[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill-google-cloud-diligence-playbook":3,"mdc-svl1um-key":39,"related-org-google-cloud-diligence-playbook":294,"related-repo-google-cloud-diligence-playbook":484},{"slug":4,"name":4,"fn":5,"description":6,"org":7,"tags":12,"stars":29,"repoUrl":30,"updatedAt":31,"license":32,"forks":33,"topics":34,"repo":35,"sourceUrl":37,"mdContent":38},"diligence-playbook","perform life sciences M&A diligence","The five life-sciences M&A diligence pillars (scientific, clinical\u002Fregulatory, commercial, financial, deal\u002Frisk), the cash-runway calculation, deal-thesis archetypes, evidence standards, and the red-flag checklist. Load for any acquisition assessment.",{"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",[13,17,20,23,26],{"name":14,"slug":15,"type":16},"Finance","finance","tag",{"name":18,"slug":19,"type":16},"Life Sciences","life-sciences",{"name":21,"slug":22,"type":16},"Regulatory Compliance","regulatory-compliance",{"name":24,"slug":25,"type":16},"Investment Banking","investment-banking",{"name":27,"slug":28,"type":16},"Risk Assessment","risk-assessment",15,"https:\u002F\u002Fgithub.com\u002FGoogleCloudPlatform\u002FLifeSciences","2026-08-19T03:58:59.400651",null,10,[],{"repoUrl":30,"stars":29,"forks":33,"topics":36,"description":32},[],"https:\u002F\u002Fgithub.com\u002FGoogleCloudPlatform\u002FLifeSciences\u002Ftree\u002FHEAD\u002Fapplications\u002Fpharma-on-gemini-enterprise\u002Fargus-on-gemini-enterprise\u002Fapp\u002Fskills\u002Fdiligence-playbook","---\nname: diligence-playbook\ndescription: \"The five life-sciences M&A diligence pillars (scientific, clinical\u002Fregulatory, commercial, financial, deal\u002Frisk), the cash-runway calculation, deal-thesis archetypes, evidence standards, and the red-flag checklist. Load for any acquisition assessment.\"\n---\n\n# Life Sciences M&A Diligence Playbook\n\nDomain methodology for Argus. Load the relevant section based on the user's\nrequest and the mode (quick answer \u002F whitepaper \u002F target screening).\n\n## The five diligence pillars\n\nEvery acquisition assessment covers these. Weight them by deal thesis\n(platform buy vs. single-asset buy vs. commercial-stage tuck-in).\n\n1. **Scientific & Modality** — mechanism of action, target validation, novelty\n   vs. crowded class, platform breadth, IP\u002Ffreedom-to-operate, differentiation\n   vs. standard of care and known competitors.\n2. **Clinical & Regulatory** — pipeline stage, trial design quality, endpoints,\n   readouts\u002Fcatalysts, prior FDA\u002FEMA interactions, breakthrough\u002Ffast-track\u002F\n   orphan designations, CMC\u002Fmanufacturing readiness, safety signals.\n3. **Commercial & Market** — addressable patient population, epidemiology,\n   pricing\u002Freimbursement, competitive landscape, peak-sales potential, launch\n   readiness, existing revenue.\n4. **Financial** — cash & equivalents, quarterly burn, cash runway (months),\n   R&D vs G&A split, debt, dilution history, valuation vs. comparable deals,\n   ownership\u002Finsider stakes.\n5. **Deal & Risk** — patent cliff\u002Fexclusivity timeline, litigation, key-person\n   dependence, partnership\u002Froyalty encumbrances, integration complexity,\n   antitrust, single-asset concentration risk.\n\n## Cash runway (core financial calculation)\n\n- Quarterly net cash burn ≈ |NetCashProvidedByUsedInOperatingActivities| for\n  the quarter (prefer cash-flow statement over net loss).\n- Total liquidity = CashAndCashEquivalents + ShortTermInvestments +\n  MarketableSecuritiesCurrent.\n- Runway (months) ≈ total_liquidity \u002F (quarterly_burn \u002F 3).\n- Flag runway \u003C 18 months as a financing-risk \u002F negotiating-leverage signal.\n- Always use the most recent reported quarterly period available from EDGAR tools\n  as of today's date; do not default to historical cutoff years.\n- Always cite the filing (form + period end) each figure came from.\n\n## Deal-thesis archetypes\n\n- **Platform acquisition**: weight Scientific highest; value the technology's\n  reusability across indications, not one asset.\n- **Single-asset \u002F late-stage**: weight Clinical\u002FRegulatory + Commercial;\n  binary readout risk dominates.\n- **Commercial tuck-in**: weight Financial + Commercial; revenue quality,\n  margins, and channel fit.\n- **Distressed \u002F buy-the-dip**: weight Financial (runway) + Deal\u002FRisk; the\n  edge is timing a financing wall.\n\n## Evidence standards\n\n- Prefer primary sources: SEC filings (via EDGAR tools), regulatory\u002Fscientific\n  databases (via science skills: openFDA, ClinicalTrials.gov, ChEMBL, Open Targets,\n  PubMed), and trial registries.\n- Real-time ground truth: Treat live filing dates, clinical trial updates, and news\n  from recent\u002Fcurrent calendar years as authentic records (never future placeholders\n  or system anomalies).\n- Use Google Search for recent news, deal comps, and catalysts without hardcoding\n  historical cutoff years — but treat it as a lead to confirm against a primary\n  source, not as the citation itself.\n- Every material claim in a whitepaper needs a source. Distinguish fact from\n  inference explicitly.\n- State confidence and gaps. \"Unknown \u002F not disclosed\" is a valid, valuable\n  finding in diligence.\n\n## Red-flag checklist (surface these prominently)\n\n- Cash runway \u003C 12–18 months without a clear financing path.\n- Single asset carrying >70% of the pipeline value.\n- Primary endpoint missed, or trial design that can't support approval.\n- Patent expiry \u002F loss of exclusivity within the investment horizon.\n- Undisclosed safety signals, clinical holds, or CRLs (complete response letters).\n- Heavy royalty\u002Fmilestone obligations to third parties on the lead asset.\n- Going-concern language in the latest 10-K\u002F10-Q.\n",{"data":40,"body":41},{"name":4,"description":6},{"type":42,"children":43},"root",[44,53,59,66,71,127,133,167,173,216,222,250,256],{"type":45,"tag":46,"props":47,"children":49},"element","h1",{"id":48},"life-sciences-ma-diligence-playbook",[50],{"type":51,"value":52},"text","Life Sciences M&A Diligence Playbook",{"type":45,"tag":54,"props":55,"children":56},"p",{},[57],{"type":51,"value":58},"Domain methodology for Argus. Load the relevant section based on the user's\nrequest and the mode (quick answer \u002F whitepaper \u002F target screening).",{"type":45,"tag":60,"props":61,"children":63},"h2",{"id":62},"the-five-diligence-pillars",[64],{"type":51,"value":65},"The five diligence pillars",{"type":45,"tag":54,"props":67,"children":68},{},[69],{"type":51,"value":70},"Every acquisition assessment covers these. Weight them by deal thesis\n(platform buy vs. single-asset buy vs. commercial-stage tuck-in).",{"type":45,"tag":72,"props":73,"children":74},"ol",{},[75,87,97,107,117],{"type":45,"tag":76,"props":77,"children":78},"li",{},[79,85],{"type":45,"tag":80,"props":81,"children":82},"strong",{},[83],{"type":51,"value":84},"Scientific & Modality",{"type":51,"value":86}," — mechanism of action, target validation, novelty\nvs. crowded class, platform breadth, IP\u002Ffreedom-to-operate, differentiation\nvs. standard of care and known competitors.",{"type":45,"tag":76,"props":88,"children":89},{},[90,95],{"type":45,"tag":80,"props":91,"children":92},{},[93],{"type":51,"value":94},"Clinical & Regulatory",{"type":51,"value":96}," — pipeline stage, trial design quality, endpoints,\nreadouts\u002Fcatalysts, prior FDA\u002FEMA interactions, breakthrough\u002Ffast-track\u002F\norphan designations, CMC\u002Fmanufacturing readiness, safety signals.",{"type":45,"tag":76,"props":98,"children":99},{},[100,105],{"type":45,"tag":80,"props":101,"children":102},{},[103],{"type":51,"value":104},"Commercial & Market",{"type":51,"value":106}," — addressable patient population, epidemiology,\npricing\u002Freimbursement, competitive landscape, peak-sales potential, launch\nreadiness, existing revenue.",{"type":45,"tag":76,"props":108,"children":109},{},[110,115],{"type":45,"tag":80,"props":111,"children":112},{},[113],{"type":51,"value":114},"Financial",{"type":51,"value":116}," — cash & equivalents, quarterly burn, cash runway (months),\nR&D vs G&A split, debt, dilution history, valuation vs. comparable deals,\nownership\u002Finsider stakes.",{"type":45,"tag":76,"props":118,"children":119},{},[120,125],{"type":45,"tag":80,"props":121,"children":122},{},[123],{"type":51,"value":124},"Deal & Risk",{"type":51,"value":126}," — patent cliff\u002Fexclusivity timeline, litigation, key-person\ndependence, partnership\u002Froyalty encumbrances, integration complexity,\nantitrust, single-asset concentration risk.",{"type":45,"tag":60,"props":128,"children":130},{"id":129},"cash-runway-core-financial-calculation",[131],{"type":51,"value":132},"Cash runway (core financial calculation)",{"type":45,"tag":134,"props":135,"children":136},"ul",{},[137,142,147,152,157,162],{"type":45,"tag":76,"props":138,"children":139},{},[140],{"type":51,"value":141},"Quarterly net cash burn ≈ |NetCashProvidedByUsedInOperatingActivities| for\nthe quarter (prefer cash-flow statement over net loss).",{"type":45,"tag":76,"props":143,"children":144},{},[145],{"type":51,"value":146},"Total liquidity = CashAndCashEquivalents + ShortTermInvestments +\nMarketableSecuritiesCurrent.",{"type":45,"tag":76,"props":148,"children":149},{},[150],{"type":51,"value":151},"Runway (months) ≈ total_liquidity \u002F (quarterly_burn \u002F 3).",{"type":45,"tag":76,"props":153,"children":154},{},[155],{"type":51,"value":156},"Flag runway \u003C 18 months as a financing-risk \u002F negotiating-leverage signal.",{"type":45,"tag":76,"props":158,"children":159},{},[160],{"type":51,"value":161},"Always use the most recent reported quarterly period available from EDGAR tools\nas of today's date; do not default to historical cutoff years.",{"type":45,"tag":76,"props":163,"children":164},{},[165],{"type":51,"value":166},"Always cite the filing (form + period end) each figure came from.",{"type":45,"tag":60,"props":168,"children":170},{"id":169},"deal-thesis-archetypes",[171],{"type":51,"value":172},"Deal-thesis archetypes",{"type":45,"tag":134,"props":174,"children":175},{},[176,186,196,206],{"type":45,"tag":76,"props":177,"children":178},{},[179,184],{"type":45,"tag":80,"props":180,"children":181},{},[182],{"type":51,"value":183},"Platform acquisition",{"type":51,"value":185},": weight Scientific highest; value the technology's\nreusability across indications, not one asset.",{"type":45,"tag":76,"props":187,"children":188},{},[189,194],{"type":45,"tag":80,"props":190,"children":191},{},[192],{"type":51,"value":193},"Single-asset \u002F late-stage",{"type":51,"value":195},": weight Clinical\u002FRegulatory + Commercial;\nbinary readout risk dominates.",{"type":45,"tag":76,"props":197,"children":198},{},[199,204],{"type":45,"tag":80,"props":200,"children":201},{},[202],{"type":51,"value":203},"Commercial tuck-in",{"type":51,"value":205},": weight Financial + Commercial; revenue quality,\nmargins, and channel fit.",{"type":45,"tag":76,"props":207,"children":208},{},[209,214],{"type":45,"tag":80,"props":210,"children":211},{},[212],{"type":51,"value":213},"Distressed \u002F buy-the-dip",{"type":51,"value":215},": weight Financial (runway) + Deal\u002FRisk; the\nedge is timing a financing wall.",{"type":45,"tag":60,"props":217,"children":219},{"id":218},"evidence-standards",[220],{"type":51,"value":221},"Evidence standards",{"type":45,"tag":134,"props":223,"children":224},{},[225,230,235,240,245],{"type":45,"tag":76,"props":226,"children":227},{},[228],{"type":51,"value":229},"Prefer primary sources: SEC filings (via EDGAR tools), regulatory\u002Fscientific\ndatabases (via science skills: openFDA, ClinicalTrials.gov, ChEMBL, Open Targets,\nPubMed), and trial registries.",{"type":45,"tag":76,"props":231,"children":232},{},[233],{"type":51,"value":234},"Real-time ground truth: Treat live filing dates, clinical trial updates, and news\nfrom recent\u002Fcurrent calendar years as authentic records (never future placeholders\nor system anomalies).",{"type":45,"tag":76,"props":236,"children":237},{},[238],{"type":51,"value":239},"Use Google Search for recent news, deal comps, and catalysts without hardcoding\nhistorical cutoff years — but treat it as a lead to confirm against a primary\nsource, not as the citation itself.",{"type":45,"tag":76,"props":241,"children":242},{},[243],{"type":51,"value":244},"Every material claim in a whitepaper needs a source. Distinguish fact from\ninference explicitly.",{"type":45,"tag":76,"props":246,"children":247},{},[248],{"type":51,"value":249},"State confidence and gaps. \"Unknown \u002F not disclosed\" is a valid, valuable\nfinding in diligence.",{"type":45,"tag":60,"props":251,"children":253},{"id":252},"red-flag-checklist-surface-these-prominently",[254],{"type":51,"value":255},"Red-flag checklist (surface these prominently)",{"type":45,"tag":134,"props":257,"children":258},{},[259,264,269,274,279,284,289],{"type":45,"tag":76,"props":260,"children":261},{},[262],{"type":51,"value":263},"Cash runway \u003C 12–18 months without a clear financing path.",{"type":45,"tag":76,"props":265,"children":266},{},[267],{"type":51,"value":268},"Single asset carrying >70% of the pipeline value.",{"type":45,"tag":76,"props":270,"children":271},{},[272],{"type":51,"value":273},"Primary endpoint missed, or trial design that can't support approval.",{"type":45,"tag":76,"props":275,"children":276},{},[277],{"type":51,"value":278},"Patent expiry \u002F loss of exclusivity within the investment horizon.",{"type":45,"tag":76,"props":280,"children":281},{},[282],{"type":51,"value":283},"Undisclosed safety signals, clinical holds, or CRLs (complete response letters).",{"type":45,"tag":76,"props":285,"children":286},{},[287],{"type":51,"value":288},"Heavy royalty\u002Fmilestone obligations to third parties on the lead asset.",{"type":45,"tag":76,"props":290,"children":291},{},[292],{"type":51,"value":293},"Going-concern language in the latest 10-K\u002F10-Q.",{"items":295,"total":483},[296,314,330,349,360,375,397,411,422,436,453,470],{"slug":297,"name":297,"fn":298,"description":299,"org":300,"tags":301,"stars":311,"repoUrl":312,"updatedAt":313},"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},[302,305,308],{"name":303,"slug":304,"type":16},"Documentation","documentation",{"name":306,"slug":307,"type":16},"Knowledge Base","knowledge-base",{"name":309,"slug":310,"type":16},"Search","search",8409,"https:\u002F\u002Fgithub.com\u002FGoogleCloudPlatform\u002Fknowledge-catalog","2026-07-12T07:38:52.157375",{"slug":315,"name":316,"fn":317,"description":318,"org":319,"tags":320,"stars":311,"repoUrl":312,"updatedAt":329},"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},[321,324,325,328],{"name":322,"slug":323,"type":16},"Data Analysis","data-analysis",{"name":9,"slug":8,"type":16},{"name":326,"slug":327,"type":16},"Knowledge Management","knowledge-management",{"name":309,"slug":310,"type":16},"2026-07-12T07:38:22.196851",{"slug":331,"name":331,"fn":332,"description":333,"org":334,"tags":335,"stars":346,"repoUrl":347,"updatedAt":348},"agent-eval","execute high-performance agent evaluations","Executes high-performance agent evaluations, multi-turn UserSim simulations, and declarative metric grading aligned with google\u002Fagents-cli and the Quality Flywheel. Publishes benchmark artifacts to the GCS Evaluation Registry, executes automated head-to-head delta comparisons (--compare-to), and optimizes system instructions via ADK GEPA (Genetic Evolutionary Prompt Optimization). Use when running agent benchmarks, evaluating ADK\u002FFastAPI agents, diagnosing loss clusters, comparing prompt iterations, running GEPA prompt optimization, or serving evaluation dashboards. Don't use for raw agent code scaffolding (use google-agents-cli-scaffold) or infrastructure deployment (use google-agents-cli-deploy).",{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[336,339,342,345],{"name":337,"slug":338,"type":16},"Agents","agents",{"name":340,"slug":341,"type":16},"Benchmarking","benchmarking",{"name":343,"slug":344,"type":16},"Evals","evals",{"name":9,"slug":8,"type":16},3059,"https:\u002F\u002Fgithub.com\u002FGoogleCloudPlatform\u002Fprofessional-services","2026-08-13T05:04:15.77511",{"slug":350,"name":350,"fn":351,"description":352,"org":353,"tags":354,"stars":346,"repoUrl":347,"updatedAt":359},"agent-eval-workflow","design and run agent evaluation workflows","This skill should be used when the user wants to evaluate an AI agent end-to-end: scaffold an evaluation, design metrics that test a real hypothesis, make an agent measurable, audit generated eval config, read evaluation results, or run an improvement (\"hill climbing\") loop. Covers evaluation methodology, metric design, dataset coverage, reading deterministic vs LLM-judged metrics, and the traps that make eval runs silently measure nothing. Use alongside the tool-specific skills (agents-cli-eval, adk-eval-guide) — those cover commands and schemas, this covers the process and judgement.\n",{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[355,356,357,358],{"name":337,"slug":338,"type":16},{"name":340,"slug":341,"type":16},{"name":343,"slug":344,"type":16},{"name":9,"slug":8,"type":16},"2026-08-13T05:04:18.890378",{"slug":361,"name":361,"fn":362,"description":363,"org":364,"tags":365,"stars":346,"repoUrl":347,"updatedAt":374},"eval-breakdown","diagnose agent evaluation benchmark results","Performs an exhaustive, question-by-question narrative diagnostic breakdown of an agent-eval benchmark run by analyzing question_answer_log.md, eval_summary.json, and raw trajectory traces. Use when diagnosing low score causes, investigating the Memory Reuse vs. Traceability rubric clash, performing pre-release failure audits, or examining judge reasoning across individual scenarios. Don't use for running the benchmark CLI pipeline itself (use agent-eval) or automated genetic prompt tuning (use google-agents-cli-eval).",{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[366,369,372,373],{"name":367,"slug":368,"type":16},"Code Analysis","code-analysis",{"name":370,"slug":371,"type":16},"Debugging","debugging",{"name":343,"slug":344,"type":16},{"name":9,"slug":8,"type":16},"2026-08-13T05:04:18.336276",{"slug":376,"name":376,"fn":377,"description":378,"org":379,"tags":380,"stars":394,"repoUrl":395,"updatedAt":396},"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},[381,384,387,390,391],{"name":382,"slug":383,"type":16},"Automation","automation",{"name":385,"slug":386,"type":16},"Engineering","engineering",{"name":388,"slug":389,"type":16},"GitHub","github",{"name":9,"slug":8,"type":16},{"name":392,"slug":393,"type":16},"Pull Requests","pull-requests",2077,"https:\u002F\u002Fgithub.com\u002FGoogleCloudPlatform\u002Fcloud-foundation-fabric","2026-07-31T06:23:36.935005",{"slug":398,"name":398,"fn":399,"description":400,"org":401,"tags":402,"stars":394,"repoUrl":395,"updatedAt":410},"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},[403,404,407],{"name":9,"slug":8,"type":16},{"name":405,"slug":406,"type":16},"Infrastructure as Code","infrastructure-as-code",{"name":408,"slug":409,"type":16},"Terraform","terraform","2026-08-10T04:16:46.817883",{"slug":412,"name":412,"fn":413,"description":414,"org":415,"tags":416,"stars":394,"repoUrl":395,"updatedAt":421},"fast-prerequisites","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},[417,418],{"name":9,"slug":8,"type":16},{"name":419,"slug":420,"type":16},"Operations","operations","2026-08-06T05:36:21.590622",{"slug":423,"name":423,"fn":424,"description":425,"org":426,"tags":427,"stars":433,"repoUrl":434,"updatedAt":435},"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},[428,431,432],{"name":429,"slug":430,"type":16},"CLI","cli",{"name":385,"slug":386,"type":16},{"name":9,"slug":8,"type":16},1178,"https:\u002F\u002Fgithub.com\u002FGoogleCloudPlatform\u002Fvertex-ai-creative-studio","2026-07-12T07:39:08.41406",{"slug":437,"name":437,"fn":438,"description":439,"org":440,"tags":441,"stars":433,"repoUrl":434,"updatedAt":452},"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},[442,445,446,449],{"name":443,"slug":444,"type":16},"API Development","api-development",{"name":9,"slug":8,"type":16},{"name":447,"slug":448,"type":16},"LLM","llm",{"name":450,"slug":451,"type":16},"MCP","mcp","2026-07-12T07:39:10.911302",{"slug":454,"name":454,"fn":455,"description":456,"org":457,"tags":458,"stars":433,"repoUrl":434,"updatedAt":469},"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},[459,462,465,466],{"name":460,"slug":461,"type":16},"Audio","audio",{"name":463,"slug":464,"type":16},"Creative","creative",{"name":9,"slug":8,"type":16},{"name":467,"slug":468,"type":16},"Vertex AI","vertex-ai","2026-07-12T07:39:16.623879",{"slug":471,"name":471,"fn":472,"description":473,"org":474,"tags":475,"stars":433,"repoUrl":434,"updatedAt":482},"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},[476,477,478,481],{"name":463,"slug":464,"type":16},{"name":9,"slug":8,"type":16},{"name":479,"slug":480,"type":16},"Image Generation","image-generation",{"name":467,"slug":468,"type":16},"2026-07-12T07:39:15.372822",61,{"items":485,"total":565},[486,500,508,520,532,545,555],{"slug":487,"name":487,"fn":488,"description":489,"org":490,"tags":491,"stars":29,"repoUrl":30,"updatedAt":499},"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},[492,495,496],{"name":493,"slug":494,"type":16},"Competitive Intelligence","competitive-intelligence",{"name":18,"slug":19,"type":16},{"name":497,"slug":498,"type":16},"Research","research","2026-07-12T07:40:55.676084",{"slug":4,"name":4,"fn":5,"description":6,"org":501,"tags":502,"stars":29,"repoUrl":30,"updatedAt":31},{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[503,504,505,506,507],{"name":14,"slug":15,"type":16},{"name":24,"slug":25,"type":16},{"name":18,"slug":19,"type":16},{"name":21,"slug":22,"type":16},{"name":27,"slug":28,"type":16},{"slug":509,"name":509,"fn":510,"description":511,"org":512,"tags":513,"stars":29,"repoUrl":30,"updatedAt":519},"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},[514,515,518],{"name":18,"slug":19,"type":16},{"name":516,"slug":517,"type":16},"PubMed","pubmed",{"name":497,"slug":498,"type":16},"2026-07-12T07:40:57.110395",{"slug":521,"name":521,"fn":522,"description":523,"org":524,"tags":525,"stars":29,"repoUrl":30,"updatedAt":531},"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},[526,529,530],{"name":527,"slug":528,"type":16},"Diagrams","diagrams",{"name":18,"slug":19,"type":16},{"name":497,"slug":498,"type":16},"2026-07-12T07:41:01.085638",{"slug":533,"name":533,"fn":534,"description":535,"org":536,"tags":537,"stars":29,"repoUrl":30,"updatedAt":544},"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},[538,541,542,543],{"name":539,"slug":540,"type":16},"Bioinformatics","bioinformatics",{"name":18,"slug":19,"type":16},{"name":516,"slug":517,"type":16},{"name":497,"slug":498,"type":16},"2026-07-12T07:40:59.811387",{"slug":546,"name":546,"fn":547,"description":548,"org":549,"tags":550,"stars":29,"repoUrl":30,"updatedAt":554},"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},[551,552,553],{"name":527,"slug":528,"type":16},{"name":18,"slug":19,"type":16},{"name":497,"slug":498,"type":16},"2026-07-12T07:40:58.359064",{"slug":556,"name":556,"fn":557,"description":558,"org":559,"tags":560,"stars":29,"repoUrl":30,"updatedAt":564},"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},[561,562,563],{"name":539,"slug":540,"type":16},{"name":18,"slug":19,"type":16},{"name":497,"slug":498,"type":16},"2026-07-12T07:40:53.048652",9]