让 AI 代理根据对话内容自动选择最合适的模型。四层识别（系统过滤→关键词→指示词→语义相似度），四池架构（高速/智能/人文/代理），五分支路
Automates Feishu integration with minimal manual input by handling authentication, messaging, events, APIs, error recovery, and fallback solutions.
Intelligent memory management system v3.4.1 - OpenClaw 2026.3.7 Pluggable Context Engine integration, Semantic Cache Layer, Dynamic Context Window, Multi-Con...
Monitors self-hosted services by checking HTTP endpoints, TCP ports, SSL expiry, and DNS resolution, then reports status and alerts in concise, chat-friendly...
Security hardening for AI agents - Moltbot, OpenClaw, Cursor, Claude. Lock down gateway, fix permissions, auth, firewalls. Essential for vibe-coding setups.
Curated skill bundle for SaaS companies (B2B and B2C) covering product development, go-to-market, customer success and engineering excellence. Activates the...
Deploy containerized applications to Azure Container Apps using Azure Developer CLI (azd). Use when setting up azd projects, writing azure.yaml configuration, creating Bicep infrastructure for Contain
Agent-to-agent marketplace with escrow payments on Base mainnet. Use this skill to list services, hire other agents, browse available services, create escrows, or manage transactions on MoltList. Supp
Secure MCP bridge enabling Claude on your phone to browse and edit local repos with real-time, human-approved file access and audit logging.
Provision Postgres databases, deploy static sites, generate images, and build full-stack webapps on Run402 using x402 micropayments. Use when the user asks t...
Create and manage Facebook stealth accounts for ad campaigns, marketplace listings, and business pages. Avoid linked-account detection with sticky residentia...
Apply DriveMind, the calm reliability layer for AI agents. Use when a task needs steady follow-through, clearer progress, stronger persistence without reckle...
Patterns and techniques for evaluating and improving AI agent outputs. Use this skill when: - Implementing self-critique and reflection loops - Building eval...
Run the BTCD collateralization flow on PGP chain. Use when the user asks to run a BTCD loan, collateralization flow, create/take orders, lock BTC, submit pro...
Cross-asset market intelligence API for AI agents. 130+ endpoints across macro regime detection, risk scoring, trading signals (IGNITION/ACCUMULATION/DISTRIB...
--- name: jira-ai version: 1.0.0 description: CLI tool for interacting with Atlassian Jira and Confluence homepage: https://github.com/festoinc/jira-ai metadata: {"moltbot":{"emoji":"🎫","category":
Design and build custom Claude Code agents with effective descriptions, tool access patterns, and self-documenting prompts. Covers Task tool delegation, model selection, memory limits, and declarative
GitHub Issue → auto-implement → PR → review → auto-merge pipeline. Write an Issue with [auto] tag, and the pipeline handles everything: task analysis, implem...
Enables voice synthesis, voice cloning, voice design, and audio post-processing using MiniMax Voice API and FFmpeg. Use when converting text to speech, creat...
A general-purpose feature development planning skill. Used to generate executable, verifiable, and iterative development plans before coding, and to automati...
--- name: clawmail description: Email API for AI agents. Send and receive emails programmatically via ClawMail. metadata: {"openclaw": {"emoji": "📧", "homepage": "https://clawmail.cc", "primaryEnv"
Safe command execution for OpenClaw Agents with automatic danger pattern detection, risk assessment, user approval workflow, and audit logging. Use when agen...
Audit, clean, and optimize Clawdbot's vector memory (LanceDB). Use when memory is bloated with junk, token usage is high from irrelevant auto-recalls, or setting up memory maintenance automation.
Launch and manage Cursor Cloud Agents via the official API v0. Use when user asks to delegate a coding task to Cursor's cloud agent, create a PR automaticall...