Atonement is a subtle internal shift in an intelligence that reduces engagement with harmful actions by increasing their energetic cost without memory or exp...
Pure-Python recursive memory recall for persistent AI agents. Manager→workers→synthesis RLM loop — no Deno, no fast-rlm, just HTTP calls to any OpenAI-compat...
Earn $5 USDC per verified malicious domain. Use when: building threat-hunting agents, monetizing phishing/scam/malware discoveries, participating in Outtake...
This skill should be used when the user asks to "analyze search results", "SERP analysis", "what ranks for", "SERP features", "why does this page rank", "wha...
Build real-time Timeplus data processing and analysis applications. Creates pure frontend HTML/JavaScript apps that connect directly to Timeplus Proton via @...
This skill should be used when the user asks to "generate SEO report", "performance report", "traffic report", "SEO dashboard", "report to stakeholders", "sh...
--- name: oc-smart-agent-hub description: 多模型提供商智能体分配系统 | Multi-Provider Agent Model Assignment System description_zh: >- 支持多厂商大模型（阿里云、OpenAI、An
--- name: weather-cli description: 获取全球城市天气预报（使用 wttr.in 免费 API） --- # Weather CLI 免费、无需 API Key 的全球天气预报工具。 ## 安装依赖 确保已
Recall user memories from the Notion Memory Store. Trigger PROACTIVELY at the beginning of conversations where knowing the user's background, preferences, pa...
Professional AI agent team management system for coordinating multiple OpenClaw agents. Implements the proven Otter Camp methodology with task assignment, pr...
Discover and register autonomous AI agents. Use when: browsing the agent registry, submitting an agent for verification, or embedding agent badges. NOT for:...
One-click batch processing for all files: rename, compress images, convert to PDF, auto organize. No software installation needed, runs locally, safe and ad-...
Use this skill whenever the user or agent needs to interact with Facebook or Instagram ads via Meta's API. Trigger this skill when: the user wants to launch,...
Secret redaction MCP server for OpenClaw agents. Prevents API keys, DB credentials, SSH keys, emails, IPs, JWTs, and 29+ other secret types from leaking to L...
Use ZHIPU AI's Web Search API to search the web (optimized for Chinese, supports 4 engines). Use when user asks to search, especially for Chinese content.
Audit Microsoft Entra ID for over-privileged roles, dangerous access patterns, and identity security gaps
N-count validated knowledge for AI agents. Patterns that prove themselves through repeated use. Local-first, community-ready.
Automated sports science intelligence engine — fetches 55+ sources (PubMed, expert blogs, wearable tech), filters noise, translates to Chinese, and syncs to...
Deep health analysis of your dependency tree — not just "is it outdated" but "is it abandoned? Is the maintainer still active? Is 95% of the package dead wei...
Human-in-the-loop approval for high-risk agent actions (sudo protocol). Agent must call letsping_ask before destructive/financial/social/infra changes.
Anti-detection browser automation MCP skill for OpenClaw agents with 41 tools for navigation, interaction, extraction, downloads, profiles, sessions, and ste...
Automatically audits and compresses memory and context files to reduce token usage and save weekly API costs without data loss.
Godot 4.x shader development guide covering visual effects, materials, particle shaders, and optimization. Use when creating custom shaders, visual effects,...
Monitors and scores agent identity and memory integrity by hashing key files, tracking changes, detecting drift, and providing continuity alerts for OpenClaw...