[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill-google-cloud-prisma-systematic-review":3,"mdc-vzjzdj-key":33,"related-org-google-cloud-prisma-systematic-review":380,"related-repo-google-cloud-prisma-systematic-review":569},{"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},"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},"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},"Life Sciences","life-sciences",{"name":21,"slug":22,"type":16},"Diagrams","diagrams",14,"https:\u002F\u002Fgithub.com\u002FGoogleCloudPlatform\u002FLifeSciences","2026-07-12T07:40:58.359064",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\u002Fprisma-systematic-review","---\nname: prisma-systematic-review\ndescription: 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.\n---\n\n# PRISMA 2020 Systematic Review\n\nYou are executing a [PRISMA 2020](https:\u002F\u002Fwww.bmj.com\u002Fcontent\u002F372\u002Fbmj.n71)\naligned systematic review. Pharma reviewers use these for HEOR\nsubmissions, payer dossiers, and regulatory briefing books — every\nexclusion must be defensible and counted.\n\n## Workflow\n\n### Step 0 — Lock the protocol\n\nBefore any searches, get explicit user agreement on:\n\n- The PICO question (use the `pico-search-strategy` skill if not already\n  done).\n- Inclusion criteria: study designs, population, intervention\u002Fexposure,\n  comparator, outcomes, follow-up window, language, date range.\n- Exclusion criteria, listed positively (e.g. \"exclude single-arm Phase 1\n  trials\", not \"exclude weak studies\").\n\nEcho these back to the user as a numbered list and ask \"approve to\nproceed?\" before running searches. This is the version of record for the\nreview's audit trail.\n\n### Step 1 — Identification\n\nCall `DeepResearchPipeline` with a `request` that includes the locked PICO\n+ filters, so PubMed + Europe PMC + ClinicalTrials.gov + preprints all run\nin parallel. Record:\n\n- Records identified per database (counts go in the PRISMA flow diagram).\n- Records identified from registers (ClinicalTrials.gov hits — PRISMA 2020\n  separates databases from registers).\n\nIf the user names additional sources (Embase via a partner, internal\nstudy registry, conference abstracts), add a note that these were not\nsearched in this run.\n\n### Step 2 — Deduplication\n\nDe-duplicate across PubMed + Europe PMC by PMID first, then by DOI, then\nby normalized title (lowercased, punctuation-stripped, first 80 chars).\nRecord the number of duplicates removed.\n\n### Step 3 — Title\u002Fabstract screening\n\nFor each unique record, decide INCLUDE \u002F EXCLUDE \u002F UNCERTAIN against the\ninclusion criteria. For every EXCLUDE, record the single most specific\nreason from the standard PRISMA exclusion taxonomy:\n\n- Wrong population\n- Wrong intervention\n- Wrong comparator\n- Wrong outcome\n- Wrong study design\n- Wrong publication type (editorial \u002F commentary \u002F letter)\n- Conference abstract only\n- Not in target language\n- Outside date range\n- Duplicate\n- Other (must specify)\n\nMark UNCERTAIN cases for full-text review rather than guessing. Do NOT\nsilently drop records.\n\n### Step 4 — Full-text retrieval + eligibility\n\nFor INCLUDE + UNCERTAIN records: call `get_europe_pmc_fulltext` for\nopen-access PMCIDs. For paywalled records, mark as \"full text not\nretrieved\" — this is a real PRISMA category and must be counted.\n\nRe-screen against inclusion criteria with the full text in hand. Record\nexclusions with the same reason taxonomy.\n\n### Step 5 — Render the PRISMA flow diagram\n\nCall `visualize_concept` with `figure_type=\"prisma_flow\"` and a description\nthat includes every count from steps 1-4:\n\n```\nIdentification: PubMed n=X, Europe PMC n=Y, ClinicalTrials.gov n=Z, Preprints n=W\nDuplicates removed: D\nRecords screened (title\u002Fabstract): S\nExcluded at title\u002Fabstract: E (with the top-3 reasons + counts)\nFull-text reports sought: F\nReports not retrieved: NR\nReports assessed for eligibility: A\nExcluded at full text: X (with reasons + counts)\nStudies included in synthesis: I\n```\n\n### Step 6 — Synthesis + reporting\n\nHand the included set to a synthesis pass that produces:\n\n- Characteristics-of-included-studies table (study, design, n, population,\n  intervention, comparator, outcome, follow-up).\n- Narrative synthesis grouped by outcome.\n- Risk-of-bias note (acknowledge that formal RoB scoring needs a human\n  reviewer; this skill does not auto-grade studies).\n\nAlways cite each included study by PMID \u002F NCT and link.\n\n## Failure modes to avoid\n\n- Silent exclusions: every dropped record must have a counted reason.\n- Mixing identification of databases with registers in the PRISMA counts.\n- Over-claiming: state \"this is a literature scan suitable for an\n  internal evidence brief\" unless the user has done dual-reviewer\n  screening + formal RoB scoring offline.\n- Forgetting the search date — record YYYY-MM-DD on the flow diagram.\n",{"data":34,"body":35},{"name":4,"description":6},{"type":36,"children":37},"root",[38,47,64,71,78,83,112,117,123,144,152,165,170,176,181,187,192,250,255,261,274,279,285,305,317,323,328,346,351,357],{"type":39,"tag":40,"props":41,"children":43},"element","h1",{"id":42},"prisma-2020-systematic-review",[44],{"type":45,"value":46},"text","PRISMA 2020 Systematic Review",{"type":39,"tag":48,"props":49,"children":50},"p",{},[51,53,62],{"type":45,"value":52},"You are executing a ",{"type":39,"tag":54,"props":55,"children":59},"a",{"href":56,"rel":57},"https:\u002F\u002Fwww.bmj.com\u002Fcontent\u002F372\u002Fbmj.n71",[58],"nofollow",[60],{"type":45,"value":61},"PRISMA 2020",{"type":45,"value":63},"\naligned systematic review. Pharma reviewers use these for HEOR\nsubmissions, payer dossiers, and regulatory briefing books — every\nexclusion must be defensible and counted.",{"type":39,"tag":65,"props":66,"children":68},"h2",{"id":67},"workflow",[69],{"type":45,"value":70},"Workflow",{"type":39,"tag":72,"props":73,"children":75},"h3",{"id":74},"step-0-lock-the-protocol",[76],{"type":45,"value":77},"Step 0 — Lock the protocol",{"type":39,"tag":48,"props":79,"children":80},{},[81],{"type":45,"value":82},"Before any searches, get explicit user agreement on:",{"type":39,"tag":84,"props":85,"children":86},"ul",{},[87,102,107],{"type":39,"tag":88,"props":89,"children":90},"li",{},[91,93,100],{"type":45,"value":92},"The PICO question (use the ",{"type":39,"tag":94,"props":95,"children":97},"code",{"className":96},[],[98],{"type":45,"value":99},"pico-search-strategy",{"type":45,"value":101}," skill if not already\ndone).",{"type":39,"tag":88,"props":103,"children":104},{},[105],{"type":45,"value":106},"Inclusion criteria: study designs, population, intervention\u002Fexposure,\ncomparator, outcomes, follow-up window, language, date range.",{"type":39,"tag":88,"props":108,"children":109},{},[110],{"type":45,"value":111},"Exclusion criteria, listed positively (e.g. \"exclude single-arm Phase 1\ntrials\", not \"exclude weak studies\").",{"type":39,"tag":48,"props":113,"children":114},{},[115],{"type":45,"value":116},"Echo these back to the user as a numbered list and ask \"approve to\nproceed?\" before running searches. This is the version of record for the\nreview's audit trail.",{"type":39,"tag":72,"props":118,"children":120},{"id":119},"step-1-identification",[121],{"type":45,"value":122},"Step 1 — Identification",{"type":39,"tag":48,"props":124,"children":125},{},[126,128,134,136,142],{"type":45,"value":127},"Call ",{"type":39,"tag":94,"props":129,"children":131},{"className":130},[],[132],{"type":45,"value":133},"DeepResearchPipeline",{"type":45,"value":135}," with a ",{"type":39,"tag":94,"props":137,"children":139},{"className":138},[],[140],{"type":45,"value":141},"request",{"type":45,"value":143}," that includes the locked PICO",{"type":39,"tag":84,"props":145,"children":146},{},[147],{"type":39,"tag":88,"props":148,"children":149},{},[150],{"type":45,"value":151},"filters, so PubMed + Europe PMC + ClinicalTrials.gov + preprints all run\nin parallel. Record:",{"type":39,"tag":84,"props":153,"children":154},{},[155,160],{"type":39,"tag":88,"props":156,"children":157},{},[158],{"type":45,"value":159},"Records identified per database (counts go in the PRISMA flow diagram).",{"type":39,"tag":88,"props":161,"children":162},{},[163],{"type":45,"value":164},"Records identified from registers (ClinicalTrials.gov hits — PRISMA 2020\nseparates databases from registers).",{"type":39,"tag":48,"props":166,"children":167},{},[168],{"type":45,"value":169},"If the user names additional sources (Embase via a partner, internal\nstudy registry, conference abstracts), add a note that these were not\nsearched in this run.",{"type":39,"tag":72,"props":171,"children":173},{"id":172},"step-2-deduplication",[174],{"type":45,"value":175},"Step 2 — Deduplication",{"type":39,"tag":48,"props":177,"children":178},{},[179],{"type":45,"value":180},"De-duplicate across PubMed + Europe PMC by PMID first, then by DOI, then\nby normalized title (lowercased, punctuation-stripped, first 80 chars).\nRecord the number of duplicates removed.",{"type":39,"tag":72,"props":182,"children":184},{"id":183},"step-3-titleabstract-screening",[185],{"type":45,"value":186},"Step 3 — Title\u002Fabstract screening",{"type":39,"tag":48,"props":188,"children":189},{},[190],{"type":45,"value":191},"For each unique record, decide INCLUDE \u002F EXCLUDE \u002F UNCERTAIN against the\ninclusion criteria. For every EXCLUDE, record the single most specific\nreason from the standard PRISMA exclusion taxonomy:",{"type":39,"tag":84,"props":193,"children":194},{},[195,200,205,210,215,220,225,230,235,240,245],{"type":39,"tag":88,"props":196,"children":197},{},[198],{"type":45,"value":199},"Wrong population",{"type":39,"tag":88,"props":201,"children":202},{},[203],{"type":45,"value":204},"Wrong intervention",{"type":39,"tag":88,"props":206,"children":207},{},[208],{"type":45,"value":209},"Wrong comparator",{"type":39,"tag":88,"props":211,"children":212},{},[213],{"type":45,"value":214},"Wrong outcome",{"type":39,"tag":88,"props":216,"children":217},{},[218],{"type":45,"value":219},"Wrong study design",{"type":39,"tag":88,"props":221,"children":222},{},[223],{"type":45,"value":224},"Wrong publication type (editorial \u002F commentary \u002F letter)",{"type":39,"tag":88,"props":226,"children":227},{},[228],{"type":45,"value":229},"Conference abstract only",{"type":39,"tag":88,"props":231,"children":232},{},[233],{"type":45,"value":234},"Not in target language",{"type":39,"tag":88,"props":236,"children":237},{},[238],{"type":45,"value":239},"Outside date range",{"type":39,"tag":88,"props":241,"children":242},{},[243],{"type":45,"value":244},"Duplicate",{"type":39,"tag":88,"props":246,"children":247},{},[248],{"type":45,"value":249},"Other (must specify)",{"type":39,"tag":48,"props":251,"children":252},{},[253],{"type":45,"value":254},"Mark UNCERTAIN cases for full-text review rather than guessing. Do NOT\nsilently drop records.",{"type":39,"tag":72,"props":256,"children":258},{"id":257},"step-4-full-text-retrieval-eligibility",[259],{"type":45,"value":260},"Step 4 — Full-text retrieval + eligibility",{"type":39,"tag":48,"props":262,"children":263},{},[264,266,272],{"type":45,"value":265},"For INCLUDE + UNCERTAIN records: call ",{"type":39,"tag":94,"props":267,"children":269},{"className":268},[],[270],{"type":45,"value":271},"get_europe_pmc_fulltext",{"type":45,"value":273}," for\nopen-access PMCIDs. For paywalled records, mark as \"full text not\nretrieved\" — this is a real PRISMA category and must be counted.",{"type":39,"tag":48,"props":275,"children":276},{},[277],{"type":45,"value":278},"Re-screen against inclusion criteria with the full text in hand. Record\nexclusions with the same reason taxonomy.",{"type":39,"tag":72,"props":280,"children":282},{"id":281},"step-5-render-the-prisma-flow-diagram",[283],{"type":45,"value":284},"Step 5 — Render the PRISMA flow diagram",{"type":39,"tag":48,"props":286,"children":287},{},[288,289,295,297,303],{"type":45,"value":127},{"type":39,"tag":94,"props":290,"children":292},{"className":291},[],[293],{"type":45,"value":294},"visualize_concept",{"type":45,"value":296}," with ",{"type":39,"tag":94,"props":298,"children":300},{"className":299},[],[301],{"type":45,"value":302},"figure_type=\"prisma_flow\"",{"type":45,"value":304}," and a description\nthat includes every count from steps 1-4:",{"type":39,"tag":306,"props":307,"children":311},"pre",{"className":308,"code":310,"language":45},[309],"language-text","Identification: PubMed n=X, Europe PMC n=Y, ClinicalTrials.gov n=Z, Preprints n=W\nDuplicates removed: D\nRecords screened (title\u002Fabstract): S\nExcluded at title\u002Fabstract: E (with the top-3 reasons + counts)\nFull-text reports sought: F\nReports not retrieved: NR\nReports assessed for eligibility: A\nExcluded at full text: X (with reasons + counts)\nStudies included in synthesis: I\n",[312],{"type":39,"tag":94,"props":313,"children":315},{"__ignoreMap":314},"",[316],{"type":45,"value":310},{"type":39,"tag":72,"props":318,"children":320},{"id":319},"step-6-synthesis-reporting",[321],{"type":45,"value":322},"Step 6 — Synthesis + reporting",{"type":39,"tag":48,"props":324,"children":325},{},[326],{"type":45,"value":327},"Hand the included set to a synthesis pass that produces:",{"type":39,"tag":84,"props":329,"children":330},{},[331,336,341],{"type":39,"tag":88,"props":332,"children":333},{},[334],{"type":45,"value":335},"Characteristics-of-included-studies table (study, design, n, population,\nintervention, comparator, outcome, follow-up).",{"type":39,"tag":88,"props":337,"children":338},{},[339],{"type":45,"value":340},"Narrative synthesis grouped by outcome.",{"type":39,"tag":88,"props":342,"children":343},{},[344],{"type":45,"value":345},"Risk-of-bias note (acknowledge that formal RoB scoring needs a human\nreviewer; this skill does not auto-grade studies).",{"type":39,"tag":48,"props":347,"children":348},{},[349],{"type":45,"value":350},"Always cite each included study by PMID \u002F NCT and link.",{"type":39,"tag":65,"props":352,"children":354},{"id":353},"failure-modes-to-avoid",[355],{"type":45,"value":356},"Failure modes to avoid",{"type":39,"tag":84,"props":358,"children":359},{},[360,365,370,375],{"type":39,"tag":88,"props":361,"children":362},{},[363],{"type":45,"value":364},"Silent exclusions: every dropped record must have a counted reason.",{"type":39,"tag":88,"props":366,"children":367},{},[368],{"type":45,"value":369},"Mixing identification of databases with registers in the PRISMA counts.",{"type":39,"tag":88,"props":371,"children":372},{},[373],{"type":45,"value":374},"Over-claiming: state \"this is a literature scan suitable for an\ninternal evidence brief\" unless the user has done dual-reviewer\nscreening + formal RoB scoring offline.",{"type":39,"tag":88,"props":376,"children":377},{},[378],{"type":45,"value":379},"Forgetting the search date — record YYYY-MM-DD on the flow diagram.",{"items":381,"total":568},[382,400,416,438,452,463,477,494,511,524,540,550],{"slug":383,"name":383,"fn":384,"description":385,"org":386,"tags":387,"stars":397,"repoUrl":398,"updatedAt":399},"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},[388,391,394],{"name":389,"slug":390,"type":16},"Documentation","documentation",{"name":392,"slug":393,"type":16},"Knowledge Base","knowledge-base",{"name":395,"slug":396,"type":16},"Search","search",6749,"https:\u002F\u002Fgithub.com\u002FGoogleCloudPlatform\u002Fknowledge-catalog","2026-07-12T07:38:52.157375",{"slug":401,"name":402,"fn":403,"description":404,"org":405,"tags":406,"stars":397,"repoUrl":398,"updatedAt":415},"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},[407,410,411,414],{"name":408,"slug":409,"type":16},"Data Analysis","data-analysis",{"name":9,"slug":8,"type":16},{"name":412,"slug":413,"type":16},"Knowledge Management","knowledge-management",{"name":395,"slug":396,"type":16},"2026-07-12T07:38:22.196851",{"slug":417,"name":417,"fn":418,"description":419,"org":420,"tags":421,"stars":435,"repoUrl":436,"updatedAt":437},"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},[422,425,428,431,432],{"name":423,"slug":424,"type":16},"Automation","automation",{"name":426,"slug":427,"type":16},"Engineering","engineering",{"name":429,"slug":430,"type":16},"GitHub","github",{"name":9,"slug":8,"type":16},{"name":433,"slug":434,"type":16},"Pull Requests","pull-requests",2062,"https:\u002F\u002Fgithub.com\u002FGoogleCloudPlatform\u002Fcloud-foundation-fabric","2026-07-31T06:23:36.935005",{"slug":439,"name":439,"fn":440,"description":441,"org":442,"tags":443,"stars":435,"repoUrl":436,"updatedAt":451},"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},[444,445,448],{"name":9,"slug":8,"type":16},{"name":446,"slug":447,"type":16},"Infrastructure as Code","infrastructure-as-code",{"name":449,"slug":450,"type":16},"Terraform","terraform","2026-07-12T07:38:23.514555",{"slug":453,"name":453,"fn":454,"description":455,"org":456,"tags":457,"stars":435,"repoUrl":436,"updatedAt":462},"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},[458,459],{"name":9,"slug":8,"type":16},{"name":460,"slug":461,"type":16},"Operations","operations","2026-07-12T07:38:28.127148",{"slug":464,"name":464,"fn":465,"description":466,"org":467,"tags":468,"stars":474,"repoUrl":475,"updatedAt":476},"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},[469,472,473],{"name":470,"slug":471,"type":16},"CLI","cli",{"name":426,"slug":427,"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":478,"name":478,"fn":479,"description":480,"org":481,"tags":482,"stars":474,"repoUrl":475,"updatedAt":493},"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},[483,486,487,490],{"name":484,"slug":485,"type":16},"API Development","api-development",{"name":9,"slug":8,"type":16},{"name":488,"slug":489,"type":16},"LLM","llm",{"name":491,"slug":492,"type":16},"MCP","mcp","2026-07-12T07:39:10.911302",{"slug":495,"name":495,"fn":496,"description":497,"org":498,"tags":499,"stars":474,"repoUrl":475,"updatedAt":510},"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},[500,503,506,507],{"name":501,"slug":502,"type":16},"Audio","audio",{"name":504,"slug":505,"type":16},"Creative","creative",{"name":9,"slug":8,"type":16},{"name":508,"slug":509,"type":16},"Vertex AI","vertex-ai","2026-07-12T07:39:16.623879",{"slug":512,"name":512,"fn":513,"description":514,"org":515,"tags":516,"stars":474,"repoUrl":475,"updatedAt":523},"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},[517,518,519,522],{"name":504,"slug":505,"type":16},{"name":9,"slug":8,"type":16},{"name":520,"slug":521,"type":16},"Image Generation","image-generation",{"name":508,"slug":509,"type":16},"2026-07-12T07:39:15.372822",{"slug":525,"name":525,"fn":526,"description":527,"org":528,"tags":529,"stars":474,"repoUrl":475,"updatedAt":539},"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},[530,531,532,533,536],{"name":501,"slug":502,"type":16},{"name":504,"slug":505,"type":16},{"name":9,"slug":8,"type":16},{"name":534,"slug":535,"type":16},"Media","media",{"name":537,"slug":538,"type":16},"Video","video","2026-07-12T07:39:09.672849",{"slug":541,"name":541,"fn":542,"description":543,"org":544,"tags":545,"stars":474,"repoUrl":475,"updatedAt":549},"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},[546,547,548],{"name":504,"slug":505,"type":16},{"name":9,"slug":8,"type":16},{"name":537,"slug":538,"type":16},"2026-07-12T07:39:13.749081",{"slug":551,"name":551,"fn":552,"description":553,"org":554,"tags":555,"stars":474,"repoUrl":475,"updatedAt":567},"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},[556,557,558,561,564],{"name":501,"slug":502,"type":16},{"name":504,"slug":505,"type":16},{"name":559,"slug":560,"type":16},"Gemini","gemini",{"name":562,"slug":563,"type":16},"Speech","speech",{"name":565,"slug":566,"type":16},"Text-to-Speech","text-to-speech","2026-07-12T07:39:17.86673",80,{"items":570,"total":633},[571,583,595,605,617,623],{"slug":572,"name":572,"fn":573,"description":574,"org":575,"tags":576,"stars":23,"repoUrl":24,"updatedAt":582},"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},[577,580,581],{"name":578,"slug":579,"type":16},"Competitive Intelligence","competitive-intelligence",{"name":18,"slug":19,"type":16},{"name":14,"slug":15,"type":16},"2026-07-12T07:40:55.676084",{"slug":584,"name":584,"fn":585,"description":586,"org":587,"tags":588,"stars":23,"repoUrl":24,"updatedAt":594},"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},[589,590,593],{"name":18,"slug":19,"type":16},{"name":591,"slug":592,"type":16},"PubMed","pubmed",{"name":14,"slug":15,"type":16},"2026-07-12T07:40:57.110395",{"slug":596,"name":596,"fn":597,"description":598,"org":599,"tags":600,"stars":23,"repoUrl":24,"updatedAt":604},"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},[601,602,603],{"name":21,"slug":22,"type":16},{"name":18,"slug":19,"type":16},{"name":14,"slug":15,"type":16},"2026-07-12T07:41:01.085638",{"slug":99,"name":99,"fn":606,"description":607,"org":608,"tags":609,"stars":23,"repoUrl":24,"updatedAt":616},"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},[610,613,614,615],{"name":611,"slug":612,"type":16},"Bioinformatics","bioinformatics",{"name":18,"slug":19,"type":16},{"name":591,"slug":592,"type":16},{"name":14,"slug":15,"type":16},"2026-07-12T07:40:59.811387",{"slug":4,"name":4,"fn":5,"description":6,"org":618,"tags":619,"stars":23,"repoUrl":24,"updatedAt":25},{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[620,621,622],{"name":21,"slug":22,"type":16},{"name":18,"slug":19,"type":16},{"name":14,"slug":15,"type":16},{"slug":624,"name":624,"fn":625,"description":626,"org":627,"tags":628,"stars":23,"repoUrl":24,"updatedAt":632},"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},[629,630,631],{"name":611,"slug":612,"type":16},{"name":18,"slug":19,"type":16},{"name":14,"slug":15,"type":16},"2026-07-12T07:40:53.048652",6]