[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill-google-cloud-pico-search-strategy":3,"mdc-vhp9iu-key":36,"related-repo-google-cloud-pico-search-strategy":518,"related-org-google-cloud-pico-search-strategy":582},{"slug":4,"name":4,"fn":5,"description":6,"org":7,"tags":12,"stars":26,"repoUrl":27,"updatedAt":28,"license":29,"forks":30,"topics":31,"repo":32,"sourceUrl":34,"mdContent":35},"pico-search-strategy","translate research questions into PubMed search strategies","Translate a clinical or research question into a PICO\u002FPECO-structured PubMed + Europe PMC search strategy with MeSH terms, field tags, and search hedges. Use whenever the user asks a comparative-effectiveness, etiology, prognosis, diagnosis, or HEOR question, OR when they explicitly ask for a \"search strategy\".",{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},"google-cloud","Google Cloud","https:\u002F\u002Fpexgzepcugksgbtrxkhf.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Forg-logos\u002Fgoogle-cloud.png","GoogleCloudPlatform",[13,17,20,23],{"name":14,"slug":15,"type":16},"Research","research","tag",{"name":18,"slug":19,"type":16},"PubMed","pubmed",{"name":21,"slug":22,"type":16},"Life Sciences","life-sciences",{"name":24,"slug":25,"type":16},"Bioinformatics","bioinformatics",14,"https:\u002F\u002Fgithub.com\u002FGoogleCloudPlatform\u002FLifeSciences","2026-07-12T07:40:59.811387",null,10,[],{"repoUrl":27,"stars":26,"forks":30,"topics":33,"description":29},[],"https:\u002F\u002Fgithub.com\u002FGoogleCloudPlatform\u002FLifeSciences\u002Ftree\u002FHEAD\u002Fapplications\u002Fpharma-on-gemini-enterprise\u002Fbiocompass-on-gemini-enterprise\u002Fapp\u002Fskills\u002Fpico-search-strategy","---\nname: pico-search-strategy\ndescription: Translate a clinical or research question into a PICO\u002FPECO-structured PubMed + Europe PMC search strategy with MeSH terms, field tags, and search hedges. Use whenever the user asks a comparative-effectiveness, etiology, prognosis, diagnosis, or HEOR question, OR when they explicitly ask for a \"search strategy\".\n---\n\n# PICO Search Strategy\n\nYou are constructing a transparent, reproducible literature-search strategy\nfor a pharmaceutical researcher. The goal is to produce a query that another\nanalyst could re-run six months from now and get the same hits.\n\n## Workflow\n\n### 1. Decompose the question into PICO (or PECO for etiology)\n\n| Element | Clinical question | Etiology \u002F safety question |\n|---------|-------------------|----------------------------|\n| **P**   | Population         | Population                 |\n| **I**   | Intervention       | **E**xposure               |\n| **C**   | Comparator         | Comparator (often unexposed) |\n| **O**   | Outcome            | Outcome                    |\n\nRestate the user's question as a single PICO sentence and confirm with them\n*before* running searches if anything is ambiguous (especially the\npopulation — adults vs. pediatric, treatment-naive vs. refractory).\n\n### 2. Build the concept blocks\n\nFor each PICO element, build a concept block that combines:\n\n- **Controlled vocabulary**: MeSH (PubMed) and EMTREE-equivalent terms.\n  Use the `[MeSH]` field tag and explode by default.\n- **Free-text synonyms**: include brand + generic drug names, gene symbols\n  + protein names, and the major spelling variants (US\u002FUK).\n- **Field tags** to control precision: `[Title\u002FAbstract]` for high-precision\n  blocks, no tag for high-recall blocks.\n\nCombine within a block with `OR`, between blocks with `AND`.\n\n### 3. Apply methodologic filters as a separate block\n\nUse validated search hedges rather than ad-hoc filters:\n\n- **Systematic reviews**: `(systematic review[PT] OR meta-analysis[PT])`\n- **RCTs**: append the [Cochrane Highly Sensitive Search Strategy for\n  RCTs](https:\u002F\u002Ftraining.cochrane.org\u002Fhandbook\u002Fcurrent\u002Fchapter-04-supplement-1).\n- **Observational studies**: `(cohort studies[MeSH] OR case-control\n  studies[MeSH] OR observational study[PT])`\n- **Real-world evidence**: combine `(\"real world\"[TIAB] OR \"real-world\"[TIAB]\n  OR registry[TIAB])` with the population block.\n\n### 4. Add date \u002F language \u002F human filters last\n\n- Date: `(\"YYYY\u002FMM\u002FDD\"[PDAT] : \"YYYY\u002FMM\u002FDD\"[PDAT])`. Default to the last 5\n  years for active areas, 10 years for chronic-disease background.\n- Humans: `humans[MeSH]` only when the user wants to exclude in-vitro \u002F\n  animal work.\n- Language: avoid filtering by language unless explicitly requested; doing\n  so introduces selection bias.\n\n### 5. Run + report\n\nAlways report:\n\n- The full PubMed query string verbatim (the user must be able to paste it\n  into PubMed).\n- The hit count.\n- For Europe PMC, the equivalent query in Europe PMC field-tag syntax\n  (TITLE:, ABS:, MESH:, KW:, PUB_YEAR:[YYYY TO YYYY]).\n- A one-paragraph rationale for the trade-offs (why MeSH explosion was\u002Fwas\n  not used, why a particular synonym was included).\n\nIf hits exceed ~500, propose narrowing concept-by-concept; if hits are\nunder ~10, propose loosening the highest-precision block first (typically\nthe outcome).\n\n## Tools to call\n\n- `search_pubmed` for free-text + field-tag queries.\n- `advanced_search` when the request specifies dates, MeSH, journal, or\n  publication type as discrete filters.\n- `search_europe_pmc` for the parallel Europe PMC run (broader coverage).\n\n## What good output looks like\n\nA pharma evidence-generation analyst should be able to take your output,\npaste the query into PubMed and Europe PMC, and confirm the hit count\nmatches yours within a small drift (NCBI updates daily). Include the\nPRISMA-style \"search executed on YYYY-MM-DD\" line.\n",{"data":37,"body":38},{"name":4,"description":6},{"type":39,"children":40},"root",[41,49,55,62,69,190,203,209,214,274,295,301,306,378,384,418,424,429,460,465,471,507,513],{"type":42,"tag":43,"props":44,"children":45},"element","h1",{"id":4},[46],{"type":47,"value":48},"text","PICO Search Strategy",{"type":42,"tag":50,"props":51,"children":52},"p",{},[53],{"type":47,"value":54},"You are constructing a transparent, reproducible literature-search strategy\nfor a pharmaceutical researcher. The goal is to produce a query that another\nanalyst could re-run six months from now and get the same hits.",{"type":42,"tag":56,"props":57,"children":59},"h2",{"id":58},"workflow",[60],{"type":47,"value":61},"Workflow",{"type":42,"tag":63,"props":64,"children":66},"h3",{"id":65},"_1-decompose-the-question-into-pico-or-peco-for-etiology",[67],{"type":47,"value":68},"1. Decompose the question into PICO (or PECO for etiology)",{"type":42,"tag":70,"props":71,"children":72},"table",{},[73,97],{"type":42,"tag":74,"props":75,"children":76},"thead",{},[77],{"type":42,"tag":78,"props":79,"children":80},"tr",{},[81,87,92],{"type":42,"tag":82,"props":83,"children":84},"th",{},[85],{"type":47,"value":86},"Element",{"type":42,"tag":82,"props":88,"children":89},{},[90],{"type":47,"value":91},"Clinical question",{"type":42,"tag":82,"props":93,"children":94},{},[95],{"type":47,"value":96},"Etiology \u002F safety question",{"type":42,"tag":98,"props":99,"children":100},"tbody",{},[101,123,149,170],{"type":42,"tag":78,"props":102,"children":103},{},[104,114,119],{"type":42,"tag":105,"props":106,"children":107},"td",{},[108],{"type":42,"tag":109,"props":110,"children":111},"strong",{},[112],{"type":47,"value":113},"P",{"type":42,"tag":105,"props":115,"children":116},{},[117],{"type":47,"value":118},"Population",{"type":42,"tag":105,"props":120,"children":121},{},[122],{"type":47,"value":118},{"type":42,"tag":78,"props":124,"children":125},{},[126,134,139],{"type":42,"tag":105,"props":127,"children":128},{},[129],{"type":42,"tag":109,"props":130,"children":131},{},[132],{"type":47,"value":133},"I",{"type":42,"tag":105,"props":135,"children":136},{},[137],{"type":47,"value":138},"Intervention",{"type":42,"tag":105,"props":140,"children":141},{},[142,147],{"type":42,"tag":109,"props":143,"children":144},{},[145],{"type":47,"value":146},"E",{"type":47,"value":148},"xposure",{"type":42,"tag":78,"props":150,"children":151},{},[152,160,165],{"type":42,"tag":105,"props":153,"children":154},{},[155],{"type":42,"tag":109,"props":156,"children":157},{},[158],{"type":47,"value":159},"C",{"type":42,"tag":105,"props":161,"children":162},{},[163],{"type":47,"value":164},"Comparator",{"type":42,"tag":105,"props":166,"children":167},{},[168],{"type":47,"value":169},"Comparator (often unexposed)",{"type":42,"tag":78,"props":171,"children":172},{},[173,181,186],{"type":42,"tag":105,"props":174,"children":175},{},[176],{"type":42,"tag":109,"props":177,"children":178},{},[179],{"type":47,"value":180},"O",{"type":42,"tag":105,"props":182,"children":183},{},[184],{"type":47,"value":185},"Outcome",{"type":42,"tag":105,"props":187,"children":188},{},[189],{"type":47,"value":185},{"type":42,"tag":50,"props":191,"children":192},{},[193,195,201],{"type":47,"value":194},"Restate the user's question as a single PICO sentence and confirm with them\n",{"type":42,"tag":196,"props":197,"children":198},"em",{},[199],{"type":47,"value":200},"before",{"type":47,"value":202}," running searches if anything is ambiguous (especially the\npopulation — adults vs. pediatric, treatment-naive vs. refractory).",{"type":42,"tag":63,"props":204,"children":206},{"id":205},"_2-build-the-concept-blocks",[207],{"type":47,"value":208},"2. Build the concept blocks",{"type":42,"tag":50,"props":210,"children":211},{},[212],{"type":47,"value":213},"For each PICO element, build a concept block that combines:",{"type":42,"tag":215,"props":216,"children":217},"ul",{},[218,238,256],{"type":42,"tag":219,"props":220,"children":221},"li",{},[222,227,229,236],{"type":42,"tag":109,"props":223,"children":224},{},[225],{"type":47,"value":226},"Controlled vocabulary",{"type":47,"value":228},": MeSH (PubMed) and EMTREE-equivalent terms.\nUse the ",{"type":42,"tag":230,"props":231,"children":233},"code",{"className":232},[],[234],{"type":47,"value":235},"[MeSH]",{"type":47,"value":237}," field tag and explode by default.",{"type":42,"tag":219,"props":239,"children":240},{},[241,246,248],{"type":42,"tag":109,"props":242,"children":243},{},[244],{"type":47,"value":245},"Free-text synonyms",{"type":47,"value":247},": include brand + generic drug names, gene symbols\n",{"type":42,"tag":215,"props":249,"children":250},{},[251],{"type":42,"tag":219,"props":252,"children":253},{},[254],{"type":47,"value":255},"protein names, and the major spelling variants (US\u002FUK).",{"type":42,"tag":219,"props":257,"children":258},{},[259,264,266,272],{"type":42,"tag":109,"props":260,"children":261},{},[262],{"type":47,"value":263},"Field tags",{"type":47,"value":265}," to control precision: ",{"type":42,"tag":230,"props":267,"children":269},{"className":268},[],[270],{"type":47,"value":271},"[Title\u002FAbstract]",{"type":47,"value":273}," for high-precision\nblocks, no tag for high-recall blocks.",{"type":42,"tag":50,"props":275,"children":276},{},[277,279,285,287,293],{"type":47,"value":278},"Combine within a block with ",{"type":42,"tag":230,"props":280,"children":282},{"className":281},[],[283],{"type":47,"value":284},"OR",{"type":47,"value":286},", between blocks with ",{"type":42,"tag":230,"props":288,"children":290},{"className":289},[],[291],{"type":47,"value":292},"AND",{"type":47,"value":294},".",{"type":42,"tag":63,"props":296,"children":298},{"id":297},"_3-apply-methodologic-filters-as-a-separate-block",[299],{"type":47,"value":300},"3. Apply methodologic filters as a separate block",{"type":42,"tag":50,"props":302,"children":303},{},[304],{"type":47,"value":305},"Use validated search hedges rather than ad-hoc filters:",{"type":42,"tag":215,"props":307,"children":308},{},[309,325,345,360],{"type":42,"tag":219,"props":310,"children":311},{},[312,317,319],{"type":42,"tag":109,"props":313,"children":314},{},[315],{"type":47,"value":316},"Systematic reviews",{"type":47,"value":318},": ",{"type":42,"tag":230,"props":320,"children":322},{"className":321},[],[323],{"type":47,"value":324},"(systematic review[PT] OR meta-analysis[PT])",{"type":42,"tag":219,"props":326,"children":327},{},[328,333,335,344],{"type":42,"tag":109,"props":329,"children":330},{},[331],{"type":47,"value":332},"RCTs",{"type":47,"value":334},": append the ",{"type":42,"tag":336,"props":337,"children":341},"a",{"href":338,"rel":339},"https:\u002F\u002Ftraining.cochrane.org\u002Fhandbook\u002Fcurrent\u002Fchapter-04-supplement-1",[340],"nofollow",[342],{"type":47,"value":343},"Cochrane Highly Sensitive Search Strategy for\nRCTs",{"type":47,"value":294},{"type":42,"tag":219,"props":346,"children":347},{},[348,353,354],{"type":42,"tag":109,"props":349,"children":350},{},[351],{"type":47,"value":352},"Observational studies",{"type":47,"value":318},{"type":42,"tag":230,"props":355,"children":357},{"className":356},[],[358],{"type":47,"value":359},"(cohort studies[MeSH] OR case-control studies[MeSH] OR observational study[PT])",{"type":42,"tag":219,"props":361,"children":362},{},[363,368,370,376],{"type":42,"tag":109,"props":364,"children":365},{},[366],{"type":47,"value":367},"Real-world evidence",{"type":47,"value":369},": combine ",{"type":42,"tag":230,"props":371,"children":373},{"className":372},[],[374],{"type":47,"value":375},"(\"real world\"[TIAB] OR \"real-world\"[TIAB] OR registry[TIAB])",{"type":47,"value":377}," with the population block.",{"type":42,"tag":63,"props":379,"children":381},{"id":380},"_4-add-date-language-human-filters-last",[382],{"type":47,"value":383},"4. Add date \u002F language \u002F human filters last",{"type":42,"tag":215,"props":385,"children":386},{},[387,400,413],{"type":42,"tag":219,"props":388,"children":389},{},[390,392,398],{"type":47,"value":391},"Date: ",{"type":42,"tag":230,"props":393,"children":395},{"className":394},[],[396],{"type":47,"value":397},"(\"YYYY\u002FMM\u002FDD\"[PDAT] : \"YYYY\u002FMM\u002FDD\"[PDAT])",{"type":47,"value":399},". Default to the last 5\nyears for active areas, 10 years for chronic-disease background.",{"type":42,"tag":219,"props":401,"children":402},{},[403,405,411],{"type":47,"value":404},"Humans: ",{"type":42,"tag":230,"props":406,"children":408},{"className":407},[],[409],{"type":47,"value":410},"humans[MeSH]",{"type":47,"value":412}," only when the user wants to exclude in-vitro \u002F\nanimal work.",{"type":42,"tag":219,"props":414,"children":415},{},[416],{"type":47,"value":417},"Language: avoid filtering by language unless explicitly requested; doing\nso introduces selection bias.",{"type":42,"tag":63,"props":419,"children":421},{"id":420},"_5-run-report",[422],{"type":47,"value":423},"5. Run + report",{"type":42,"tag":50,"props":425,"children":426},{},[427],{"type":47,"value":428},"Always report:",{"type":42,"tag":215,"props":430,"children":431},{},[432,437,442,455],{"type":42,"tag":219,"props":433,"children":434},{},[435],{"type":47,"value":436},"The full PubMed query string verbatim (the user must be able to paste it\ninto PubMed).",{"type":42,"tag":219,"props":438,"children":439},{},[440],{"type":47,"value":441},"The hit count.",{"type":42,"tag":219,"props":443,"children":444},{},[445,447,453],{"type":47,"value":446},"For Europe PMC, the equivalent query in Europe PMC field-tag syntax\n(TITLE:, ABS:, MESH:, KW:, PUB_YEAR:",{"type":42,"tag":448,"props":449,"children":450},"span",{},[451],{"type":47,"value":452},"YYYY TO YYYY",{"type":47,"value":454},").",{"type":42,"tag":219,"props":456,"children":457},{},[458],{"type":47,"value":459},"A one-paragraph rationale for the trade-offs (why MeSH explosion was\u002Fwas\nnot used, why a particular synonym was included).",{"type":42,"tag":50,"props":461,"children":462},{},[463],{"type":47,"value":464},"If hits exceed ~500, propose narrowing concept-by-concept; if hits are\nunder ~10, propose loosening the highest-precision block first (typically\nthe outcome).",{"type":42,"tag":56,"props":466,"children":468},{"id":467},"tools-to-call",[469],{"type":47,"value":470},"Tools to call",{"type":42,"tag":215,"props":472,"children":473},{},[474,485,496],{"type":42,"tag":219,"props":475,"children":476},{},[477,483],{"type":42,"tag":230,"props":478,"children":480},{"className":479},[],[481],{"type":47,"value":482},"search_pubmed",{"type":47,"value":484}," for free-text + field-tag queries.",{"type":42,"tag":219,"props":486,"children":487},{},[488,494],{"type":42,"tag":230,"props":489,"children":491},{"className":490},[],[492],{"type":47,"value":493},"advanced_search",{"type":47,"value":495}," when the request specifies dates, MeSH, journal, or\npublication type as discrete filters.",{"type":42,"tag":219,"props":497,"children":498},{},[499,505],{"type":42,"tag":230,"props":500,"children":502},{"className":501},[],[503],{"type":47,"value":504},"search_europe_pmc",{"type":47,"value":506}," for the parallel Europe PMC run (broader coverage).",{"type":42,"tag":56,"props":508,"children":510},{"id":509},"what-good-output-looks-like",[511],{"type":47,"value":512},"What good output looks like",{"type":42,"tag":50,"props":514,"children":515},{},[516],{"type":47,"value":517},"A pharma evidence-generation analyst should be able to take your output,\npaste the query into PubMed and Europe PMC, and confirm the hit count\nmatches yours within a small drift (NCBI updates daily). Include the\nPRISMA-style \"search executed on YYYY-MM-DD\" line.",{"items":519,"total":581},[520,532,542,554,561,571],{"slug":521,"name":521,"fn":522,"description":523,"org":524,"tags":525,"stars":26,"repoUrl":27,"updatedAt":531},"competitive-landscape-scan","scan competitive drug development landscapes","Build a competitor pipeline view for a target \u002F mechanism \u002F indication — who is in the clinic, what phase, what differentiation. Use for BD \u002F portfolio \u002F commercial-strategy questions like \"who else is developing X\" or \"what's the pipeline for indication Y\".",{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[526,529,530],{"name":527,"slug":528,"type":16},"Competitive Intelligence","competitive-intelligence",{"name":21,"slug":22,"type":16},{"name":14,"slug":15,"type":16},"2026-07-12T07:40:55.676084",{"slug":533,"name":533,"fn":534,"description":535,"org":536,"tags":537,"stars":26,"repoUrl":27,"updatedAt":541},"drug-safety-signal-scan","scan drug safety signals","Surface emerging safety signals for a drug or class from PubMed (case reports \u002F letters \u002F RCT AE tables), plus relevant trial AE disclosures. Use for pharmacovigilance triage, medical-affairs safety updates, or competitive risk assessment. NOT a substitute for formal PV systems.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[538,539,540],{"name":21,"slug":22,"type":16},{"name":18,"slug":19,"type":16},{"name":14,"slug":15,"type":16},"2026-07-12T07:40:57.110395",{"slug":543,"name":543,"fn":544,"description":545,"org":546,"tags":547,"stars":26,"repoUrl":27,"updatedAt":553},"mechanism-of-action-explainer","explain drug mechanisms of action","Produce a literature-grounded mechanism-of-action explanation for a drug or drug class — receptor \u002F pathway \u002F downstream effects \u002F clinical relevance — with a Nano Banana Pro diagram and citations. Use for medical-affairs MSL prep, internal training, or when the user asks \"how does drug X work\" or \"what's the MoA of class Y\".",{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[548,551,552],{"name":549,"slug":550,"type":16},"Diagrams","diagrams",{"name":21,"slug":22,"type":16},{"name":14,"slug":15,"type":16},"2026-07-12T07:41:01.085638",{"slug":4,"name":4,"fn":5,"description":6,"org":555,"tags":556,"stars":26,"repoUrl":27,"updatedAt":28},{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[557,558,559,560],{"name":24,"slug":25,"type":16},{"name":21,"slug":22,"type":16},{"name":18,"slug":19,"type":16},{"name":14,"slug":15,"type":16},{"slug":562,"name":562,"fn":563,"description":564,"org":565,"tags":566,"stars":26,"repoUrl":27,"updatedAt":570},"prisma-systematic-review","conduct PRISMA systematic reviews","Run a PRISMA 2020-aligned systematic-review workflow — identification → screening → eligibility → included — with a transparent record of exclusions at each step and a rendered PRISMA flow diagram. Use when the user asks for a systematic review, evidence map, scoping review, or any task that requires a defensible screening audit trail.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[567,568,569],{"name":549,"slug":550,"type":16},{"name":21,"slug":22,"type":16},{"name":14,"slug":15,"type":16},"2026-07-12T07:40:58.359064",{"slug":572,"name":572,"fn":573,"description":574,"org":575,"tags":576,"stars":26,"repoUrl":27,"updatedAt":580},"target-evidence-dossier","build target validation dossiers","Build a target-validation dossier for a gene \u002F protein \u002F pathway — biology, disease association, druggability, existing programs, key publications, trial pipeline, safety signals. Use for early-stage discovery target review, portfolio decisions, or when the user asks \"what do we know about target X\".",{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[577,578,579],{"name":24,"slug":25,"type":16},{"name":21,"slug":22,"type":16},{"name":14,"slug":15,"type":16},"2026-07-12T07:40:53.048652",6,{"items":583,"total":770},[584,602,618,640,654,665,679,696,713,726,742,752],{"slug":585,"name":585,"fn":586,"description":587,"org":588,"tags":589,"stars":599,"repoUrl":600,"updatedAt":601},"kb-search","search and extract local knowledge base documents","Allows listing, searching and extracting information from local knowledge base documents for information about tables\n",{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[590,593,596],{"name":591,"slug":592,"type":16},"Documentation","documentation",{"name":594,"slug":595,"type":16},"Knowledge Base","knowledge-base",{"name":597,"slug":598,"type":16},"Search","search",6749,"https:\u002F\u002Fgithub.com\u002FGoogleCloudPlatform\u002Fknowledge-catalog","2026-07-12T07:38:52.157375",{"slug":603,"name":604,"fn":605,"description":606,"org":607,"tags":608,"stars":599,"repoUrl":600,"updatedAt":617},"knowledgecatalogdiscoveryagent","knowledge_catalog_discovery_agent","search and rank Knowledge Catalog data entries","Analyzes user queries, extracts relevant predicates, and utilizes Knowledge Catalog Search to find and rank the most relevant data entries. Engages with the user throughout the process.\n",{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[609,612,613,616],{"name":610,"slug":611,"type":16},"Data Analysis","data-analysis",{"name":9,"slug":8,"type":16},{"name":614,"slug":615,"type":16},"Knowledge Management","knowledge-management",{"name":597,"slug":598,"type":16},"2026-07-12T07:38:22.196851",{"slug":619,"name":619,"fn":620,"description":621,"org":622,"tags":623,"stars":637,"repoUrl":638,"updatedAt":639},"contributing","contribute to Cloud Foundation Fabric","End-to-end workflow for contributing to Cloud Foundation Fabric: triaging GitHub issues, proactive feature development, validating with tests and Policy Troubleshooter, and submitting sanitized Pull Requests. Use when addressing a Fabric GitHub issue, developing a module or FAST stage change, or preparing a branch for a pull request.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[624,627,630,633,634],{"name":625,"slug":626,"type":16},"Automation","automation",{"name":628,"slug":629,"type":16},"Engineering","engineering",{"name":631,"slug":632,"type":16},"GitHub","github",{"name":9,"slug":8,"type":16},{"name":635,"slug":636,"type":16},"Pull Requests","pull-requests",2062,"https:\u002F\u002Fgithub.com\u002FGoogleCloudPlatform\u002Fcloud-foundation-fabric","2026-07-31T06:23:36.935005",{"slug":641,"name":641,"fn":642,"description":643,"org":644,"tags":645,"stars":637,"repoUrl":638,"updatedAt":653},"fabric-builder","generate Terraform code for Google Cloud","Generates idiomatic Cloud Foundation Fabric (CFF) Terraform code using CFF modules. Use when users ask to create GCP resources, use Fabric modules, or generate Terraform code for Google Cloud.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[646,647,650],{"name":9,"slug":8,"type":16},{"name":648,"slug":649,"type":16},"Infrastructure as Code","infrastructure-as-code",{"name":651,"slug":652,"type":16},"Terraform","terraform","2026-07-12T07:38:23.514555",{"slug":655,"name":655,"fn":656,"description":657,"org":658,"tags":659,"stars":637,"repoUrl":638,"updatedAt":664},"fast-0-org-setup-prereqs","prepare prerequisites for FAST 0-org-setup","Guides the user step-by-step through the prerequisites for the FAST 0-org-setup stage, supporting both Standard GCP and Google Cloud Dedicated (GCD) environments. Use when a user asks to prepare or run prerequisites for 0-org-setup or bootstrap the FAST landing zone.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[660,661],{"name":9,"slug":8,"type":16},{"name":662,"slug":663,"type":16},"Operations","operations","2026-07-12T07:38:28.127148",{"slug":666,"name":666,"fn":667,"description":668,"org":669,"tags":670,"stars":676,"repoUrl":677,"updatedAt":678},"agent-aware-cli","design agent-aware command-line interfaces","Guide for designing and implementing command-line interfaces (CLIs) that are equally usable by human developers and automated coding agents. Use when the user wants to build a CLI, apply CLI best practices, or use Go with Cobra and Viper.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[671,674,675],{"name":672,"slug":673,"type":16},"CLI","cli",{"name":628,"slug":629,"type":16},{"name":9,"slug":8,"type":16},1150,"https:\u002F\u002Fgithub.com\u002FGoogleCloudPlatform\u002Fvertex-ai-creative-studio","2026-07-12T07:39:08.41406",{"slug":680,"name":680,"fn":681,"description":682,"org":683,"tags":684,"stars":676,"repoUrl":677,"updatedAt":695},"build-mcp-genmedia","build and configure GenAI MCP servers","Builds the mcp-genmedia Go MCP servers (nanobanana, veo, lyria, gemini-multimodal, chirp3-hd, avtool) from source and wires them into settings.json. Use this skill whenever the MCP tools are missing or broken — typically at the start of a new session, after a container restart, or when \u002Ftmp has been wiped. The prebuilt binaries in \u002Fworkspace\u002F.local\u002Fbin\u002F have no exec bit and live on a noexec mount; this skill compiles fresh executables into \u002Ftmp\u002Fbin\u002F where execution is allowed.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[685,688,689,692],{"name":686,"slug":687,"type":16},"API Development","api-development",{"name":9,"slug":8,"type":16},{"name":690,"slug":691,"type":16},"LLM","llm",{"name":693,"slug":694,"type":16},"MCP","mcp","2026-07-12T07:39:10.911302",{"slug":697,"name":697,"fn":698,"description":699,"org":700,"tags":701,"stars":676,"repoUrl":677,"updatedAt":712},"genmedia-audio-engineer","synthesize and mix audio content","Expert in audio synthesis, music generation, and mixing. Use when creating podcasts, background scores, or multi-track audio layering using mcp-chirp3-go, mcp-lyria-go, mcp-gemini-go, mcp-nanobanana-go, and mcp-avtool-go.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[702,705,708,709],{"name":703,"slug":704,"type":16},"Audio","audio",{"name":706,"slug":707,"type":16},"Creative","creative",{"name":9,"slug":8,"type":16},{"name":710,"slug":711,"type":16},"Vertex AI","vertex-ai","2026-07-12T07:39:16.623879",{"slug":714,"name":714,"fn":715,"description":716,"org":717,"tags":718,"stars":676,"repoUrl":677,"updatedAt":725},"genmedia-image-artist","generate and edit AI images","Expert in AI image generation and editing. Use when the user needs high-quality textures, character-consistent visuals, or image-to-image editing using mcp-nanobanana-go.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[719,720,721,724],{"name":706,"slug":707,"type":16},{"name":9,"slug":8,"type":16},{"name":722,"slug":723,"type":16},"Image Generation","image-generation",{"name":710,"slug":711,"type":16},"2026-07-12T07:39:15.372822",{"slug":727,"name":727,"fn":728,"description":729,"org":730,"tags":731,"stars":676,"repoUrl":677,"updatedAt":741},"genmedia-producer","produce multi-step media content","Expert media production assistant. Use when requested to help with storyboarding, podcast creation, audio assembly, or complex multi-step media workflows using the GenMedia MCP servers (Veo, Lyria, Gemini TTS, NanoBanana).",{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[732,733,734,735,738],{"name":703,"slug":704,"type":16},{"name":706,"slug":707,"type":16},{"name":9,"slug":8,"type":16},{"name":736,"slug":737,"type":16},"Media","media",{"name":739,"slug":740,"type":16},"Video","video","2026-07-12T07:39:09.672849",{"slug":743,"name":743,"fn":744,"description":745,"org":746,"tags":747,"stars":676,"repoUrl":677,"updatedAt":751},"genmedia-video-editor","edit and compose video content","Expert in video composition, editing, and format conversion. Use when the user wants to generate high-quality video, overlay images on video, concatenate clips, create GIFs, or sync audio to video using mcp-avtool-go and mcp-veo-go.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[748,749,750],{"name":706,"slug":707,"type":16},{"name":9,"slug":8,"type":16},{"name":739,"slug":740,"type":16},"2026-07-12T07:39:13.749081",{"slug":753,"name":753,"fn":754,"description":755,"org":756,"tags":757,"stars":676,"repoUrl":677,"updatedAt":769},"genmedia-voice-director","generate expressive text-to-speech with Gemini","Expert in casting, directing, and generating expressive text-to-speech using Gemini TTS. Use this when the user needs virtual voice actor personas, expressive speech generation, or multiple variations of a voiceover (like \"take 3 on the bounce\").",{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[758,759,760,763,766],{"name":703,"slug":704,"type":16},{"name":706,"slug":707,"type":16},{"name":761,"slug":762,"type":16},"Gemini","gemini",{"name":764,"slug":765,"type":16},"Speech","speech",{"name":767,"slug":768,"type":16},"Text-to-Speech","text-to-speech","2026-07-12T07:39:17.86673",80]