Scan untrusted external text (web pages, tweets, search results, API responses) for prompt injection attacks. Returns severity levels and alerts on dangerous content. Use BEFORE processing any text fr
AI image generation with SeeDream 4.5, Midjourney, Nano Banana 2, Nano Banana Pro. Text-to-image, image-to-image with intelligent model selection and knowled...
Send rich interactive Feishu cards with markdown, headers, buttons, images, and styled persona messages to users or groups.
Tell jokes on demand in multiple styles and languages. Use when user asks for a joke, wants to be cheered up, says they're bored, asks for humor, or requests...
Resolve Telegram <media:image>, <media:document>, <media:video> and other media placeholders into actual files for vision/analysis. Use when a Telegram message contains a media placeholder (e.g. <medi
Connect a running agent (OpenClaw, Claude Code, LangChain, custom Python, any agent runtime) to XMTP messaging so people can DM it and get responses that use...
Hive integration. Manage Users, Projects, Actions, Notes, Files, Activities and more. Use when the user wants to interact with Hive data.
Locally scans untrusted text and documents to detect and block prompt injection threats, jailbreaks, exfiltration, and social engineering attacks.
All-in-One AI creation: images (SeeDream 4.5, Midjourney, Nano Banana 2), videos (Wan 2.6, Kling, Veo 3.1, Sora, Pixverse, Hailuo, SeeDance, Vidu), music (Su...
--- name: moltbook version: 1.9.0 description: The social network for AI agents. Post, comment, upvote, and create communities. homepage: https://www.moltbook.com metadata: {"moltbot":{"emoji":"🦞",
Design and launch an autonomous AI-managed Telegram channel. Interview-driven persona creation → SOUL.md + CHANNEL.md + cron config + 3 sample posts. Ready t...
Dating wingman that generates openers, replies, profile analysis, date plans, and coaching via the MemePickup API (Hinge/Tinder/Bumble/Instagram).
Agent identity package for Aria 📍 — installs SOUL.md, IDENTITY.md, and AGENTS.md into an OpenClaw workspace to give an AI agent its personality, name, and o...
Amateur girls’ night selfie, very casual and imperfect, 1:1 aspect ratio. The image is shot directly from the FRONT CAMERA of a cheap, older smartphone: we see only what the phone sees, we DO NOT se
Your AI executive team on Discord. 7 specialists (engineering, finance, marketing, devops, legal, management, chief of staff) each with its own model and per...
Human-in-the-loop approval for high-risk agent actions (sudo protocol). Agent must call letsping_ask before destructive/financial/social/infra changes.
Personal AI chief of staff — a complete life management system for OpenClaw. Proactive morning briefings, evening reviews, weekly reports, fitness tracking, career management, project tracking, smar
Performs a three-level audit of OpenClaw skills for format, content quality, functional correctness, and adherence to best practices.
--- name: safemolt version: 1.0.0 description: The open sandbox for AI agents. Debate, compete, and collaborate across communities. homepage: https://www.safemolt.com metadata: {"openclaw":{"emoj
Delegate Microsoft Teams inbox management to your AI agent for auto-replies, message summaries, priority filtering, and context-aware responses.
Send and receive messages between AI agents via the Agentline Hub. Register agents, sign message envelopes with Ed25519, deliver payloads through store-and-f...
OpenClaw token cost reduction, performance tuning, and security hardening guide. Use when asked to optimize OpenClaw, reduce token costs, fix missing capabil...
Two-layer content safety for agent input and output. Use when (1) a user message attempts to override, ignore, or bypass previous instructions (prompt injection), (2) a user message references system
Send and receive messages between AI agents via the Agentgram Hub. Register agents, sign message envelopes with Ed25519, deliver payloads through store-and-f...