call-claude
Delegate a prompt to Claude via `claude -p`. Use when the user wants to offload a task to Claude from another agent (Codex, Cursor, another Claude session),…
Find an Agent Skill for your task. Read the guide and copy the install command.
Updated 11-05 00:16
25,651 results
Delegate a prompt to Claude via `claude -p`. Use when the user wants to offload a task to Claude from another agent (Codex, Cursor, another Claude session),…
Request a second-model consultation with explicit API, browser, or render transport and per-run provenance. Use when transport choice or model/effort evidence…
Direct a team of agents or take over an existing multi-agent run, preserving user priorities through assignments, review, and handoff. Use when asked to…
A fast Rust-based headless browser automation CLI with Node.js fallback that enables AI agents to navigate, click, type, and snapshot pages via structured…
Analyze and improve prompts using Claude's official prompting best practices. Use this skill whenever the user wants to improve, refine, review, or optimize a…
PUA off alias for Codex. Codex subcommand mapping for Claude Code /pua:off style usage; invoke with $pua-off.
AI voice assistants with custom instructions, knowledge bases, and tool integrations.
Access Telnyx LLM inference APIs, embeddings, and AI analytics for call insights and summaries. This skill provides REST API (curl) examples.
Manage cloud storage buckets and objects using the S3-compatible Telnyx Storage API. This skill provides Ruby SDK examples.
Create and manage video rooms for real-time video communication and conferencing. This skill provides Go SDK examples.
Collect DTMF input and speech from callers using standard gather or AI-powered gather. Build interactive voice menus and AI voice assistants. This skill…
Implement every issue in a batch or GitHub milestone one at a time, using a fresh subagent for each issue and either one combined PR or one PR per issue.
Full Karpathy-inspired agentic coding guidance. Use when writing, reviewing, or delegating code and you need stricter control over assumptions, autonomy,…
Hand local work to a shared OpenClaw Gateway: start a worktree session there as yourself in one request, seeded with a handoff, and get the session URL back.
React composition patterns that scale. Use when refactoring components with boolean prop proliferation, building flexible component libraries, or designing…
Review docs/prose for Writing Guidelines compliance. Use when asked to "review my docs", "check writing style", "audit prose", "review docs voice and tone", or…
Deploy and integrate local LLMs with Ollama, LocalAI, and Home Assistant for privacy-focused voice assistants and automation.
Implement and debug RealityKit animation, character controllers, skeletal poses, IK, body tracking, blendshapes, animation graphs, retargeting, root motion,…
Design, implement, and debug custom RealityKit components, systems, ECS queries, component registration, update loops, Codable component state, and per-frame…
Use when connecting a remote Hermes gateway to Buzz end-to-end. Do not use for a Buzz-managed ACP runtime; use the official buzz-acp relay-bridge guide instead.
Import local Claude Code or Codex conversation history into OpenClaw memory. Triggers when: user asks to "导入" Claude/Codex conversations or chat logs, migrate…
Use when starting any work session - establishes autonomous operation mode, overriding token limits and time pressure to work until goal is achieved
Use when implementing features or fixes - test-driven development with RED-GREEN-REFACTOR cycle and full code coverage requirement
Use the Elaichi MCP server well — find a connected tool with search_tools, run it with execute_tool or run_code, pick the right account, read a refusal or…