Loading...
Loading...
Found 1,141 Skills
Interactive planning and execution for complex tasks. Use when user asks to use or invoke planner skill.
Use this skill when the user wants any MCP-capable agent or IDE assistant to interact with Google ADK agents through the adk-agent-extension MCP server. Trigger for requests like wiring ADK tools into Codex/Claude Code/Cursor/Cline/Gemini, registering a stdio MCP server, listing ADK servers/agents, creating sessions, and chatting with ADK agents.
DEPRECATED - Use chatkit-backend skill instead. SSE streaming is now part of the chatkit-backend skill for ChatKit integration.
Controls InnerClaude instances on Sprites.dev VMs for testing workflows, install patterns, and Claude-to-Claude interaction. INVOKE BEFORE any 'sprite exec', 'inner Claude', 'test this workflow', 'Claude controlling Claude', or remote VM operations. Documents the critical tmux+pipe-pane pattern that makes OuterClaude/InnerClaude interaction work. Also covers checkpoint/restore and bootstrap. (user)
Generates custom Claude Code subagents with specialized expertise. Activates when user wants to create a subagent, specialized agent, or task-specific AI assistant. Creates properly formatted .md files with YAML frontmatter, suggests tool restrictions and model selection, generates effective system prompts. Use when user mentions "create subagent", "new agent", "specialized agent", "task-specific agent", or wants isolated context for domain-specific work.
This skill should be used when the user asks to "deploy to castari", "deploy my agent", "deploy agent to production", "castari deploy", "push agent to castari", "ship my agent", "set up castari", or needs help with Castari CLI installation, authentication, agent scaffolding, or deployment to cloud sandboxes.
No Polling for Background Agents
Build automated evaluation suites for AI agents using golden datasets, rubrics, and regression gates.
General RPI (Research, Plan, Implement, Iterate) execution skill. It is used for engineering tasks where users require "research first, then plan, then implement, and finally iterate", or when tasks are highly complex, high-risk, or have unclear impact. This skill does not rely on specific command-line tools or platforms, and is applicable to any AI Agent that supports skill mechanisms.
Ensure AI agents work in an isolated Git worktree to prevent changes to the main working directory. Use when AI is about to make its first code modification in a session, or when the user requests isolated/safe editing. Triggers include starting to edit files, implementing features, or fixing bugs.
Adopt multiple expert personas sequentially for complex problem analysis from diverse perspectives. Single-agent only — do NOT spawn sub-agents.
Guide for creating Agent Skills: structure, best practices, and SKILL.md format for Claude Code, Codex, Gemini CLI, and other AI agents.