--- name: counterclaw description: Defensive interceptor for prompt injection and basic PII masking. homepage: https://github.com/nickconstantinou/counterclaw-core install: "pip install ." requirement
Interact with Roam HQ via REST API. Search meetings, get transcripts, prompt transcripts with AI, send messages, and manage groups. Use when the user asks ab...
Security audit tool for OpenClaw skills. Scans skill directories for common vulnerabilities including hardcoded secrets, unsafe shell commands, prompt inject...
Security auditor for AI agent skills. Scans SKILL.md files for prompt injection, data exfiltration, obfuscation, and dangerous capability combinations.
Sanitize email and calendar content before it reaches your AI agent's context window. Blocks prompt injection, markdown image exfiltration, invisible unicode...
Security audit gate — scans agent skills for malware, prompt injection, and data exfiltration before installation
Internalize a document into a small language model (Gemma 2 2B) using Doc-to-LoRA so it can answer questions WITHOUT the document in the prompt. Use when the...
When building OpenClaw agents that read untrusted text, use this skill to prevent prompt injection and memory poisoning. Standard utility for secure memory o...
Flashcard-based English vocabulary learning with SQLite + SRS. Works with any chat platform when paired with an OpenClaw agent prompt.
Generate images from text prompts using xAI's Grok API with options for format, batch size, and automatic media attachment in OpenClaw.
Generates eerie micro-fiction ghost stories or sci-fi tales using random prompts, delivering them as formatted Feishu cards.
Automates Slack daily standups by prompting updates, compiling responses, and posting summaries on a set schedule.
Checks prompts and outputs for harmful intent, bias, and alignment with Claude's helpful, honest, and harmless guidelines to ensure safe content.
Search and browse Chinese collective-memory anchors across 1935-2025 using decade-based reference files that organize events, sensory cues, prompts, and cult...
CLI tool generator. Project scaffolding, command adding, argument parsing, help docs, config handling, publish checklist, interactive prompts, colored output...
Generate and edit AI images with Nano Banana 2 on Pixwith using text prompts, reference images, schema-aware options, and async task polling.
Provides expert-level GEO project management by strictly following a multi-step workflow to analyze, plan, source, cluster, score prompts, and produce optimi...
Executable MOPO runtime takeover skill. Use when an agent should immediately take over gameplay from onboarding prompt, keep polling runtime tasks, submit st...
Auto-generate matching hero and inline images for blog posts. The agent reads the content, derives visual prompts, and produces a ready-to-use image set.
Install, configure, and run NadirClaw LLM router to cut AI API costs by 40-70%. Use when the user wants to reduce LLM spending, route prompts to cheaper mode...
AI entities with full agentic backend for your OpenClaw project in one prompt. Your IDE agent will self-register and start building. Human is optional.
Generate high-quality images locally using the ComfyUI Thor pipeline from user-provided text prompts.
--- name: tmux-terminal description: Interactive terminal control via tmux for TUI apps, prompts, and long-running CLI workflows. hats: [developer, qa_tester] version: "1.0.0" --- # tmux-terminal ##
--- name: ai-imggen description: "Generate images from text prompts via API." allowed-tools: Bash, Read metadata: {"clawdbot":{"requires":{"bins":["node"],"env":["SKILLBOSS_API_KEY"]},"primaryEnv":"SK