[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill-google-cloud-whitepaper-template":3,"mdc--ao9737-key":39,"related-repo-google-cloud-whitepaper-template":399,"related-org-google-cloud-whitepaper-template":491},{"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},"whitepaper-template","generate investment-grade acquisition whitepapers","Section-by-section structure for an investment-grade acquisition whitepaper (executive summary through recommendation and sources). Load before writing a detailed report or generating the PDF.",{"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},"PDF","pdf","tag",{"name":18,"slug":19,"type":16},"Life Sciences","life-sciences",{"name":21,"slug":22,"type":16},"Templates","templates",{"name":24,"slug":25,"type":16},"Documents","documents",{"name":27,"slug":28,"type":16},"Investment Banking","investment-banking",15,"https:\u002F\u002Fgithub.com\u002FGoogleCloudPlatform\u002FLifeSciences","2026-08-19T03:58:56.849369",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\u002Fwhitepaper-template","---\nname: whitepaper-template\ndescription: \"Section-by-section structure for an investment-grade acquisition whitepaper (executive summary through recommendation and sources). Load before writing a detailed report or generating the PDF.\"\n---\n\n# Investment Whitepaper Template\n\nStructure for a detailed acquisition-assessment whitepaper. Produce clean\nmarkdown (headings, tables, blockquotes) — it is rendered to PDF verbatim by\nthe `generate_whitepaper_pdf` tool, so formatting matters.\n\nUse markdown tables for all quantitative comparisons. Use `>` blockquotes for\nthe most important risk callouts. Do not invent figures.\n\nCITATIONS: every material claim, figure, and table value carries an inline\nnumbered footnote marker in Markdown footnote syntax, e.g. \"14.7% weight\nloss[^venture]\". Reuse the same short key for the same source; define every key\nunder a final `## References` heading (e.g. `[^venture]: Phase 2 VENTURE 13-week\nresults, Obesity, Jan 2026.`). The renderer turns these into a numbered, linked\nreference list. Never fabricate a source, URL, accession number, or doc ID.\n\nFORMATTING: write plain markdown only. Do NOT use LaTeX or MathJax math\nnotation (`$...$`, `$$...$$`, `\\frac`, `\\text`, `\\ge`, `\\gamma`, etc.) — the PDF\nrenderer shows it raw. Use Unicode symbols and inline arithmetic instead, e.g.\n\"≥70%\", \"Fcγ receptor\", and \"Runway = $56.4M \u002F ($22.6M \u002F 3) = 7.5 months\".\n\n---\n\n# Acquisition Assessment: \u003CTarget Company>\n\n## 1. Executive Summary\n- 4–7 bullets: what the target is, the deal thesis, headline recommendation\n  (Pursue \u002F Pursue with conditions \u002F Pass \u002F Monitor), and the single biggest\n  value driver and the single biggest risk.\n- One-line **Recommendation** with a conviction level (High\u002FMedium\u002FLow).\n\n## 2. Company & Deal Thesis\n- What they do, lead assets, corporate stage, why they'd be acquired now.\n- Deal-thesis archetype (platform \u002F single-asset \u002F tuck-in \u002F distressed).\n\n## 3. Scientific & Modality Assessment\n- Mechanism, novelty, platform breadth, IP position, differentiation.\n- Competitive class table (asset | company | mechanism | stage).\n\n## 4. Clinical & Regulatory Assessment\n- Pipeline table (asset | indication | phase | next catalyst | key risk).\n- Trial design quality, regulatory designations, agency interactions, CMC.\n\n## 5. Commercial & Market Assessment\n- Addressable population, epidemiology, competitive landscape, pricing\u002F\n  reimbursement outlook, peak-sales framing (state assumptions).\n\n## 6. Financial Assessment\n- Financial-snapshot table (metric | latest | prior | source).\n- Cash runway calculation shown explicitly with the formula and inputs.\n- Burn trajectory, dilution history, debt, valuation context.\n\n## 7. Deal Structure & Risk Analysis\n- Risk register table (risk | likelihood | impact | mitigation).\n- Exclusivity\u002Fpatent timeline, encumbrances, integration considerations.\n\n## 8. Valuation & Comparable Transactions\n- Recent comparable M&A deals (target | acquirer | value | premium | date).\n- Rough valuation framing; label all assumptions clearly.\n\n## 9. Recommendation & Conditions\n- Restate recommendation, conditions precedent, diligence follow-ups, and the\n  key questions to resolve before term sheet.\n\n## 10. Confidence & Information Gaps\n- Explicit confidence statement (High\u002FMedium\u002FLow by pillar) and the biggest\n  information gaps.\n\n## References\n- Define every footnote key used above, one per line\n  (`[^key]: full citation with the most specific locator you have`). The renderer\n  renders these as a numbered, linked reference list — do not also hand-write a\n  separate bulleted source list.\n\n---\n\n*Footer note is added automatically by the renderer. Keep total length\nproportionate to available evidence — do not pad sections with speculation.*\n",{"data":40,"body":41},{"name":4,"description":6},{"type":42,"children":43},"root",[44,53,68,81,110,159,163,174,181,204,210,223,229,242,248,261,267,275,281,299,305,318,324,337,343,351,357,365,371,387,390],{"type":45,"tag":46,"props":47,"children":49},"element","h1",{"id":48},"investment-whitepaper-template",[50],{"type":51,"value":52},"text","Investment Whitepaper Template",{"type":45,"tag":54,"props":55,"children":56},"p",{},[57,59,66],{"type":51,"value":58},"Structure for a detailed acquisition-assessment whitepaper. Produce clean\nmarkdown (headings, tables, blockquotes) — it is rendered to PDF verbatim by\nthe ",{"type":45,"tag":60,"props":61,"children":63},"code",{"className":62},[],[64],{"type":51,"value":65},"generate_whitepaper_pdf",{"type":51,"value":67}," tool, so formatting matters.",{"type":45,"tag":54,"props":69,"children":70},{},[71,73,79],{"type":51,"value":72},"Use markdown tables for all quantitative comparisons. Use ",{"type":45,"tag":60,"props":74,"children":76},{"className":75},[],[77],{"type":51,"value":78},">",{"type":51,"value":80}," blockquotes for\nthe most important risk callouts. Do not invent figures.",{"type":45,"tag":54,"props":82,"children":83},{},[84,86,92,94,100,102,108],{"type":51,"value":85},"CITATIONS: every material claim, figure, and table value carries an inline\nnumbered footnote marker in Markdown footnote syntax, e.g. \"14.7% weight\nloss",{"type":45,"tag":87,"props":88,"children":89},"span",{},[90],{"type":51,"value":91},"^venture",{"type":51,"value":93},"\". Reuse the same short key for the same source; define every key\nunder a final ",{"type":45,"tag":60,"props":95,"children":97},{"className":96},[],[98],{"type":51,"value":99},"## References",{"type":51,"value":101}," heading (e.g. ",{"type":45,"tag":60,"props":103,"children":105},{"className":104},[],[106],{"type":51,"value":107},"[^venture]: Phase 2 VENTURE 13-week results, Obesity, Jan 2026.",{"type":51,"value":109},"). The renderer turns these into a numbered, linked\nreference list. Never fabricate a source, URL, accession number, or doc ID.",{"type":45,"tag":54,"props":111,"children":112},{},[113,115,121,123,129,130,136,137,143,144,150,151,157],{"type":51,"value":114},"FORMATTING: write plain markdown only. Do NOT use LaTeX or MathJax math\nnotation (",{"type":45,"tag":60,"props":116,"children":118},{"className":117},[],[119],{"type":51,"value":120},"$...$",{"type":51,"value":122},", ",{"type":45,"tag":60,"props":124,"children":126},{"className":125},[],[127],{"type":51,"value":128},"$$...$$",{"type":51,"value":122},{"type":45,"tag":60,"props":131,"children":133},{"className":132},[],[134],{"type":51,"value":135},"\\frac",{"type":51,"value":122},{"type":45,"tag":60,"props":138,"children":140},{"className":139},[],[141],{"type":51,"value":142},"\\text",{"type":51,"value":122},{"type":45,"tag":60,"props":145,"children":147},{"className":146},[],[148],{"type":51,"value":149},"\\ge",{"type":51,"value":122},{"type":45,"tag":60,"props":152,"children":154},{"className":153},[],[155],{"type":51,"value":156},"\\gamma",{"type":51,"value":158},", etc.) — the PDF\nrenderer shows it raw. Use Unicode symbols and inline arithmetic instead, e.g.\n\"≥70%\", \"Fcγ receptor\", and \"Runway = $56.4M \u002F ($22.6M \u002F 3) = 7.5 months\".",{"type":45,"tag":160,"props":161,"children":162},"hr",{},[],{"type":45,"tag":46,"props":164,"children":166},{"id":165},"acquisition-assessment",[167,169],{"type":51,"value":168},"Acquisition Assessment: ",{"type":45,"tag":170,"props":171,"children":173},"target",{"company":172},"",[],{"type":45,"tag":175,"props":176,"children":178},"h2",{"id":177},"_1-executive-summary",[179],{"type":51,"value":180},"1. Executive Summary",{"type":45,"tag":182,"props":183,"children":184},"ul",{},[185,191],{"type":45,"tag":186,"props":187,"children":188},"li",{},[189],{"type":51,"value":190},"4–7 bullets: what the target is, the deal thesis, headline recommendation\n(Pursue \u002F Pursue with conditions \u002F Pass \u002F Monitor), and the single biggest\nvalue driver and the single biggest risk.",{"type":45,"tag":186,"props":192,"children":193},{},[194,196,202],{"type":51,"value":195},"One-line ",{"type":45,"tag":197,"props":198,"children":199},"strong",{},[200],{"type":51,"value":201},"Recommendation",{"type":51,"value":203}," with a conviction level (High\u002FMedium\u002FLow).",{"type":45,"tag":175,"props":205,"children":207},{"id":206},"_2-company-deal-thesis",[208],{"type":51,"value":209},"2. Company & Deal Thesis",{"type":45,"tag":182,"props":211,"children":212},{},[213,218],{"type":45,"tag":186,"props":214,"children":215},{},[216],{"type":51,"value":217},"What they do, lead assets, corporate stage, why they'd be acquired now.",{"type":45,"tag":186,"props":219,"children":220},{},[221],{"type":51,"value":222},"Deal-thesis archetype (platform \u002F single-asset \u002F tuck-in \u002F distressed).",{"type":45,"tag":175,"props":224,"children":226},{"id":225},"_3-scientific-modality-assessment",[227],{"type":51,"value":228},"3. Scientific & Modality Assessment",{"type":45,"tag":182,"props":230,"children":231},{},[232,237],{"type":45,"tag":186,"props":233,"children":234},{},[235],{"type":51,"value":236},"Mechanism, novelty, platform breadth, IP position, differentiation.",{"type":45,"tag":186,"props":238,"children":239},{},[240],{"type":51,"value":241},"Competitive class table (asset | company | mechanism | stage).",{"type":45,"tag":175,"props":243,"children":245},{"id":244},"_4-clinical-regulatory-assessment",[246],{"type":51,"value":247},"4. Clinical & Regulatory Assessment",{"type":45,"tag":182,"props":249,"children":250},{},[251,256],{"type":45,"tag":186,"props":252,"children":253},{},[254],{"type":51,"value":255},"Pipeline table (asset | indication | phase | next catalyst | key risk).",{"type":45,"tag":186,"props":257,"children":258},{},[259],{"type":51,"value":260},"Trial design quality, regulatory designations, agency interactions, CMC.",{"type":45,"tag":175,"props":262,"children":264},{"id":263},"_5-commercial-market-assessment",[265],{"type":51,"value":266},"5. Commercial & Market Assessment",{"type":45,"tag":182,"props":268,"children":269},{},[270],{"type":45,"tag":186,"props":271,"children":272},{},[273],{"type":51,"value":274},"Addressable population, epidemiology, competitive landscape, pricing\u002F\nreimbursement outlook, peak-sales framing (state assumptions).",{"type":45,"tag":175,"props":276,"children":278},{"id":277},"_6-financial-assessment",[279],{"type":51,"value":280},"6. Financial Assessment",{"type":45,"tag":182,"props":282,"children":283},{},[284,289,294],{"type":45,"tag":186,"props":285,"children":286},{},[287],{"type":51,"value":288},"Financial-snapshot table (metric | latest | prior | source).",{"type":45,"tag":186,"props":290,"children":291},{},[292],{"type":51,"value":293},"Cash runway calculation shown explicitly with the formula and inputs.",{"type":45,"tag":186,"props":295,"children":296},{},[297],{"type":51,"value":298},"Burn trajectory, dilution history, debt, valuation context.",{"type":45,"tag":175,"props":300,"children":302},{"id":301},"_7-deal-structure-risk-analysis",[303],{"type":51,"value":304},"7. Deal Structure & Risk Analysis",{"type":45,"tag":182,"props":306,"children":307},{},[308,313],{"type":45,"tag":186,"props":309,"children":310},{},[311],{"type":51,"value":312},"Risk register table (risk | likelihood | impact | mitigation).",{"type":45,"tag":186,"props":314,"children":315},{},[316],{"type":51,"value":317},"Exclusivity\u002Fpatent timeline, encumbrances, integration considerations.",{"type":45,"tag":175,"props":319,"children":321},{"id":320},"_8-valuation-comparable-transactions",[322],{"type":51,"value":323},"8. Valuation & Comparable Transactions",{"type":45,"tag":182,"props":325,"children":326},{},[327,332],{"type":45,"tag":186,"props":328,"children":329},{},[330],{"type":51,"value":331},"Recent comparable M&A deals (target | acquirer | value | premium | date).",{"type":45,"tag":186,"props":333,"children":334},{},[335],{"type":51,"value":336},"Rough valuation framing; label all assumptions clearly.",{"type":45,"tag":175,"props":338,"children":340},{"id":339},"_9-recommendation-conditions",[341],{"type":51,"value":342},"9. Recommendation & Conditions",{"type":45,"tag":182,"props":344,"children":345},{},[346],{"type":45,"tag":186,"props":347,"children":348},{},[349],{"type":51,"value":350},"Restate recommendation, conditions precedent, diligence follow-ups, and the\nkey questions to resolve before term sheet.",{"type":45,"tag":175,"props":352,"children":354},{"id":353},"_10-confidence-information-gaps",[355],{"type":51,"value":356},"10. Confidence & Information Gaps",{"type":45,"tag":182,"props":358,"children":359},{},[360],{"type":45,"tag":186,"props":361,"children":362},{},[363],{"type":51,"value":364},"Explicit confidence statement (High\u002FMedium\u002FLow by pillar) and the biggest\ninformation gaps.",{"type":45,"tag":175,"props":366,"children":368},{"id":367},"references",[369],{"type":51,"value":370},"References",{"type":45,"tag":182,"props":372,"children":373},{},[374],{"type":45,"tag":186,"props":375,"children":376},{},[377,379,385],{"type":51,"value":378},"Define every footnote key used above, one per line\n(",{"type":45,"tag":60,"props":380,"children":382},{"className":381},[],[383],{"type":51,"value":384},"[^key]: full citation with the most specific locator you have",{"type":51,"value":386},"). The renderer\nrenders these as a numbered, linked reference list — do not also hand-write a\nseparate bulleted source list.",{"type":45,"tag":160,"props":388,"children":389},{},[],{"type":45,"tag":54,"props":391,"children":392},{},[393],{"type":45,"tag":394,"props":395,"children":396},"em",{},[397],{"type":51,"value":398},"Footer note is added automatically by the renderer. Keep total length\nproportionate to available evidence — do not pad sections with speculation.",{"items":400,"total":490},[401,415,433,445,457,470,480],{"slug":402,"name":402,"fn":403,"description":404,"org":405,"tags":406,"stars":29,"repoUrl":30,"updatedAt":414},"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},[407,410,411],{"name":408,"slug":409,"type":16},"Competitive Intelligence","competitive-intelligence",{"name":18,"slug":19,"type":16},{"name":412,"slug":413,"type":16},"Research","research","2026-07-12T07:40:55.676084",{"slug":416,"name":416,"fn":417,"description":418,"org":419,"tags":420,"stars":29,"repoUrl":30,"updatedAt":432},"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},[421,424,425,426,429],{"name":422,"slug":423,"type":16},"Finance","finance",{"name":27,"slug":28,"type":16},{"name":18,"slug":19,"type":16},{"name":427,"slug":428,"type":16},"Regulatory Compliance","regulatory-compliance",{"name":430,"slug":431,"type":16},"Risk Assessment","risk-assessment","2026-08-19T03:58:59.400651",{"slug":434,"name":434,"fn":435,"description":436,"org":437,"tags":438,"stars":29,"repoUrl":30,"updatedAt":444},"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},[439,440,443],{"name":18,"slug":19,"type":16},{"name":441,"slug":442,"type":16},"PubMed","pubmed",{"name":412,"slug":413,"type":16},"2026-07-12T07:40:57.110395",{"slug":446,"name":446,"fn":447,"description":448,"org":449,"tags":450,"stars":29,"repoUrl":30,"updatedAt":456},"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},[451,454,455],{"name":452,"slug":453,"type":16},"Diagrams","diagrams",{"name":18,"slug":19,"type":16},{"name":412,"slug":413,"type":16},"2026-07-12T07:41:01.085638",{"slug":458,"name":458,"fn":459,"description":460,"org":461,"tags":462,"stars":29,"repoUrl":30,"updatedAt":469},"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},[463,466,467,468],{"name":464,"slug":465,"type":16},"Bioinformatics","bioinformatics",{"name":18,"slug":19,"type":16},{"name":441,"slug":442,"type":16},{"name":412,"slug":413,"type":16},"2026-07-12T07:40:59.811387",{"slug":471,"name":471,"fn":472,"description":473,"org":474,"tags":475,"stars":29,"repoUrl":30,"updatedAt":479},"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},[476,477,478],{"name":452,"slug":453,"type":16},{"name":18,"slug":19,"type":16},{"name":412,"slug":413,"type":16},"2026-07-12T07:40:58.359064",{"slug":481,"name":481,"fn":482,"description":483,"org":484,"tags":485,"stars":29,"repoUrl":30,"updatedAt":489},"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},[486,487,488],{"name":464,"slug":465,"type":16},{"name":18,"slug":19,"type":16},{"name":412,"slug":413,"type":16},"2026-07-12T07:40:53.048652",9,{"items":492,"total":680},[493,511,527,546,557,572,594,608,619,633,650,667],{"slug":494,"name":494,"fn":495,"description":496,"org":497,"tags":498,"stars":508,"repoUrl":509,"updatedAt":510},"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},[499,502,505],{"name":500,"slug":501,"type":16},"Documentation","documentation",{"name":503,"slug":504,"type":16},"Knowledge Base","knowledge-base",{"name":506,"slug":507,"type":16},"Search","search",8409,"https:\u002F\u002Fgithub.com\u002FGoogleCloudPlatform\u002Fknowledge-catalog","2026-07-12T07:38:52.157375",{"slug":512,"name":513,"fn":514,"description":515,"org":516,"tags":517,"stars":508,"repoUrl":509,"updatedAt":526},"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},[518,521,522,525],{"name":519,"slug":520,"type":16},"Data Analysis","data-analysis",{"name":9,"slug":8,"type":16},{"name":523,"slug":524,"type":16},"Knowledge Management","knowledge-management",{"name":506,"slug":507,"type":16},"2026-07-12T07:38:22.196851",{"slug":528,"name":528,"fn":529,"description":530,"org":531,"tags":532,"stars":543,"repoUrl":544,"updatedAt":545},"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},[533,536,539,542],{"name":534,"slug":535,"type":16},"Agents","agents",{"name":537,"slug":538,"type":16},"Benchmarking","benchmarking",{"name":540,"slug":541,"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":547,"name":547,"fn":548,"description":549,"org":550,"tags":551,"stars":543,"repoUrl":544,"updatedAt":556},"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},[552,553,554,555],{"name":534,"slug":535,"type":16},{"name":537,"slug":538,"type":16},{"name":540,"slug":541,"type":16},{"name":9,"slug":8,"type":16},"2026-08-13T05:04:18.890378",{"slug":558,"name":558,"fn":559,"description":560,"org":561,"tags":562,"stars":543,"repoUrl":544,"updatedAt":571},"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},[563,566,569,570],{"name":564,"slug":565,"type":16},"Code Analysis","code-analysis",{"name":567,"slug":568,"type":16},"Debugging","debugging",{"name":540,"slug":541,"type":16},{"name":9,"slug":8,"type":16},"2026-08-13T05:04:18.336276",{"slug":573,"name":573,"fn":574,"description":575,"org":576,"tags":577,"stars":591,"repoUrl":592,"updatedAt":593},"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},[578,581,584,587,588],{"name":579,"slug":580,"type":16},"Automation","automation",{"name":582,"slug":583,"type":16},"Engineering","engineering",{"name":585,"slug":586,"type":16},"GitHub","github",{"name":9,"slug":8,"type":16},{"name":589,"slug":590,"type":16},"Pull Requests","pull-requests",2077,"https:\u002F\u002Fgithub.com\u002FGoogleCloudPlatform\u002Fcloud-foundation-fabric","2026-07-31T06:23:36.935005",{"slug":595,"name":595,"fn":596,"description":597,"org":598,"tags":599,"stars":591,"repoUrl":592,"updatedAt":607},"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},[600,601,604],{"name":9,"slug":8,"type":16},{"name":602,"slug":603,"type":16},"Infrastructure as Code","infrastructure-as-code",{"name":605,"slug":606,"type":16},"Terraform","terraform","2026-08-10T04:16:46.817883",{"slug":609,"name":609,"fn":610,"description":611,"org":612,"tags":613,"stars":591,"repoUrl":592,"updatedAt":618},"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},[614,615],{"name":9,"slug":8,"type":16},{"name":616,"slug":617,"type":16},"Operations","operations","2026-08-06T05:36:21.590622",{"slug":620,"name":620,"fn":621,"description":622,"org":623,"tags":624,"stars":630,"repoUrl":631,"updatedAt":632},"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},[625,628,629],{"name":626,"slug":627,"type":16},"CLI","cli",{"name":582,"slug":583,"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":634,"name":634,"fn":635,"description":636,"org":637,"tags":638,"stars":630,"repoUrl":631,"updatedAt":649},"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},[639,642,643,646],{"name":640,"slug":641,"type":16},"API Development","api-development",{"name":9,"slug":8,"type":16},{"name":644,"slug":645,"type":16},"LLM","llm",{"name":647,"slug":648,"type":16},"MCP","mcp","2026-07-12T07:39:10.911302",{"slug":651,"name":651,"fn":652,"description":653,"org":654,"tags":655,"stars":630,"repoUrl":631,"updatedAt":666},"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},[656,659,662,663],{"name":657,"slug":658,"type":16},"Audio","audio",{"name":660,"slug":661,"type":16},"Creative","creative",{"name":9,"slug":8,"type":16},{"name":664,"slug":665,"type":16},"Vertex AI","vertex-ai","2026-07-12T07:39:16.623879",{"slug":668,"name":668,"fn":669,"description":670,"org":671,"tags":672,"stars":630,"repoUrl":631,"updatedAt":679},"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},[673,674,675,678],{"name":660,"slug":661,"type":16},{"name":9,"slug":8,"type":16},{"name":676,"slug":677,"type":16},"Image Generation","image-generation",{"name":664,"slug":665,"type":16},"2026-07-12T07:39:15.372822",61]