Loading...
Loading...
Found 830 Skills
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.
Adopt multiple expert personas sequentially for complex problem analysis from diverse perspectives. Single-agent only — do NOT spawn sub-agents.
Official Notion Model Context Protocol Server for workspace interaction.
N coordinated agents on shared task list (compatibility facade over team)
Structured checkpoint format for requesting human input. When an agent needs a decision, it must stop, present context, show options, and wait. Activate when delegating to subagents, running background tasks, or hitting any decision point that requires human judgment.
File-based knowledge persistence patterns: when to store discoveries, when to recall past solutions, and how to organize project memory. Activate when starting tasks, encountering errors, making decisions, or when context may be lost between sessions.
Determine the escalation path (Researcher vs. Human) and format the appropriate handoff. Used when the fix-engine has exhausted retry attempts.
Generate professional Agent Skills for Claude Code and other AI agents. Creates complete skill packages with SKILL.md, references, scripts, and templates. Use when creating new skills, generating custom slash commands, or building reusable AI capabilities. Validates against Agent Skills specification.