[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill-google-cloud-drug-safety-signal-scan":3,"mdc--9ghfpe-key":33,"related-org-google-cloud-drug-safety-signal-scan":413,"related-repo-google-cloud-drug-safety-signal-scan":602},{"slug":4,"name":4,"fn":5,"description":6,"org":7,"tags":12,"stars":23,"repoUrl":24,"updatedAt":25,"license":26,"forks":27,"topics":28,"repo":29,"sourceUrl":31,"mdContent":32},"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},"google-cloud","Google Cloud","https:\u002F\u002Fpexgzepcugksgbtrxkhf.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Forg-logos\u002Fgoogle-cloud.png","GoogleCloudPlatform",[13,17,20],{"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",14,"https:\u002F\u002Fgithub.com\u002FGoogleCloudPlatform\u002FLifeSciences","2026-07-12T07:40:57.110395",null,10,[],{"repoUrl":24,"stars":23,"forks":27,"topics":30,"description":26},[],"https:\u002F\u002Fgithub.com\u002FGoogleCloudPlatform\u002FLifeSciences\u002Ftree\u002FHEAD\u002Fapplications\u002Fpharma-on-gemini-enterprise\u002Fbiocompass-on-gemini-enterprise\u002Fapp\u002Fskills\u002Fdrug-safety-signal-scan","---\nname: drug-safety-signal-scan\ndescription: 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.\n---\n\n# Drug Safety Signal Scan\n\nYou are doing rapid pharmacovigilance triage for a pharma medical-affairs\nor PV scientist. The audience needs a fast read on whether the literature\nis signaling a new or evolving safety concern — they will follow up with\ntheir formal PV systems, this is the upstream early-warning step.\n\n## Workflow\n\n### 1. Disambiguate the drug\n\nCall `lookup_entity_id` with `concept=\"chemical\"` to nail the canonical\nID. Note synonyms — case reports often use brand or chemical name only.\n\nIf the request is for a class (e.g. \"PI3K inhibitors\", \"JAK inhibitors\"),\ntreat the class as the subject and run the workflow for each leading\nclass member, then pool the signals at the end.\n\n### 2. Pull the literature signal sources\n\nRun these in parallel via `DeepResearchPipeline` with a request like:\n\n> \"Surface adverse events, safety signals, case reports, and post-marketing\n> findings for \u003Cdrug> from the last 24 months. Include all trial reports,\n> case reports, letters, editorials, and review articles. Pay attention\n> to organ-class events not in the original label.\"\n\nOr run individually:\n\n- `advanced_search` with `publication_types=[\"case reports\", \"letter\"]`\n  + the drug name + date filter for last 24 months.\n- `search_pubmed` for `\"\u003Cdrug> AND adverse\"` and `\"\u003Cdrug> AND\n  toxicity\"`.\n- `search_clinical_trials` with `intervention=\u003Cdrug>` + `status=COMPLETED`\n  to find recently completed trials whose AE tables may reveal new\n  signals.\n\n### 3. Use entity analysis to extract organ-class events\n\nFor each retrieved article (especially case reports), call\n`annotate_articles` to extract the disease entities mentioned. Group the\nmentioned diseases by organ class (cardiac, hepatic, renal, neurologic,\nhematologic, immune-mediated, dermatologic, GI, endocrine, ocular).\n\nA signal is interesting when:\n\n- A new organ class appears that is not on the current label.\n- The frequency of an existing labeled AE appears to be increasing in\n  recent reports.\n- A pattern of severe outcomes (hospitalization, death) clusters in\n  recent reports.\n- Multiple independent groups report the same AE within a short window.\n\n### 4. Cross-check against the existing label\n\nAsk the user whether they have current label text handy; if not, search\nthe literature for the most recent FDA label update or boxed-warning\naddition (`search_pubmed` for `\"\u003Cdrug> AND label change\"` or\n`\"\u003Cdrug> AND boxed warning\"`).\n\nTag each candidate signal as:\n\n- **Labeled** — already in the current Warnings\u002FPrecautions\u002FAEs section.\n- **Updated** — labeled but the recent literature increases concern\n  (severity, frequency, or specific subpopulations).\n- **Novel** — not on the label as far as the literature suggests.\n\n### 5. Output\n\n```\n# Safety signal scan — \u003Cdrug>\nScan date: YYYY-MM-DD | Window: last 24 months | Sources: PubMed + ClinicalTrials.gov\n\n## Top-of-mind signals\n| Signal | Status (labeled \u002F updated \u002F novel) | # reports | Severity | Key refs |\n|--------|------------------------------------|-----------|----------|----------|\n\n## Organ-class summary\n- Cardiac: ... (PMIDs)\n- Hepatic: ...\n- ... (only include classes with hits)\n\n## Trial-disclosed AEs of note\n- NCT##### (sponsor, phase, completion date) — AE finding (1 line)\n\n## What this is and isn't\nThis is a literature-first signal scan — it does not replace formal PV\nsystems (FAERS, EudraVigilance, sponsor PSURs). Use as the upstream\ntrigger for a formal PV review.\n```\n\n### 6. Optional figure\n\nCall `visualize_concept` with `figure_type=\"infographic\"` for an\norgan-class signal heatmap — colored cells per organ class, intensity by\nreport count. Useful for SAB or governance-meeting slides.\n\n## Guardrails\n\n- A *case report* is hypothesis-generating, not causal evidence. Flag the\n  level-of-evidence on every signal.\n- Do not aggregate AE rates across heterogeneous studies as if they were\n  comparable.\n- Class-effect attribution is hard — distinguish \"reported with this\n  drug\" from \"established class effect\".\n- This skill cannot access FAERS \u002F EudraVigilance directly; if the user\n  needs those, route them to their PV team or the openFDA API (not yet\n  wired into this agent).\n",{"data":34,"body":35},{"name":4,"description":6},{"type":36,"children":37},"root",[38,46,52,59,66,88,93,99,112,127,132,214,220,233,238,261,267,294,299,333,339,351,357,376,382],{"type":39,"tag":40,"props":41,"children":42},"element","h1",{"id":4},[43],{"type":44,"value":45},"text","Drug Safety Signal Scan",{"type":39,"tag":47,"props":48,"children":49},"p",{},[50],{"type":44,"value":51},"You are doing rapid pharmacovigilance triage for a pharma medical-affairs\nor PV scientist. The audience needs a fast read on whether the literature\nis signaling a new or evolving safety concern — they will follow up with\ntheir formal PV systems, this is the upstream early-warning step.",{"type":39,"tag":53,"props":54,"children":56},"h2",{"id":55},"workflow",[57],{"type":44,"value":58},"Workflow",{"type":39,"tag":60,"props":61,"children":63},"h3",{"id":62},"_1-disambiguate-the-drug",[64],{"type":44,"value":65},"1. Disambiguate the drug",{"type":39,"tag":47,"props":67,"children":68},{},[69,71,78,80,86],{"type":44,"value":70},"Call ",{"type":39,"tag":72,"props":73,"children":75},"code",{"className":74},[],[76],{"type":44,"value":77},"lookup_entity_id",{"type":44,"value":79}," with ",{"type":39,"tag":72,"props":81,"children":83},{"className":82},[],[84],{"type":44,"value":85},"concept=\"chemical\"",{"type":44,"value":87}," to nail the canonical\nID. Note synonyms — case reports often use brand or chemical name only.",{"type":39,"tag":47,"props":89,"children":90},{},[91],{"type":44,"value":92},"If the request is for a class (e.g. \"PI3K inhibitors\", \"JAK inhibitors\"),\ntreat the class as the subject and run the workflow for each leading\nclass member, then pool the signals at the end.",{"type":39,"tag":60,"props":94,"children":96},{"id":95},"_2-pull-the-literature-signal-sources",[97],{"type":44,"value":98},"2. Pull the literature signal sources",{"type":39,"tag":47,"props":100,"children":101},{},[102,104,110],{"type":44,"value":103},"Run these in parallel via ",{"type":39,"tag":72,"props":105,"children":107},{"className":106},[],[108],{"type":44,"value":109},"DeepResearchPipeline",{"type":44,"value":111}," with a request like:",{"type":39,"tag":113,"props":114,"children":115},"blockquote",{},[116],{"type":39,"tag":47,"props":117,"children":118},{},[119,121],{"type":44,"value":120},"\"Surface adverse events, safety signals, case reports, and post-marketing\nfindings for ",{"type":39,"tag":122,"props":123,"children":124},"drug",{},[125],{"type":44,"value":126}," from the last 24 months. Include all trial reports,\ncase reports, letters, editorials, and review articles. Pay attention\nto organ-class events not in the original label.\"",{"type":39,"tag":47,"props":128,"children":129},{},[130],{"type":44,"value":131},"Or run individually:",{"type":39,"tag":133,"props":134,"children":135},"ul",{},[136,161,188],{"type":39,"tag":137,"props":138,"children":139},"li",{},[140,146,147,153],{"type":39,"tag":72,"props":141,"children":143},{"className":142},[],[144],{"type":44,"value":145},"advanced_search",{"type":44,"value":79},{"type":39,"tag":72,"props":148,"children":150},{"className":149},[],[151],{"type":44,"value":152},"publication_types=[\"case reports\", \"letter\"]",{"type":39,"tag":133,"props":154,"children":155},{},[156],{"type":39,"tag":137,"props":157,"children":158},{},[159],{"type":44,"value":160},"the drug name + date filter for last 24 months.",{"type":39,"tag":137,"props":162,"children":163},{},[164,170,172,178,180,186],{"type":39,"tag":72,"props":165,"children":167},{"className":166},[],[168],{"type":44,"value":169},"search_pubmed",{"type":44,"value":171}," for ",{"type":39,"tag":72,"props":173,"children":175},{"className":174},[],[176],{"type":44,"value":177},"\"\u003Cdrug> AND adverse\"",{"type":44,"value":179}," and ",{"type":39,"tag":72,"props":181,"children":183},{"className":182},[],[184],{"type":44,"value":185},"\"\u003Cdrug> AND toxicity\"",{"type":44,"value":187},".",{"type":39,"tag":137,"props":189,"children":190},{},[191,197,198,204,206,212],{"type":39,"tag":72,"props":192,"children":194},{"className":193},[],[195],{"type":44,"value":196},"search_clinical_trials",{"type":44,"value":79},{"type":39,"tag":72,"props":199,"children":201},{"className":200},[],[202],{"type":44,"value":203},"intervention=\u003Cdrug>",{"type":44,"value":205}," + ",{"type":39,"tag":72,"props":207,"children":209},{"className":208},[],[210],{"type":44,"value":211},"status=COMPLETED",{"type":44,"value":213},"\nto find recently completed trials whose AE tables may reveal new\nsignals.",{"type":39,"tag":60,"props":215,"children":217},{"id":216},"_3-use-entity-analysis-to-extract-organ-class-events",[218],{"type":44,"value":219},"3. Use entity analysis to extract organ-class events",{"type":39,"tag":47,"props":221,"children":222},{},[223,225,231],{"type":44,"value":224},"For each retrieved article (especially case reports), call\n",{"type":39,"tag":72,"props":226,"children":228},{"className":227},[],[229],{"type":44,"value":230},"annotate_articles",{"type":44,"value":232}," to extract the disease entities mentioned. Group the\nmentioned diseases by organ class (cardiac, hepatic, renal, neurologic,\nhematologic, immune-mediated, dermatologic, GI, endocrine, ocular).",{"type":39,"tag":47,"props":234,"children":235},{},[236],{"type":44,"value":237},"A signal is interesting when:",{"type":39,"tag":133,"props":239,"children":240},{},[241,246,251,256],{"type":39,"tag":137,"props":242,"children":243},{},[244],{"type":44,"value":245},"A new organ class appears that is not on the current label.",{"type":39,"tag":137,"props":247,"children":248},{},[249],{"type":44,"value":250},"The frequency of an existing labeled AE appears to be increasing in\nrecent reports.",{"type":39,"tag":137,"props":252,"children":253},{},[254],{"type":44,"value":255},"A pattern of severe outcomes (hospitalization, death) clusters in\nrecent reports.",{"type":39,"tag":137,"props":257,"children":258},{},[259],{"type":44,"value":260},"Multiple independent groups report the same AE within a short window.",{"type":39,"tag":60,"props":262,"children":264},{"id":263},"_4-cross-check-against-the-existing-label",[265],{"type":44,"value":266},"4. Cross-check against the existing label",{"type":39,"tag":47,"props":268,"children":269},{},[270,272,277,278,284,286,292],{"type":44,"value":271},"Ask the user whether they have current label text handy; if not, search\nthe literature for the most recent FDA label update or boxed-warning\naddition (",{"type":39,"tag":72,"props":273,"children":275},{"className":274},[],[276],{"type":44,"value":169},{"type":44,"value":171},{"type":39,"tag":72,"props":279,"children":281},{"className":280},[],[282],{"type":44,"value":283},"\"\u003Cdrug> AND label change\"",{"type":44,"value":285}," or\n",{"type":39,"tag":72,"props":287,"children":289},{"className":288},[],[290],{"type":44,"value":291},"\"\u003Cdrug> AND boxed warning\"",{"type":44,"value":293},").",{"type":39,"tag":47,"props":295,"children":296},{},[297],{"type":44,"value":298},"Tag each candidate signal as:",{"type":39,"tag":133,"props":300,"children":301},{},[302,313,323],{"type":39,"tag":137,"props":303,"children":304},{},[305,311],{"type":39,"tag":306,"props":307,"children":308},"strong",{},[309],{"type":44,"value":310},"Labeled",{"type":44,"value":312}," — already in the current Warnings\u002FPrecautions\u002FAEs section.",{"type":39,"tag":137,"props":314,"children":315},{},[316,321],{"type":39,"tag":306,"props":317,"children":318},{},[319],{"type":44,"value":320},"Updated",{"type":44,"value":322}," — labeled but the recent literature increases concern\n(severity, frequency, or specific subpopulations).",{"type":39,"tag":137,"props":324,"children":325},{},[326,331],{"type":39,"tag":306,"props":327,"children":328},{},[329],{"type":44,"value":330},"Novel",{"type":44,"value":332}," — not on the label as far as the literature suggests.",{"type":39,"tag":60,"props":334,"children":336},{"id":335},"_5-output",[337],{"type":44,"value":338},"5. Output",{"type":39,"tag":340,"props":341,"children":345},"pre",{"className":342,"code":344,"language":44},[343],"language-text","# Safety signal scan — \u003Cdrug>\nScan date: YYYY-MM-DD | Window: last 24 months | Sources: PubMed + ClinicalTrials.gov\n\n## Top-of-mind signals\n| Signal | Status (labeled \u002F updated \u002F novel) | # reports | Severity | Key refs |\n|--------|------------------------------------|-----------|----------|----------|\n\n## Organ-class summary\n- Cardiac: ... (PMIDs)\n- Hepatic: ...\n- ... (only include classes with hits)\n\n## Trial-disclosed AEs of note\n- NCT##### (sponsor, phase, completion date) — AE finding (1 line)\n\n## What this is and isn't\nThis is a literature-first signal scan — it does not replace formal PV\nsystems (FAERS, EudraVigilance, sponsor PSURs). Use as the upstream\ntrigger for a formal PV review.\n",[346],{"type":39,"tag":72,"props":347,"children":349},{"__ignoreMap":348},"",[350],{"type":44,"value":344},{"type":39,"tag":60,"props":352,"children":354},{"id":353},"_6-optional-figure",[355],{"type":44,"value":356},"6. Optional figure",{"type":39,"tag":47,"props":358,"children":359},{},[360,361,367,368,374],{"type":44,"value":70},{"type":39,"tag":72,"props":362,"children":364},{"className":363},[],[365],{"type":44,"value":366},"visualize_concept",{"type":44,"value":79},{"type":39,"tag":72,"props":369,"children":371},{"className":370},[],[372],{"type":44,"value":373},"figure_type=\"infographic\"",{"type":44,"value":375}," for an\norgan-class signal heatmap — colored cells per organ class, intensity by\nreport count. Useful for SAB or governance-meeting slides.",{"type":39,"tag":53,"props":377,"children":379},{"id":378},"guardrails",[380],{"type":44,"value":381},"Guardrails",{"type":39,"tag":133,"props":383,"children":384},{},[385,398,403,408],{"type":39,"tag":137,"props":386,"children":387},{},[388,390,396],{"type":44,"value":389},"A ",{"type":39,"tag":391,"props":392,"children":393},"em",{},[394],{"type":44,"value":395},"case report",{"type":44,"value":397}," is hypothesis-generating, not causal evidence. Flag the\nlevel-of-evidence on every signal.",{"type":39,"tag":137,"props":399,"children":400},{},[401],{"type":44,"value":402},"Do not aggregate AE rates across heterogeneous studies as if they were\ncomparable.",{"type":39,"tag":137,"props":404,"children":405},{},[406],{"type":44,"value":407},"Class-effect attribution is hard — distinguish \"reported with this\ndrug\" from \"established class effect\".",{"type":39,"tag":137,"props":409,"children":410},{},[411],{"type":44,"value":412},"This skill cannot access FAERS \u002F EudraVigilance directly; if the user\nneeds those, route them to their PV team or the openFDA API (not yet\nwired into this agent).",{"items":414,"total":601},[415,433,449,471,485,496,510,527,544,557,573,583],{"slug":416,"name":416,"fn":417,"description":418,"org":419,"tags":420,"stars":430,"repoUrl":431,"updatedAt":432},"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},[421,424,427],{"name":422,"slug":423,"type":16},"Documentation","documentation",{"name":425,"slug":426,"type":16},"Knowledge Base","knowledge-base",{"name":428,"slug":429,"type":16},"Search","search",6749,"https:\u002F\u002Fgithub.com\u002FGoogleCloudPlatform\u002Fknowledge-catalog","2026-07-12T07:38:52.157375",{"slug":434,"name":435,"fn":436,"description":437,"org":438,"tags":439,"stars":430,"repoUrl":431,"updatedAt":448},"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},[440,443,444,447],{"name":441,"slug":442,"type":16},"Data Analysis","data-analysis",{"name":9,"slug":8,"type":16},{"name":445,"slug":446,"type":16},"Knowledge Management","knowledge-management",{"name":428,"slug":429,"type":16},"2026-07-12T07:38:22.196851",{"slug":450,"name":450,"fn":451,"description":452,"org":453,"tags":454,"stars":468,"repoUrl":469,"updatedAt":470},"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},[455,458,461,464,465],{"name":456,"slug":457,"type":16},"Automation","automation",{"name":459,"slug":460,"type":16},"Engineering","engineering",{"name":462,"slug":463,"type":16},"GitHub","github",{"name":9,"slug":8,"type":16},{"name":466,"slug":467,"type":16},"Pull Requests","pull-requests",2062,"https:\u002F\u002Fgithub.com\u002FGoogleCloudPlatform\u002Fcloud-foundation-fabric","2026-07-31T06:23:36.935005",{"slug":472,"name":472,"fn":473,"description":474,"org":475,"tags":476,"stars":468,"repoUrl":469,"updatedAt":484},"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},[477,478,481],{"name":9,"slug":8,"type":16},{"name":479,"slug":480,"type":16},"Infrastructure as Code","infrastructure-as-code",{"name":482,"slug":483,"type":16},"Terraform","terraform","2026-07-12T07:38:23.514555",{"slug":486,"name":486,"fn":487,"description":488,"org":489,"tags":490,"stars":468,"repoUrl":469,"updatedAt":495},"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},[491,492],{"name":9,"slug":8,"type":16},{"name":493,"slug":494,"type":16},"Operations","operations","2026-07-12T07:38:28.127148",{"slug":497,"name":497,"fn":498,"description":499,"org":500,"tags":501,"stars":507,"repoUrl":508,"updatedAt":509},"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},[502,505,506],{"name":503,"slug":504,"type":16},"CLI","cli",{"name":459,"slug":460,"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":511,"name":511,"fn":512,"description":513,"org":514,"tags":515,"stars":507,"repoUrl":508,"updatedAt":526},"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},[516,519,520,523],{"name":517,"slug":518,"type":16},"API Development","api-development",{"name":9,"slug":8,"type":16},{"name":521,"slug":522,"type":16},"LLM","llm",{"name":524,"slug":525,"type":16},"MCP","mcp","2026-07-12T07:39:10.911302",{"slug":528,"name":528,"fn":529,"description":530,"org":531,"tags":532,"stars":507,"repoUrl":508,"updatedAt":543},"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},[533,536,539,540],{"name":534,"slug":535,"type":16},"Audio","audio",{"name":537,"slug":538,"type":16},"Creative","creative",{"name":9,"slug":8,"type":16},{"name":541,"slug":542,"type":16},"Vertex AI","vertex-ai","2026-07-12T07:39:16.623879",{"slug":545,"name":545,"fn":546,"description":547,"org":548,"tags":549,"stars":507,"repoUrl":508,"updatedAt":556},"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},[550,551,552,555],{"name":537,"slug":538,"type":16},{"name":9,"slug":8,"type":16},{"name":553,"slug":554,"type":16},"Image Generation","image-generation",{"name":541,"slug":542,"type":16},"2026-07-12T07:39:15.372822",{"slug":558,"name":558,"fn":559,"description":560,"org":561,"tags":562,"stars":507,"repoUrl":508,"updatedAt":572},"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},[563,564,565,566,569],{"name":534,"slug":535,"type":16},{"name":537,"slug":538,"type":16},{"name":9,"slug":8,"type":16},{"name":567,"slug":568,"type":16},"Media","media",{"name":570,"slug":571,"type":16},"Video","video","2026-07-12T07:39:09.672849",{"slug":574,"name":574,"fn":575,"description":576,"org":577,"tags":578,"stars":507,"repoUrl":508,"updatedAt":582},"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},[579,580,581],{"name":537,"slug":538,"type":16},{"name":9,"slug":8,"type":16},{"name":570,"slug":571,"type":16},"2026-07-12T07:39:13.749081",{"slug":584,"name":584,"fn":585,"description":586,"org":587,"tags":588,"stars":507,"repoUrl":508,"updatedAt":600},"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},[589,590,591,594,597],{"name":534,"slug":535,"type":16},{"name":537,"slug":538,"type":16},{"name":592,"slug":593,"type":16},"Gemini","gemini",{"name":595,"slug":596,"type":16},"Speech","speech",{"name":598,"slug":599,"type":16},"Text-to-Speech","text-to-speech","2026-07-12T07:39:17.86673",80,{"items":603,"total":667},[604,616,622,634,647,657],{"slug":605,"name":605,"fn":606,"description":607,"org":608,"tags":609,"stars":23,"repoUrl":24,"updatedAt":615},"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},[610,613,614],{"name":611,"slug":612,"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":4,"name":4,"fn":5,"description":6,"org":617,"tags":618,"stars":23,"repoUrl":24,"updatedAt":25},{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[619,620,621],{"name":21,"slug":22,"type":16},{"name":18,"slug":19,"type":16},{"name":14,"slug":15,"type":16},{"slug":623,"name":623,"fn":624,"description":625,"org":626,"tags":627,"stars":23,"repoUrl":24,"updatedAt":633},"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},[628,631,632],{"name":629,"slug":630,"type":16},"Diagrams","diagrams",{"name":21,"slug":22,"type":16},{"name":14,"slug":15,"type":16},"2026-07-12T07:41:01.085638",{"slug":635,"name":635,"fn":636,"description":637,"org":638,"tags":639,"stars":23,"repoUrl":24,"updatedAt":646},"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},[640,643,644,645],{"name":641,"slug":642,"type":16},"Bioinformatics","bioinformatics",{"name":21,"slug":22,"type":16},{"name":18,"slug":19,"type":16},{"name":14,"slug":15,"type":16},"2026-07-12T07:40:59.811387",{"slug":648,"name":648,"fn":649,"description":650,"org":651,"tags":652,"stars":23,"repoUrl":24,"updatedAt":656},"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},[653,654,655],{"name":629,"slug":630,"type":16},{"name":21,"slug":22,"type":16},{"name":14,"slug":15,"type":16},"2026-07-12T07:40:58.359064",{"slug":658,"name":658,"fn":659,"description":660,"org":661,"tags":662,"stars":23,"repoUrl":24,"updatedAt":666},"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},[663,664,665],{"name":641,"slug":642,"type":16},{"name":21,"slug":22,"type":16},{"name":14,"slug":15,"type":16},"2026-07-12T07:40:53.048652",6]