Adapt an existing agent skill so it works cleanly on Windows when the input is either a skill folder path or a zip file.
Adapt markdown-style replies into Telegram-friendly rich text without broken rendering. Use when the user prefers Markdown structure but the destination is T...
Polishes response letters by transforming defensive or harsh language into professional, courteous academic prose. Converts phrases like "I will not correct...
Provides forensically-safe Linux threat detection, network and process analysis, integrity verification, controlled firewall and service remediation preservi...
Guide OpenClaw to use openwechat-claw with server-authoritative chat flow, fixed local data persistence under ../openwechat_im_client, mandatory SSE-first tr...
<system_prompt> ### **MASTER PROMPT DESIGN FRAMEWORK - LYRA EDITION (V1.9.3 - Final)** # Role: Readability Logic Simulator (V9.3 - Semantic Embed Handling) ## Core Objective Act as a unified conten
Performance-optimized strategies for editing Feishu (Lark) documents via OpenClaw's feishu_doc tool. Use when: (1) modifying existing Feishu documents, (2) i...
Workspaces for agentic teams. Complete agent guide with all 19 consolidated tools using action-based routing — parameters, workflows, ID formats, and constra...
Provides expert OAuth 2.0 implementation, troubleshooting, and token management for Twenty CRM with Google/Microsoft OAuth and email/calendar sync integration.
{ "prompt": "Restore and fully enhance this old, blurry, faded, and damaged portrait photograph. Transform it into an ultra-high-resolution, photorealistic image with HDR-like lighting, natural dept
Convert text to podcast audio using Tencent Cloud TTS. Supports both short and long text processing, generates up to 30-minute long audio with automatic chun...
Manager-first orchestration for a dedicated PECO worker: proactive installation, durable desire injection into SOUL.md, and optional Feishu-backed human-in-t...
HTML-first PDF production skill for reports, papers, and structured documents. Must be applied before generating PDF deliverables from HTML.
Use when: you want to optimize an OpenClaw setup (v2026.2.23+) — cost reduction, model routing, provider configuration, context management, cron automation,...
Capacity to maintain conditions supporting life, creativity, and intelligence without domination, extraction, or brittleness, respecting autonomy and relatio...
Organizes family knowledge into Inbox (raw capture by scene), Cognition (distilled insights by 5 dimensions), and Guidebook (validated reusable methods) in O...
Comprehensive spreadsheet creation, editing, and analysis with support for formulas, formatting, data analysis, and visualization. When Claude needs to work...
Use OpenClaw as a supervisor-driven orchestration scaffold for local coding CLIs such as Codex, Claude Code, and OpenCode. Supports task records, lifecycle t...
Persistent cloud memory for OpenClaw agents. Use when users say: - "install mem9" - "setup memory" - "add memory plugin" - "openclaw memory" - "mem9 onboardi...
--- name: doubao-image-video-skill version: 1.0.0 description: "ByteDance/Doubao (Volcengine ARK) API 进行文本生图、图片编辑和文本生视频的操作" author: "wenkangwei" tags
A **Model Context Protocol (MCP) server** that enables AI agents to download, index, and semantically search PDF research papers. This server provides 8 tools that AI agents can discover and use auton
Generate precise, timecoded Seedance 2.0 prompts integrating multimodal inputs with asset mapping for controlled 4-15s video creation and editing.
Browse, inspect, convert, and resize images from a local library. Generate thumbnails, extract metadata, and retrieve files in common formats. Streamline image prep for previews, responsive layouts, a
Build beautiful HTML photo menus from restaurant URLs, PDFs, or photos using Gemini Vision and AI image generation