,"type":15},{"name":1090,"slug":1091,"type":15},{"name":1105,"slug":1106,"type":15},"Documentation","documentation",{"name":1078,"slug":1071,"type":15},{"name":907,"slug":908,"type":15},"2026-05-16T06:07:47.821474",{"slug":1111,"name":1111,"fn":1112,"description":1113,"org":1114,"tags":1115,"stars":998,"repoUrl":999,"updatedAt":1121},"figma-implement-design","translate Figma designs into application code","Translates Figma designs into production-ready application code with 1:1 visual fidelity. Use when implementing UI code from Figma files, when user mentions \"implement design\", \"generate code\", \"implement component\", provides Figma URLs, or asks to build components matching Figma specs. For Figma canvas writes via `use_figma`, use `figma-use`.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[1116,1117,1118,1119,1120],{"name":851,"slug":852,"type":15},{"name":1078,"slug":1071,"type":15},{"name":907,"slug":908,"type":15},{"name":916,"slug":917,"type":15},{"name":996,"slug":997,"type":15},"2026-05-16T06:07:40.583615",{"slug":1123,"name":1123,"fn":1124,"description":1125,"org":1126,"tags":1127,"stars":998,"repoUrl":999,"updatedAt":1136},"hatch-pet","create animated pets for Codex","Create, repair, validate, visually QA, and package Codex-compatible animated pets and pet spritesheets from character art, generated images, company or prospect brand cues, or visual references. Use when a user wants a lightweight-worker Codex pet workflow, a non-pixel custom pet style, a prospect or company mascot pet, or a full 8x9 animated pet atlas with transparent unused cells, QA contact sheets, and pet.json packaging. This skill composes the installed $imagegen system skill for visual generation and uses bundled scripts for deterministic spritesheet assembly.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[1128,1131,1132,1135],{"name":1129,"slug":1130,"type":15},"Animation","animation",{"name":1031,"slug":1032,"type":15},{"name":1133,"slug":1134,"type":15},"Creative","creative",{"name":851,"slug":852,"type":15},"2026-05-02T05:31:48.48485",{"slug":1138,"name":1138,"fn":1139,"description":1140,"org":1141,"tags":1142,"stars":998,"repoUrl":999,"updatedAt":1152},"imagegen","generate and edit raster images","Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output should be a bitmap asset rather than repo-native code or vector. Do not use when the task is better handled by editing existing SVG\u002Fvector\u002Fcode-native assets, extending an established icon or logo system, or building the visual directly in HTML\u002FCSS\u002Fcanvas.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[1143,1144,1145,1148,1151],{"name":1133,"slug":1134,"type":15},{"name":851,"slug":852,"type":15},{"name":1146,"slug":1147,"type":15},"Image Generation","image-generation",{"name":1149,"slug":1150,"type":15},"Images","images",{"name":9,"slug":8,"type":15},"2026-05-15T06:23:24.312127",675]