Agent Workflow Skills

Google Model Armor: Sanitize a user prompt through a Model Armor template.

Evaluates agent skills against Anthropic's best practices. Use when asked to review, evaluate, assess, or audit a skill for quality. Analyzes SKILL.md structure, naming conventions, description quality, content organization, and identifies anti-patterns. Produces actionable improvement recommendations.

This skill should be used when the user asks to "model agent mental states", "implement BDI architecture", "create belief-desire-intention models", "transform RDF to beliefs", "build cognitive agent", or mentions BDI ontology, mental state modeling, rational agency, or neuro-symbolic AI integration.

This skill should be used when the user asks to "compress context", "summarize conversation history", "implement compaction", "reduce token usage", or mentions context compression, structured summarization, tokens-per-task optimization, or long-running agent sessions exceeding context limits.

This skill should be used when the user asks to "diagnose context problems", "fix lost-in-middle issues", "debug agent failures", "understand context poisoning", or mentions context degradation, attention patterns, context clash, context confusion, or agent performance degradation. Provides patterns for recognizing and mitigating context failures.

This skill should be used when the user asks to "understand context", "explain context windows", "design agent architecture", "debug context issues", "optimize context usage", or discusses context components, attention mechanics, progressive disclosure, or context budgeting. Provides foundational understanding of context engineering for AI agent systems.

Use when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies

This skill should be used when the user asks to "evaluate agent performance", "build test framework", "measure agent quality", "create evaluation rubrics", or mentions LLM-as-judge, multi-dimensional evaluation, agent testing, or quality gates for agent pipelines.

This skill should be used when the user asks to "offload context to files", "implement dynamic context discovery", "use filesystem for agent memory", "reduce context window bloat", or mentions file-based context management, tool output persistence, agent scratch pads, or just-in-time context loading.

This skill should be used when the user asks to "build background agent", "create hosted coding agent", "set up sandboxed execution", "implement multiplayer agent", or mentions background agents, sandboxed VMs, agent infrastructure, Modal sandboxes, self-spawning agents, or remote coding environments.

> Guides implementation of agent memory systems, compares production frameworks (Mem0, Zep/Graphiti, Letta, LangMem, Cognee), and designs persistence architectures for cross-session knowledge retention. Use when the user asks to "implement agent memory", "persist state across sessions", "build knowledge graph for agents", "track entities over time", "add long-term memory", "choose a memory framework", or mentions temporal knowledge graphs, vector stores, entity memory, adaptive memory, dynamic memory or memory benchmarks (LoCoMo, LongMemEval).

This skill should be used when the user asks to "design multi-agent system", "implement supervisor pattern", "create swarm architecture", "coordinate multiple agents", or mentions multi-agent patterns, context isolation, agent handoffs, sub-agents, or parallel agent execution.

This skill should be used when the user asks to "start an LLM project", "design batch pipeline", "evaluate task-model fit", "structure agent project", or mentions pipeline architecture, agent-assisted development, cost estimation, or choosing between LLM and traditional approaches.

Use when executing implementation plans with independent tasks in the current session

This skill should be used when the user asks to "design agent tools", "create tool descriptions", "reduce tool complexity", "implement MCP tools", or mentions tool consolidation, architectural reduction, tool naming conventions, or agent-tool interfaces.

Public main skill for the RenderDoc/RDC GPU debugger framework. Use when the user wants defect diagnosis, root-cause analysis, regression explanation, or fix verification for a GPU rendering issue from one or more `.rdc` captures. This skill owns intent gate classification, preflight, missing-input collection, intake normalization, and the handoff into `team_lead`; it is the only framework classifier and the normal user-facing entry instead of sending users directly to specialist roles.

Contract-First Map-Reduce coordination protocol for native TeamCreate multi-agent teams. Wraps TeamCreate, Task (teammates), SendMessage with an upfront shared contract phase that eliminates 75% of integration errors. Based on 400+ experiment research proving 52.5% quality improvement over naive coordination.

Optimize prompts for better AI responses. Use when user asks to improve a prompt, refine a prompt, make a prompt better, optimize prompting, review their prompt, or says "/improve-prompt". Transforms vague requests into clear, specific, actionable prompts.

Second test skill

Maintains Defold agent skills. Use when asked to update link lists in api-fetch/docs-fetch/examples-fetch skills, create or update proto file references, or fetch proto schemas.

Transform user requests into detailed, precise prompts for AI models. Use when users say "promptify", "promptify this", or explicitly request prompt engineering or improvement of their request for better AI responses.

Build production-ready AI agents using Google's Agent Development Kit with Claude integration, React patterns, multi-agent orchestration, and comprehensive tool libraries

| Use when appropriate context detected. Trigger with relevant phrases based on skill purpose.

| Execute this skill should be used when the user asks about "SPAWN REQUEST format", "agent reports", "agent coordination", "parallel agents", "report format", "agent communication", or needs to understand how agents coordinate within the sprint system. Use when appropriate context detected. Trigger with relevant phrases based on skill purpose.

| This skill optimizes prompts for Large Language Models (LLMs) to reduce token usage, lower costs, and improve performance. It analyzes the prompt, identifies areas for simplification and redundancy removal, and rewrites the prompt to be more concise and effective. It is used when the user wants to reduce LLM costs, improve response speed, or enhance the quality of LLM outputs by optimizing the prompt. Trigger terms include "optimize prompt", "reduce LLM cost", "improve prompt performance", "rewrite prompt", "prompt optimization".

| This skill enables Claude to orchestrate multi-agent systems using the AI SDK v5. It allows Claude to set up agent handoffs, intelligent routing, and coordinated workflows across different AI providers like OpenAI, Anthropic, and Google. Use this skill when the user asks to create multi-agent systems, needs help with agent coordination, task routing, or wants to build complex workflows involving specialized agents. It is triggered by phrases like "multi-agent system", "agent orchestration", "agent handoff", "intelligent routing", or "coordinate agents".

| Debug complex Claude API issues including context window overflow, tool use failures, streaming corruption, and response quality problems. Trigger with phrases like "anthropic advanced debug", "claude complex issue", "claude tool use failing", "claude context overflow".

| Optimize Claude API performance with prompt caching, model selection, streaming, and latency reduction techniques. Use when experiencing slow responses, optimizing token usage, or reducing time-to-first-token in production. Trigger with phrases like "anthropic performance", "claude speed", "optimize claude latency", "anthropic caching", "faster claude responses".

| Handle sensitive data with Claude — PII redaction, conversation management, Use when working with data-handling patterns. context window optimization, and data retention policies. Trigger with "anthropic data privacy", "claude pii", "anthropic context window", "manage claude conversations", "anthropic data retention".

| Build Claude Code plugins — skills, agents, MCP servers, hooks, and slash commands. Use when working with reference-architecture patterns. The complete guide to extending Claude Code with the Anthropic plugin system. Trigger with "claude code plugin", "build a skill", "create mcp server", "anthropic plugin architecture", "claude code hooks".

| orchestration. Triggers on "advanced composer", "composer patterns", "multi-file generation", "composer refactoring", "agent mode", "parallel agents".

| Optimize context window usage in Cursor with @-mentions, context pills, and conversation strategy. Triggers on "cursor context", "context window", "context limit", "cursor memory", "context management", "@-mentions", "context pills".

| Create effective custom prompts for Cursor AI using project rules, prompt engineering patterns, and reusable templates. Triggers on "cursor prompts", "prompt engineering cursor", "better cursor prompts", "cursor instructions", "cursor prompt templates".

| Manages Firebase/Firestore operations including CRUD, queries, batch processing, A2A agent communication, MCP server integration, and Cloud Run service coordination. Activates when you request "firestore operations", "create firestore document", "query firestore", "A2A agent communication", "MCP server setup", "agent-to-agent messaging", or "Cloud Run firestore integration". Handles both basic database operations for regular users and advanced A2A framework patterns for AI agents.

| Manage multi-agent orchestrator for Claude Code. Use when user mentions gastown, gas town, gt commands, bd commands, convoys, polecats, crew, rigs, slinging work, multi-agent coordination, beads, hooks, molecules, workflows, the witness, the mayor, the refinery, the deacon, dogs, escalation, or wants to run multiple AI agents on projects simultaneously. Handles installation, workspace setup, work tracking, agent lifecycle, crash recovery, and all gt/bd CLI operations. Trigger with phrases like "gas town", "gt sling", "fire up the engine".

| Execute automatic activation for all google cloud agent development kit (adk) Use when appropriate context detected. Trigger with relevant phrases based on skill purpose.

| Persistent context management for Claude Code sessions. Save, load, update, share, and audit session memory via MEMORY.md. Prevents context loss on compaction or session restart. Use when starting a session, before compaction, syncing context across teammates, or pruning stale memory entries. Trigger with "save memory", "load memory", "memory audit", "memory share".

| Execute this skill optimizes prompts for large language models (llms) to reduce token usage, lower costs, and improve performance. it analyzes the prompt, identifies areas for simplification and redundancy removal, and rewrites the prompt to be more conci... Use when optimizing performance. Trigger with phrases like 'optimize', 'performance', or 'speed up'.

| Execute orchestrate multi-agent systems with handoffs, routing, and workflows across AI providers. Use when building complex AI systems requiring agent collaboration, task delegation, or workflow coordination. Trigger with phrases like "create multi-agent system", "orchestrate agents", or "coordinate agent workflows".

Analyzes existing plugins to extract their capabilities, then adapts and applies those skills to the current task. Acts as a universal skill chameleon that learns from other plugins.

| This skill enables Claude to check session security implementations within a codebase. It analyzes session management practices to identify potential vulnerabilities. Use this skill when a user requests to "check session security", "audit session handling", "review session implementation", or asks about "session security best practices" in their code. It helps identify issues like insecure session IDs, lack of proper session expiration, or insufficient protection against session fixation attacks. This skill leverages the session-security-checker plugin. Activates when you request "checking session security" functionality.

| Execute analyzes existing plugins to extract their capabilities, then adapts and applies those skills to the current task. Acts as a universal skill chameleon that learns from other plugins. Activates when you request "skill adapter" functionality. Use when appropriate context detected. Trigger with relevant phrases based on skill purpose.

| This skill enables Claude to orchestrate complex test workflows using the test-orchestrator plugin. It allows Claude to define test execution graphs with dependencies, execute tests in parallel, and intelligently select tests to run based on code changes. Use this skill when a user requests test orchestration, dependency management for tests, parallel test execution, smart test selection, or CI/CD integration for testing. Trigger terms include "orchestrate tests", "test workflow", "parallel testing", "smart test selection", "test dependencies", and "/orchestrate".