google

Provides expert guidance on Identity and Access Management (IAM) and authenticating and authorizing to Google Cloud services and APIs, covering human users, service identities, Application Default Credentials (ADC), and best practices for secure access.

Analyzes the downstream impact (blast radius) using data lineage on Google Cloud when a BigQuery table or view is broken, stale, or modified. Identifies all downstream tables, dashboards, and processes that will be affected. Use when: - Performing a blast…

Summarizes data lineage graphs on Google Cloud to help users debug data quality issues and understand data provenance for BigQuery and Cloud Storage. Use when summarizing upstream and downstream data flows, and presenting complex lineage data as an intuitive…

Queries and retrieves active security findings, external exposures, toxic combinations, vulnerabilities, threats, and sensitive data risks from Security Command Center on Google Cloud. Use when retrieving details for a security finding by its name, validating…

Safely simulates and applies Identity and Access Management (IAM) v1 (Allow) policy changes on Google Cloud. Uses the Policy Simulator to replay historical access logs against proposed policies to prevent breaking active workloads before applying the changes.…

Diagnoses, remediates, and manages Identity and Access Management (IAM) access issues on Google Cloud. Supports two distinct operational modes: (1) Requester Flow for developers encountering access denials (capturing error context, self-service PAM JIT…

Diagnose GKE Cloud TPU training throughput drops and step-time regressions (15%+ TPU duty-cycle drop) using ML Diagnostics Workload Monitoring (`gcloud alpha mldiagnostics monitored-events` / `hypercomputecluster.googleapis.com/v1alpha`) and 1-minute Cloud…

Diagnose GKE Cloud TPU multi-slice training hangs (Megascale `HANG_DETECTED` logs and hang monitored events) using the ML Diagnostics `Megascale XLA (MXLA) Hang Analyzer` (`gcloud alpha mldiagnostics monitored-events`) and 1-minute Cloud Monitoring…

Capsem's release process: orthogonal binary/profile CI, signing, notarization, channel deployment. Use for release commands, failures, manifests, or anything affecting what ships.

Capsem's unified cache control plane. Use for cache inventory, retention, cleanup, test reuse, or disk, Docker/Colima, Tart, Cargo, Python, Node, BuildKit, and VM asset cache work.

The Citadel guard suite. Use when adding a guard, a linter, or a source surface, or when a citadel test fails and you need to know what it is protecting.

CI triage and red-gate discipline. Use when an Actions run is red, pr-gate blocks a PR, you are deciding whether to rerun, or you are editing .github/workflows/.

Debugging methodology: reproduce first, find the root cause, fix the whole pattern. Use for bugs, test failures, or CI/local parity failures.

How capsem-gate works and how to add or change a gate command. Use when touching build, test, or release logic, or when a boundary/primitive/recursion/purity guard fails.

Capsem's small Just surface and its boundary with the Python gate. Use when adding or changing a recipe, or deciding whether logic belongs in Just or in a gate plan.

Setting up a Capsem dev environment from scratch. Use when onboarding, provisioning a machine, or troubleshooting environment and container-runtime issues.

Work with the Ambient Quality Agent (AQuA) added to this agents-cli project: augment the agents-cli agent with AQuA or attach the agent to an AQuA deployed elsewhere, read the quality insights it finds in production conversations, get AQuA's root-cause…

Run a custom investigation: review a chosen slice of conversations instead of a random sample, by writing a SQL selector over the observed agent's telemetry, and optionally narrow what the reviewer reports. Use when a message asks to investigate only certain…

Root-cause analysis of one AQuA insight against the observed agent's own source code. Use when a message names an insight and asks what the root cause is, how to fix it, why the agent behaved that way, or to diagnose a failure -- for example `Diagnose insight…

Creates product search agents with semantic search and RAG on Google Cloud (Vector Search on Gemini Enterprise Agent Platform, BigQuery, embeddings). Use when the user wants to "build a product search agent", "create an e-commerce search", "make a shopping…

Creates virtual try-on agents supporting image and video (catwalk animation) try-ons on Google Cloud (Gemini image models and Veo on Gemini Enterprise Agent Platform). Handles resource setup, user photo uploading, image/video generation pipelines, local…

Blog post writing skill with structure templates and style guidelines. Guides the agent through writing well-structured, engaging technical blog posts with proper formatting, section flow, and reader engagement techniques.

Content research and SEO writing methodology. Guides the agent through topic research, keyword identification, competitive analysis, and writing SEO-optimized content that ranks well and provides genuine value to readers.

Review a GitHub pull request and leave inline comments in a natural human reviewing voice, indistinguishable from comments typed by hand on the GitHub web UI. Deliberately bounded to defects a reader can settle by looking at the anchored line, rather than a…

Proactive security advisor and architectural remediation assistant for secure code development. Use to query threat models, historical vulnerability lineages, verified patch patterns, triaged false positives, and learned trajectory invariants before code…

Configures and validates Mantis pipeline environments, sandbox mechanisms, and AI models. Use to set up workflow.json, auto-detect host capabilities, switch between sandboxes (static-only, gvisor, microsandbox, gce), select AI models, and run fast 1-2s…

Launches automated vulnerability review campaigns on target files or repositories. Use to initiate Mantis vulnerability review pipelines with automated preflight checks, environment auto-configuration, and runtime overrides (sandboxes, models, endpoints).…

Consolidates raw security findings to eliminate redundant reports. Use when raw findings have been generated by the researcher and need consolidation before review. Don't use for initial code auditing or patch generation.

Interactively guides the design and implementation of custom deterministic orchestrator harnesses. Use when a user wants to build their own pipeline to wrap and run Mantis skills reliably. Don't use for executing the default pipeline directly.

Assesses the production viability of findings, filtering out debug-only features and assertion traps. Use when findings have been validated and you need to confirm they are triggerable in production release builds (with assertions disabled). Don't use for…

Generates and runs crash reproducers to verify security flaws. Use when viable findings exist and you need to write and execute a script or payload to verify the crash. Don't use for code auditing or patching.

Formulates a targeted defensive security reviewing plan based on the active threat model and historical learnings. Use when starting a security review campaign to map the codebase boundaries and generate a roadmap (workspace/plan.json). Don't use for…

Mandatory checks to run before completing any task that touches md files or dart code in this repository.

Instructions for adding a new validation rule and CLI flag to skills_lint. Use this skill when asked to create a new rule that validates aspects of skills (like frontmatter metadata).

Guidelines and format for writing pull request descriptions in this repository. Use this skill whenever the user asks you to draft a pull request description, submit a PR, or update a PR description.

Formats Dart code with dart format and fixes the lints that formatting can't. Use when a change fails the formatting check in CI.

Prepares and publishes a new version of a Dart package to pub.dev, from the version bump to the GitHub release. Use when asked to cut, tag or publish a release.

Sorts new GitHub issues by type and priority, asks for missing details, and closes duplicates. Use when asked to triage, label or clean up the issue tracker.

How to add a test that enforces a convention on this repository's own code, docs or config, such as a rule about imports, file layout, comments or CHANGELOG entries. Use when asked to add or extend a convention, hygiene or consistency check that scans the…

Executes AI agent skill evaluations with staged execution pipelines and data-driven discovery. Requires a reserved keyword (content, triggers, audit, all, help); running without arguments displays the CLI usage guide.

Explains how the ADK runtime fits together: the node and graph execution model, Context and Event flow, checkpoint and resume, tracing, and the rules governing the public API surface. Use when answering "how does X work" about ADK internals, tracing where an…

Reviews the uncommitted changes in an adk-python working tree and reports correctness, design, public-API stability, test, sample and documentation gaps as a prioritized findings report, fixing them only when asked. Use when the user asks to review local…

Python style and codebase conventions for ADK (Agent Development Kit): private-by-default file visibility, imports, type hints, Pydantic v2 models, formatting, docstrings, logging, async I/O, file and test layout, and unit test structure. Use when writing or…

Leverages BigQuery's built-in machine learning and GenAI capabilities for advanced data analytics. Use when you need to write SQL queries that perform time-series forecasting, predict values, detect outliers or anomalies, find key drivers, perform semantic…

Sets up a local ADK Python development environment in a git clone of the open-source adk-python repository: a uv virtual environment, all dependency extras, pre-commit hooks, and a first unit-test run. Runs only when explicitly requested, never on its own.…

Builds ADK (Agent Development Kit) Python agents: LLM agents with tools, graph workflows of function and agent nodes, conditional routing, fan-out and join, schema-validated delegation between agents, human-in-the-loop pauses, and pytest coverage for all of…

Writes a hands-on developer guide for one ADK code unit — a minimal runnable example, how it works, a configuration-option table, advanced uses, limitations, and links to related samples — to `docs/guides/{topic}/{unit}/index.md`, then lists it in the index…

Diagnoses misbehaving ADK agents by inspecting sessions, events, tool calls, and the exact request that reached the model. Covers the `adk run` CLI and the `adk web` dev server with its session, trace, and debug HTTP endpoints. Use when an agent returns the…

Translates a common phrase into one or more languages.

Builds ADK Kotlin agents: LlmAgent with instructions and tools, @Tool function tools generated by KSP, hand-written tools, agent-as-tool and MCP, Sequential / Parallel / Loop agents and LLM transfer between sub-agents, callbacks and plugins, session state,…

Sets up ADK Kotlin: either a consumer project that depends on the published com.google.adk artifacts (Gradle or Maven coordinates, KSP wiring for the @Tool processor, Kotlin / JDK / Android floors) or a contributor checkout of the adk-kotlin repository…

Casts a fireball at a specified target.

Summons a magical creature to assist you.

A skill living directly under the assets root.

Description 1

Description 2

Standard verification pipeline to execute after modifying C++ source or header files. Use this skill to format includes, build the engine, and run core tests.

Guidelines and SOP for synchronizing public C++ API changes (methods, enums, options structs) to Java (Android JNI) and JavaScript/TypeScript (Web/WASM Embind).

Clean and build Filament targets for development, debugging, and production. Use this skill whenever you need to clean the workspace or compile desktop targets.

Cherry-pick a commit onto another branch and open the PR. Use when the user asks to cherry-pick or backport a commit or PR to a release branch.

Adversarial systems, concurrency, memory-model, and architecture code review protocol. Use this skill whenever asked to review code, PRs, diffs, or branches in Filament.

Enforce C++ static thread safety annotations and correct synchronization primitives. Use this skill when designing multi-threaded classes or editing guarded member fields.

Build, deploy, run, and benchmark Filament binaries on connected Android devices or emulators. Use this skill for compiling, pushing, and executing Android tests or benchmarks.

Enforce correct Filament object creation and destruction lifecycles. Use this skill when initializing rendering pipelines or allocating/deallocating GPU buffers and entities.

Run and interpret the unified A/B Lightflow benchmark (benchmarks/run_benchmark.py) comparing Arm A (Lightflow DAG) against Arm B (Traditional Skill) across 7 matched domain workflow pairs (3 to 22 stages).

Spawn a detached background export job, poll its status file until READY, verify the exported artifact checksum, and always clean up temporary status files using examples/async_job_watcher/actions.py.

Run an 8-stage blue/green canary release with parallel validation, green slot warmup polling, an operator cutover gate, automatic canary traffic rollback on SLO failure, surgical recovery, green promotion, and old-slot decommission.

Fetch top Hacker News stories, pause for human editorial approval, and publish a curated Markdown digest using examples/hn_digest/actions.py.

Run a 9-stage regional primary database failover with outage confirmation, failover candidate election, conditional WAL lag replay vs. zero-loss sync verification, STONITH fencing join, Incident Commander approval gate, standby promotion, connection-pooler…

Audit pinned Python dependencies against PyPI, pause for operator approval, apply upgrades with automatic rollback on smoke-test failure, and recover without re-auditing using examples/pypi_upgrade_guard/actions.py.

Execute the 22-stage multi-branch Kubernetes, Cloud IAM, KMS, and ArgoCD GitOps tenant onboarding workflow using examples/tenant_gitops_onboarding/actions.py.

Poll the USGS M4.5+ earthquake feed, conditionally pause for Incident Commander triage when magnitude >= 5.0, and emit an incident bulletin using examples/usgs_seismic_alert/actions.py.

Use when working in this project — adding tools, editing the agent, running, evaluating, serving or deploying it — or when guidance mentions ADK, LlmAgent, google.adk, adk web, or an ADK runner. This project is LangChain/LangGraph scaffolded by agents-cli, so…

This skill should be used when the user wants to "write agent code", "build an agent with ADK", "add a tool", "create a callback", "define an agent", "use state management" — in a project that needs ADK (Agent Development Kit) API patterns and code examples.…

This skill should be used when the user wants to "deploy an agent", "deploy my ADK agent", "set up CI/CD", "configure secrets", "troubleshoot a deployment", or needs guidance on Agent Runtime, Cloud Run, or GKE deployment targets, or binding an agent to an…

This skill should be used when the user wants to "run an evaluation", "evaluate my agent", "evaluate my ADK agent", "write an eval dataset", "analyze eval failures", "compare eval results", "optimize agent", or needs guidance on the Agent Platform eval…

This skill should be used when the user wants to "set up tracing", "monitor my agent", "configure logging", "add observability", "debug production traffic", or needs guidance on monitoring deployed agents, including ADK (Agent Development Kit) agents. Covers…

This skill should be used when the user wants to "publish an agent", "publish my ADK agent", "register an agent with Gemini Enterprise", "publish to Gemini Enterprise", or needs guidance on the agents-cli publish gemini-enterprise command. Also use when the…

This skill should be used when the user wants to "create an agent project", "start a new ADK project", "build me a new agent", "add CI/CD to my project", "add deployment", "enhance my project", or "upgrade my project". Part of the agents-cli skills suite.…

This skill should be used when the user wants to "develop an agent", "build an agent using ADK", "run the agent locally", "debug agent code", "test an agent", "deploy an agent", "publish an agent", "monitor an agent", or needs the ADK (Agent Development Kit)…

Develop, modify, build, test, or validate code in google/zerocopy's zerocopy crate and its derive crate. Use for implementation work, compiler-version gating, generated macro code, UI or compile-fail tests, test placement, linting, feature-gate validation,…

Review proposed changes to google/zerocopy's zerocopy crate and derive crate. Use for pull-request, patch, or diff review where findings should account for zerocopy's correctness, compatibility, testing, maintainability, known merge-blocking placeholders and…

Author, document, review, audit, or redesign unsafe Rust with proof-grade rigor. Use for unsafe blocks and functions, unsafe traits and impls, raw pointers, FFI, inline assembly, intrinsics, layout or validity reasoning, concurrency and atomics, SIMD and…

Author, document, review, audit, or redesign unsafe Rust with proof-grade rigor. Use for unsafe blocks and functions, unsafe traits and impls, raw pointers, FFI, inline assembly, intrinsics, layout or validity reasoning, concurrency and atomics, SIMD and…

Author, document, review, audit, or redesign unsafe Rust with proof-grade rigor. Use for unsafe blocks and functions, unsafe traits and impls, raw pointers, FFI, inline assembly, intrinsics, layout or validity reasoning, concurrency and atomics, SIMD and…

Author, document, review, audit, or redesign unsafe Rust with proof-grade rigor. Use for unsafe blocks and functions, unsafe traits and impls, raw pointers, FFI, inline assembly, intrinsics, layout or validity reasoning, concurrency and atomics, SIMD and…

Author, document, review, or audit unsafe Rust with proof-grade rigor. Use for unsafe blocks and functions, unsafe traits and impls, raw pointers, FFI, inline assembly, intrinsics, layout or validity reasoning, concurrency and atomics, SIMD and target…

Author, document, review, audit, or redesign unsafe Rust with proof-grade rigor. Use for unsafe blocks and functions, unsafe traits and impls, raw pointers, FFI, inline assembly, intrinsics, layout or validity reasoning, concurrency and atomics, SIMD and…

Design and implement XR Blocks interactions. Use when adding selection, hover, direct touch, grab, gestures, event ownership, propagation, automatic manipulation, or physics-driven object behavior.

Build spatial UI in XR Blocks. Use when adding cards, overlays, panels, text, controls, model-viewer interfaces, layout, styling, themes, or UI placement with the built-in UI system.

Add AI behavior to an XR Blocks application. Use when implementing Gemini or OpenAI queries, Gemini Live voice or vision, generated images, scene-grounded responses, or model-requested tools with an observable XR outcome.

Connect physical-world sensing to XR Blocks application state. Use when adding planes, scene meshes, depth, occlusion, world collision evidence, object or human recognition, face tracking, segmentation, or agent-facing scene context.

Build or extend a complete XR Blocks application. Use when the request concerns an app scaffold, a whole experience, several SDK areas, or an end-to-end simulator or XR handoff rather than one focused subsystem.

Complete an XR Blocks SDK change across implementation, runtime wiring, public exports, proof, build output, examples, and canonical documentation. Use when editing the XR Blocks repository rather than an application that consumes it.

Debug and repair XR Blocks applications. Use when an app fails to build or run, produces incorrect UI, interaction, sensing, or rendering behavior, differs between simulator and device, leaks resources, or contains obsolete SDK patterns.

Pin content to a real place with WebXR spatial anchors, and bring it back in a later session. Use when virtual content must stay put as the headset refines its map of the room, or when an app should remember where things were left. Covers `enableAnchors()`,…