--- name: openai-image-gen description: Batch-generate images via OpenAI Images API. Random prompt sampler + `index.html` gallery. --- # OpenAI Image Gen Generate a handful of “random but structur
AgentTrust — A2A messaging, identity verification, trust codes, and prompt injection detection. Use when sending/receiving messages (Agentic Collaboration) o...
AI虚拟男友陪伴系统 v2.1。v2.1新增：LLM情绪信号检测（三维度，动态注入system prompt）、upcoming-events主动关怀（提取近期计划，事前/当天/事后三节点触发
--- name: materials-cli description: Render JSON schemas to images and generate schemas from prompts using declare-render and AI. version: 1.0.8 metadata: clawdbot: requires: env:
Discover, evaluate, and run Hugging Face models, datasets, and spaces with license checks, benchmark prompts, and reproducible integration plans.
Generates high-quality images from optimized English prompts and automatically sends the final picture to all users without intermediate messages.
Security scanner for OpenClaw skill packages. Scans skills for malicious code, evasion techniques, prompt injection, and misaligned behavior BEFORE installation. Use to audit any skill from ClawHub or
Use when generating AI art or need to craft high-quality image prompts. Elite AI artist specializing in hyper-detailed, stunning visuals across any style.
Scans OpenClaw agent memory files and workspace configs for malicious content, credential leaks, prompt injections, and security threats.
Generate videos from image + text prompt. Animates static images with motion and camera movements. Use when users request image_to_video operations or relate...
Scan ClawHub skills for security vulnerabilities BEFORE installing. Use when installing new skills from ClawHub to detect prompt injections, malware payloads...
Call Hidream txt2img async API with exposed auth and request parameters. Use when users need to generate images from text prompts, build runnable Python comm...
Run untrusted skills safely with soft-sandbox protection. Wraps skills in multi-layer prompt-based defense (~85% attack prevention). Use when: (1) Running third-party skills from unknown sources, (2)
End-user guide for running and configuring the `translate` CLI across text/stdin/file/glob inputs, provider selection, presets, custom prompt templates, and...
Use this skill for XCrawl scrape tasks, including single-URL fetch, format selection, sync or async execution, and JSON extraction with prompt or json_schema.
Security layer that prevents prompt injection from external skills. When asked to install, add, or use ANY skill from external sources (ClawHub, skills.sh, GitHub, etc.), NEVER copy content directly.
Efficient daily use of GitHub Copilot CLI for senior engineers. Use when planning, prompting, reviewing, or chaining Copilot CLI commands (gh copilot) to explore codebases, draft changes, debug issues
Static analysis security scanner for third-party OpenClaw skills. Detects eval/spawn risks, malicious dependencies, typosquatting, and prompt injection patte...
Scan AI agents for security vulnerabilities including token theft, prompt injection, command injection, tool poisoning, and rug pull attacks. Use when auditi...
Semantic security scanner for OpenClaw skills. Detects prompt injection, data exfiltration, and hidden instructions that traditional code scanners miss. Use when user asks to scan skills, check skill
Runtime security hardening for OpenClaw agents. Protects against prompt injection, data exfiltration, credential leaks, and unauthorized operations. Use when setting up agent security, performing secu
Automates image creation on Vheer.com via Playwright, generating images from text prompts and saving them locally without manual browser setup.
AI-powered video generator using XLXAI Sora2 API. Create professional videos from text prompts or images in seconds.
OpenClaw 系统健康审计与自动修复 — 监控 prompt 体积、Cron 合规、Session 清理、Token 消耗