GoogleCloudPlatform/professional-services
Skill Claude CodeCodex
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…
GoogleCloudPlatform/professional-services
Skill Claude CodeCodex
Executes 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 delta comparisons (--compare-to), and optimizes system…
GoogleCloudPlatform/professional-services
Skill Claude CodeCodex needs its repo
Performs an exhaustive, question-by-question narrative diagnostic breakdown of an agent-eval benchmark run by analyzing questionanswerlog.md, evalsummary.json, and raw trajectory traces. Use when diagnosing low score causes, investigating the Memory Reuse vs. Traceability rubric clash, performing pre-release failure…
Hook Claude Code
One of 9 in settings.json
Runs when a session starts, running sciontool hook --dialect=claude. From GoogleCloudPlatform/scion.
Hook Claude Code
One of 9 in settings.json
Runs when a session ends, running sciontool hook --dialect=claude. From GoogleCloudPlatform/scion.
Hook Claude Code
One of 9 in settings.json
Runs when you submit a prompt, before the agent sees it, running sciontool hook --dialect=claude. From GoogleCloudPlatform/scion.
Hook Claude Code
One of 9 in settings.json
Runs when the agent finishes a response, running sciontool hook --dialect=claude. From GoogleCloudPlatform/scion.
Hook Claude Code
One of 9 in settings.json
Runs when a subagent finishes, running sciontool hook --dialect=claude. From GoogleCloudPlatform/scion.
Hook Claude Code
One of 9 in settings.json
Runs before the agent uses a tool, running sciontool hook --dialect=claude. From GoogleCloudPlatform/scion.
Hook Claude Code
One of 9 in settings.json
Runs after a tool call finishes, running sciontool hook --dialect=claude. From GoogleCloudPlatform/scion.
Hook Claude Code
One of 9 in settings.json
Runs when the agent sends a notification for ToolPermission tool calls, running sciontool hook --dialect=claude. From GoogleCloudPlatform/scion.
Settings file Claude Code
One of 9 in settings.json
Agent settings declaring 8 hook events (SessionStart, SessionEnd, UserPromptSubmit, Stop) and 1 allowed tools.
Skill Claude CodeCodex
Uses 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.
Skill Claude CodeCodex
Git 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.
Skill Claude CodeCodex
Git 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.
Skill Claude CodeCodex
Manage concurrent LLM-based code agents with scion - orchestrate parallel agents with isolated workspaces, troubleshoot and recover stuck agents.
Skill Claude CodeCodex
Operational constraints for Scion agents running in containerized sandboxes. Covers prohibited commands and hub-only API access. Complements the scion CLI reference and messaging skills.
Skill Claude CodeCodex
How to use the scion message command effectively. Use this for communication with other agents or users. Covers recipient types, message timing, content best practices, and special message flags.
Skill Claude CodeCodex
Schedule 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.
Skill Claude CodeCodex
Create 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 new roles to an existing team, modifying workflows, or…
Skill Claude CodeCodex
How to use the scion conversation command for managing conversations. Covers listing, creating, viewing, participant management, and message retrieval. Complements the scion-messaging skill.
GoogleCloudPlatform/vertex-ai-samples
Skill Claude CodeCodex
Guides 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, tools, multimedia generation, caching, and batch prediction.
GoogleCloudPlatform/vertex-ai-samples
Skill Claude CodeCodex
Generates 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 session setup/resumption, bearer token refresh, and…
GoogleCloudPlatform/vertex-ai-samples
Skill Claude CodeCodex
Evaluate 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 client.evals.evaluate(), and analyzes results to suggest concrete…
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: