MCP App StoreMCP App Store
from openclaw-master-skills2,046
Initiate real-time video calls with a custom AI avatar (Runway Characters) that opens the conversation and returns a transcript and recording for follow-up.
This skill lets an agent create and manage real-time video call sessions using Runway's Characters API. The agent can create a persistent custom avatar (voice, personality, reference image), update the avatar with call-specific context, generate a call invite (local or tunnel URL), wait for the call to finish, and retrieve the transcript and recording for post-call actions. Typical uses include urgent alerts, standups, complex explanations, and decision meetings where real-time conversation is faster than text.
Use for scenarios that benefit from voice/video and human-like presence: CI/ops alerts that need quick confirmation, daily or ad-hoc standups, walkthroughs of complex bugs or architecture, or any situation where a short face-to-face conversation reduces miscommunication. Avoid for simple notifications or one-line updates.
This skill is best suited to agents that can run local processes and HTTP requests (OpenClaw-style agents using Node/npm runtimes). It assumes access to Node/npm and a RUNWAYML_API_SECRET environment variable for server-side avatar creation and call orchestration.
Video Call Agent enables real-time AI avatar video calls via Runway Characters API. The SKILL.md is comprehensive with detailed setup, avatar creation, call flow, and API reference. No bundled scripts — relies entirely on external npm package (openclaw-video-call) and curl commands. Privacy section is a nice touch. Skill is well-documented but narrowly targets users with Runway API access.
npx execution of external npm package without checksum is a minor security consideration. All API endpoints are legitimate (Runway + localhost). SKILL.md is lengthy (~4K words) — voice/avatar preset tables could be moved to references/ for leaner SKILL.md.
Prompt Engineering Patterns
A practical collection of prompt engineering techniques and patterns for building reliable, controllable LLM prompts: CoT, few-shot, structured outputs, templat
Popup CRO
Design and optimize popups, modals, banners, and slide-ins to increase conversions without harming user experience or SEO.
Bagman — Secure Key Management
Secure key-management patterns and operational guardrails for AI agents that need to handle private keys, session keys, and secrets safely.
Atlassian Confluence Expert
Manage Confluence spaces, templates, permissions, and documentation workflows; create page hierarchies, macros, and templates for knowledge bases.
Superfluid Protocol Knowledge Base
Comprehensive developer-oriented reference for Superfluid Protocol: ABIs, forwarders, SDKs, automation, and common gotchas for building streaming-money apps.
JACS Cryptographic Provenance
Post-quantum cryptographic signing and verification for agents: sign documents, verify provenance, claim HAI.ai usernames, and send/receive signed email.
KIPRIS CLI
CLI wrapper around KIPRIS Plus OpenAPI to fetch Korean patents, trademarks, and designs and return normalized JSONL for agent consumption.
listenhub
Explain anything — turn ideas into podcasts, explainer videos, or voice narration. Use when the user wants to "make a podcast", "create an explainer video", ...
InkOS - Autonomous Novel Writer
CLI agent for end-to-end fiction writing: draft, audit (33-dimension), revise, import/export and multi-genre support (English & Chinese).
ATXP — Agent Infrastructure & Paid Tools
Provides agents a funded identity (wallet, email) plus paid API tools: web search, image/video/music generation, SMS/voice, email, and an LLM gateway — useful w
Sandbox0 Integration
Guidance and templates for integrating Sandbox0 sandboxing into AI agents — CLI/SDK patterns, templates, volumes, network policy, and deployment choices.
Monitoring Stack Deployer
Deploy and configure production-ready monitoring stacks (Prometheus, Grafana, Datadog) with collectors, dashboards, and alerting rules for Kubernetes, Docker, o
Skill Retro
Analyze a session's skill invocations to surface performance issues and recommend or apply improvements using the skill-creator workflow.
NotebookLM Research Agent
End-to-end research-to-content pipeline: ingest sources into Google NotebookLM, run deep cited research, generate downloadable artifacts, and produce polished c
Call — Voice conversations with Claude
Enable voice calls with Claude (Opus) to discuss a project's code and context, supporting inbound and outbound calls and automatic transcript saving.
Picnic Grocery Ordering
Use the picnic CLI to search products, manage a shopping cart, and schedule delivery slots for Picnic supermarket (DE/NL).
Zylos Shell Channel
Channel skill that connects a CLI REPL to a Claude-like backend via a Unix socket, routing user input to the agent and delivering responses back to the REPL.
Runway Prod Checklist
Production checklist and SDK patterns for integrating Runway (AI video/image generation) into production workflows.