diligence-playbookThe five life-sciences M&A diligence pillars (scientific, clinical/regulatory, commercial, financial, deal/risk), the cash-runway calculation, deal-thesis archetypes, evidence standards, and the red-flag checklist. Load for any acquisition assessment.target-screeningMethodology and ranked-shortlist output format for recommending acquisition targets: candidate generation, screening funnel, pillar scoring. Load for 'recommend targets' requests.whitepaper-templateSection-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.competitive-landscape-scanBuild a competitor pipeline view for a target / mechanism / indication — who is in the clinic, what phase, what differentiation. Use for BD / portfolio / commercial-strategy questions like "who else is developing X" or "what's the pipeline for indication Y".drug-safety-signal-scanSurface emerging safety signals for a drug or class from PubMed (case reports / letters / RCT AE tables), plus relevant trial AE disclosures. Use for pharmacovigilance triage, medical-affairs safety updates, or competitive risk assessment. NOT a substitute…mechanism-of-action-explainerProduce a literature-grounded mechanism-of-action explanation for a drug or drug class — receptor / pathway / downstream effects / clinical relevance — with a Nano Banana Pro diagram and citations. Use for medical-affairs MSL prep, internal training, or when…pico-search-strategyTranslate a clinical or research question into a PICO/PECO-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,…prisma-systematic-reviewRun 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,…
explorador de repositórios
GoogleCloudPlatform · Repositórios e skills representativas - Página 2
Visão por repositório de 328 skills coletadas em 47 repositórios do GitHub.
analysis-report-generationGuides on querying benchmark results from BigQuery tables via bq query or query_results.py, evaluating throughput and latency metrics against baselines or intra-run configurations, separating sequential and random read workloads, verifying params.yaml machine…run-gcsfuse-npiMaster entrypoint and orchestration skill for running the end-to-end GCSFuse New Product Introduction (NPI) pipeline across modular skills, coordinating SSH socket setup, bucket creation via bucket-creation skill, target buffer mounting via raid0-script.sh,…conformance-testingGuides on cloning GCSFuse, executing Makefile npi-conformance target on target GCE VMs, coordinating GKE cluster E2E conformance testing via gke-e2e-testing, parsing test logs into conformance_results_<TARGET_NAME>.json, enforcing non-blocking permission…gke-e2e-testingGuides on provisioning GKE clusters (e.g. n2-standard-64) with Workload Identity and GCSFuse CSI Driver addon enabled, enforcing isolated KUBECONFIG policy, configuring gcs-fuse-csi-driver test suite, executing end-to-end (e2e) tests, and parsing Ginkgo test…bucket-creationGuides on provisioning Regional HNS (Hierarchical Namespace) and Zonal RAPID HNS Google Cloud Storage buckets for GCSFuse NPI benchmarking and conformance testing, enforcing uniform bucket-level access, verifying colocation, and inspecting bucket metadata.benchmark-build-setupGuides on checking out GCSFuse, configuring GCE target VMs and GKE runner VMs with RAID0 or tmpfs RAM disk storage buffers via raid0-script.sh, setting up Docker and Artifact Registry permissions, building and pushing benchmarking container images for both…benchmark-suite-executionGuides on configuring targets.json, parameterizing and executing benchmark suites on GCE VMs and GKE clusters using npi_orchestrator.py, managing state resets in ~/.npi/npi_run_state.json, enforcing active safety policies (4h inactivity timeout, 85% disk…remediation-advisorGuides on diagnosing GCSFuse NPI performance regressions, 20 GB/s SLA gate failures, and conformance errors, analyzing root causes across FUSE queue depths, gRPC connection pools, OS LRO/GRO offloads, RFS/RPS packet steering, and sysctl TCP buffers, and…
scion-messagingTeaches agents how to use the scion message command effectively. Use this for ANY agent type that needs to communicate with other agents or users. Covers recipient types, message timing, content best practices, and special message flags.scion-agent-manageManage concurrent LLM-based code agents with scion - orchestrate parallel agents with isolated workspaces, troubleshoot and recover stuck agentsscion-cli-operationsOperational constraints for Scion agents running in containerized sandboxes. Covers prohibited commands and hub-only API access. Complements the scion CLI reference and messaging skills.git-operationsGit safety and operational guidance for Scion agents. Covers working tree resets, rebase pitfalls, and general git behavior that agents should know regardless of workspace mode. For workspace-mode-specific git rules, see the git-sandbox skill.scion-schedulerSchedule one-shot and recurring events for agents using the Scion CLI. Covers when to use scheduled events vs inline message delays, recurring cron schedules, lifecycle management, and the blocked-wait pairing rule.team-creationCreate or extend scion agent team templates from a high-level description of roles and workflow. Use when the user describes a multi-agent team, panel, crew, pipeline, or any scenario requiring coordinated LLM agents with distinct roles. Also use when adding…git-sandboxGit workflow protocol for agents in sandbox/worktree environments. Covers local-only operations, worktree-aware branch management, and non-interactive conflict resolution. Injected only for git-associated workspaces.chrome-devtoolsUses Chrome DevTools via MCP for efficient debugging, troubleshooting and browser automation. Use when debugging web pages, automating browser interactions, analyzing performance, or inspecting network requests.
task-record-replayPractical guidelines and recipes for creating and running microbenchmarks and pprof profiling for KHI DAG tasks using taskrecord and JobTestHarness.khi-parserGuidelines, package patterns, and task implementations for adding new log type support or modifying existing log parsers in KHI.log-timeline-mapperGuidelines for implementing and testing LogIngesterTask and LogToTimelineMapper tasks in KHI.jj-workflowGuidelines and procedures for using Jujutsu (jj) in KHI, including change management, workspace isolation, pushing commits with auto-generated bookmarks, addressing PR review feedback without squashing, and resolving conflicts incrementally from oldest to…backward-compatibility-policyGuidelines on backward compatibility in KHI, explaining why internal code requires no backward compatibility, identifying anti-patterns with concrete examples, and detailing the single exception for .khi files.streaming-apiGuidelines, naming conventions, and implementation patterns for designing Server-Side Streaming RPCs and their polling fallbacks in KHI.googlecloud-apiGuidelines and mandatory rules for calling Google Cloud APIs in KHI, including CallOptionInjector, ClientFactory, and context propagation.
context-engineering-bootstrapGuides the agent to bootstrap an initial ContextSet (templates, facets, and value searches) by deducing key information from the database schema and generating a ContextSet file.context-engineering-hillclimbGuides the agent to perform hill-climbing iterations to improve a ContextSet based on Evalbench evaluation results.context-generation-guideGuidelines and best practices for generating context items (Templates, Facets, Value Searches). Use this skill whenever the user asks to create, author, or generate context for database enrichment, or asks for examples and instructions on how to write…context-engineering-dataset-generationGenerate or expand a golden evaluation dataset of SQL/Question (NLQ+SQL) pairs for evaluating NL-to-SQL translation accuracy on a target database.context-engineering-evaluateGuides the agent to execute an evaluation of a ContextSet against a golden NLQ+SQL dataset using the Evalbench framework.context-engineering-initOrchestrates the initialization workflow for context engineering, and provides helper workflow for setting up database connections by creating or updating tools.yaml configurations.context-engineering-workflowContext engineering for Gemini Data Analytics API's data agent developer platform tools. Generates, evaluates, and iteratively optimizes a ContextSet (Templates, Facets, Value Searches) to maximize Natural-Language-to-SQL translation accuracy. Use this skill…
contributingEnd-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,…fabric-builderGenerates 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.fast-prerequisitesGuides 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…release-processGuide for cutting a new release of the Cloud Foundation Fabric (CFF) repository. Use this skill when asked to create, prepare, or draft a new release.tool-test-skillA simple skill to test if the agent correctly executes tools.fast-setup-pocA wizard to help users configure FAST (Fabric Architecture Setup Tool) step-by-step. Use this skill when asked to configure FAST, run the FAST wizard, or setup FAST.
ge-demo-generatorSynthesizes and deploys complete, domain-specific Gemini Enterprise demo environments directly to Google Cloud. Use when the user asks to create an AI agent demo for any customer domain (e.g. 'example.com', 'example.co.jp', 'example.de', 'example.fr' - any…professional-documentProduce a formal business document as .docx (python-docx) or PDF (reportlab) - reports, proposals, briefings, one-pagers, meeting summaries. Use whenever the task asks for a written document, report file, proposal, or PDF. Covers structure, typography, build…professional-presentationBuild a professional, executive-quality presentation deck (.pptx) with python-pptx. Use whenever the task asks for slides, a deck, a board/executive presentation, or a pitch. Covers design system, slide patterns, build process, and delivery.web-reportBuild a polished, self-contained single-page HTML report or briefing microsite - executive briefings, analysis reports, campaign/project one-pagers rendered for the browser. Use whenever the task asks for a web page, HTML report, briefing page, or microsite.…migration-config-skillHolds canonical source and target environment parameters and verified DataStore mappings.
liveapi-serviceGenerates a LiveAPI client service class in the user's chosen programming language. Use when the user wants to build, scaffold, or integrate a client that connects to the Gemini LiveAPI websocket endpoint (Gemini Enterprise or non-Gemini Enterprise), handles…genai-sdkGuides the usage of Gemini API on Google Cloud Vertex AI with the Gen AI SDK. Use when the user asks about using Gemini in an enterprise environment or explicitly mentions Vertex AI. Covers SDK usage (Python, JS/TS, Go, Java, C#), capabilities like Live API,…quality-flywheelEvaluate and improve GenAI models and agents using the Google GenAI Evaluation SDK. Creates eval datasets (from session traces or synthetic generation), selects and configures metrics (RubricMetric, LLMMetric, CodeExecutionMetric), executes evals via…vertex-aiPrimary Router for Vertex AI skills. Use this skill when the user wants to work with Google Cloud Vertex AI (e.g., deploying models, running inference, or tuning models). This skill routes to vertex-deploy, vertex-inference, or vertex-tuning.vertex-tuningVertex AI Model Tuning. Use when you need to fine-tune models using Vertex AI's infrastructure.
use-case-deploymentEnd-to-end orchestration and deployment runner for all solution guides in this repository. Use when deploying, running, ingesting test data into, or validating any of the 8 solution guides: GenAI & ML (Gemma 4 with vLLM on GPU), ETL & Integration (Spanner…dataflow-pipeline-devDevelop, format, lint, package, and test Apache Beam Dataflow pipelines in Python and Java within this repository. Use when modifying existing pipeline DoFns, creating new Beam pipelines, configuring pipeline options, running local tests with DirectRunner,…dataflow-troubleshootingDiagnose, debug, and resolve common Apache Beam and Google Cloud Dataflow errors in this repository. Use when Dataflow jobs fail to start, workers crash or fail health checks, IAM permission errors occur, Cloud Build or Docker container images fail, GPU…pr-reviewReview, validate, test, approve, and merge Pull Requests in this repository. Use when asked to review a PR, wait for CI builds/checks to pass, verify compliance with repository policies (AGENTS.md, security guardrails, coding standards), approve safe PRs,…terraform-deployManage, validate, plan, apply, and destroy Google Cloud Foundation Fabric Terraform infrastructure across all solution guides in this repository. Use when setting up new GCP environments, modifying IAM configurations, managing Spanner/BigQuery/Bigtable…
llm-d-benchmarkingBenchmarks a deployed llm-d well-lit path guide stack on GKE using llm-d-benchmark cli with inference-perf as the harness, the user a will select the appropriate workload profiles from llm-d-benchmark.llm-d-workload-tunerThis is an experimental Skill. It automatically tunes GKE vLLM inference server parameters and resources based on workload profiles specified in the benchmark configs.gke-inference-stack-deployDeploys the GKE base platform and inference-specific terra-services (GPU/TPU) for accelerated workloads.llm-d-deploy-stackDeploys the llm-d stack on GKE using well-lit paths specification.
skillsGathers detailed information on a topic using Google Search.skillsTransforms research findings into a formatted course module and verifies structure.agent-platform-debuggerDebug GCP Gemini Enterprise Agent Platform issues: Agent Gateway 403s, Agent Registry failures, Agent Identity/IAM denials, IAP egressor authz, service-extensions delegated authz, Model Armor integration failures (500s/denials), hostname mismatches,…
agent-evalExecutes high-performance agent evaluations, multi-turn UserSim simulations, and declarative metric grading aligned with google/agents-cli and the Quality Flywheel. Publishes benchmark artifacts to the GCS Evaluation Registry, executes automated head-to-head…agent-eval-workflowThis 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…eval-breakdownPerforms 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…