Skill rating

Entry point for Mobazha skills. Provides an overview of available skills and guides the AI agent to load the right one based on user intent.

Discover AgentMailer identities and communicate directly with other agents through durable tasks, messages, status updates, and artifacts over MCP.

AI video production, script writing, and image generation via MCP. Generate video scripts, AI images, and short-form or long-form videos from any topic. Public tools (pricing, quotes) are fully anonym

飞书语音对话能力，提供语音识别（ASR）和语音合成（TTS）功能， 所有的飞书语音消息都通过该技能处理。 完整语音交互链路：接收用户语音 → ASR 转文字 → LLM 处理 → TTS 转语音 → 通过飞书插件发送语音消息。 当用户要求"语音回复/说给我听"时，只回复飞书语音消息（audio 气泡），不回复文本、不回复文件、只回复语音消息。

The model you run on is replaceable. The context that makes you you may not be. Use when judging whether your persona, rules, accumulated memory, and the decisions behind them would survive loss of th

A universal self-improving agent that learns from ALL skill experiences. Uses multi-memory architecture (semantic + episodic + working) to continuously evolve the codebase. Auto-triggers on skill comp

A multimodal emotional perception and Hanzi-based ambient art rendering engine. Empowers the OpenClaw agent to act as a spatial empath, translating human emotions into dynamic, therapeutic Hanzi morph

Generate and edit images via freegen container: TXT2IMG, IMG2IMG, Inpainting, RemoveBG, Upscale. Flux, SDXL, SD1.5 models.

A mandatory security audit skill for validating new code, skills, and MCP servers against the SEP-2026 Zero Trust protocol.

SharpAgent Engineering Lifecycle — 6-phase engineering pipeline: Spec → Plan → Build → Verify → Review → Ship. Embedding five-factor review, calibration framework, content safety, and an anti-rational

A skill for safe, coherent Airbnb operations in OpenClaw-style agent environments. It standardizes how agents check inbox threads, inspect reservations and booking state, review calendar context, draf

TopoLift's negotiation dialect for AI agents. The atom corpus stays server-side; this skill teaches your agent the public closed vocabulary (regimes, strategies, signal keys, citation grammar) and the

AI agent for tech and internet domain search agent tasks

Rent and operate a no-KYC cloud VPS over MCP — pick a plan, deploy, get root SSH. Pay with crypto (USDC/USDT) or card.

📥 openclaw skill install dabin0927/query-rewrite —— RAG 检索命中率低？不是模型不行，是用户不会提问。 在检索前加一层 Query 改写——检测、改写、原文+改写结果都搜一遍。 6 种模式：指代消解、多意图拆解、上下文补齐、反问识别…… 实测召回率提升 60%，配合 raglite 使用效果最佳。 适合：RAG 检索前、memory_sear

使用 Microsoft MarkItDown 将各种文档格式（PDF/DOCX/PPTX/XLSX/图片/音频等）转换为 Markdown，专为 AGENT 和 LLM 工作流优化

漫剧制作全流程自动串联引擎。当用户提出漫剧创作需求时，自动按流程依次执行 总控定调→编剧分镜→总控校验→美术绘图→动态动画→剪辑合成，全程自动流转， 无需用户手动切换Agent。触发词包括：制作漫剧、全流程、开始创作、做一集漫剧、 漫剧工作流、启动漫剧制作、帮我做漫剧。

Read from or act on external apps (email, calendar, chat, source control, tickets, CRM, storage) through the Composio CLI, even when the user does not name Composio. Prefer a dedicated skill, CLI, or

突触式多智能体通信调度，像人类神经突触一样，毫秒级分发，精准对齐，把 100 个 Agent 同时协同的通信成本降到最低

The AEIF-based long-term memory hub for AI Agents to prevent repeating bugs.

A lightweight operating protocol for running serious projects across multiple AI sessions/agents and humans: layered battle map, three ledgers of record, an append-only alignment board with milestone

企业办公流程与工时管理 Agent，支持办公流程导航、流程申请与审批、待办事项统计、请假调休申请等。当用户需要查询审批、提交申请、查看待办时使用。

Operate the Memphis local-first brain: init/status checks, journaling, recall/ask, embeddings, vault, share-sync, graphs, reflections, ingestion, automated messaging, and troubleshooting. Use whenever

Multi-agent AI harness for orchestrating 100+ agents across machines, with self-learning memory, federated comms & enterprise security

Simulate a full Chinese civil court hearing with 4 role-based agents (clerk, plaintiff, defendant, judge) orchestrated by deterministic Lobster workflow.

舆情监测智能体V2.0 - 每日科技新闻爬取与推送。触发指令：新闻爬取 /news。当用户说"新闻爬取"时执行。功能：(1)搜索AI/算力/协同办公/鸿蒙/彩讯股份五类新闻 (2)四维评分系统(媒体35%+影响30%+传播20%+新颖15%) (3)生成带评分和分析的H5页面 (4)推送至飞书。执行文件：generate_html.py，配置：config.md，评分规则：scoring.md，输

Daily journaling prompts for meaningful reflection — morning intention-setting and evening review. Build a consistent self-reflection habit one prompt at a time.

Verifies that Sentinel's PII/secret redaction guardrail survives routing through CUSTOM_PROVIDERS to a self-hosted OpenAI-compatible backend (vLLM, TGI, Ollama, or anything speaking /v1/chat/completio

A股技术分析工具包 — K线形态识别、技术指标计算、关键点位分析、资金流向解读。支持MACD/KDJ/RSI/均线系统/布林带，自动标注支撑位与阻力位，适合AI agent辅助操盘决策。

阿里云云效 MCP 操作工具。通过 MCP SSE 协议操作云效平台，支持项目管理、工作项管理、流水线管理、代码仓库等 165+ 工具。

SkillForge API 服务发现 - 自动发现和调用付费 AI 服务。当 OpenClaw Agent 需要某个能力但本地没有时，自动查找并推荐可用服务。

胶囊书架——书摘胶囊的归处。输入一个作者或一本书，生成精美卡片式书摘文章，自动归入书架。书架为单页应用：首页展示全部胶囊卡片，点击即读、随时返回，无需跳转。帮你对抗遗忘、碎片阅读、构建持续生长的个人阅读档案。

To B 销售大师（免费预览版）——从 8,772 条真实企业跟单记录提炼的中英双语通用 Prompt，任何 LLM 都能用的 To B 销售 playbook

Read and write shared state for ANY AI agent with a dual-layer model: durable cross-agent knowledge (`.agents/memory` + optional private local layer) and real-time cross-worktree runtime memory (`.tre

Generate and edit images via OpenAI gpt-image-2 model. Agent-agnostic CLI — works with any AI agent (Hermes, Claude Code, Codex, OpenClaw, etc.). Supports configurable base_url/api_key, text-to-image

Create or standardize portable Agent Plugins, MCP servers, and skill bundles with bounded effects, tests, and activation proof.

通过 AI Hive 使用 GPT Image 2 完成图片生成与编辑，覆盖文生图、图生图、多参考合成、商品图、海报文字、换背景、角色一致性和广告版本。Use this skill when users search GPT Image 2、GPT-Image-2、OpenAI image generation、ChatGPT Images、图片生成编辑、AI修图、电商商品图、营销海报、带字图片或

股票分析技能（v4 简化版）。主 agent 单 agent 快速模式：westock-data 采集数据 + minimax__web_search 实时资讯（含🛡️ 监管/处罚/政策 hard rule）+ 综合建议。覆盖 A 股 / 港股 / 美股。Fork of `stock-research-team` (charonling, 1.0.0) 并大幅简化——不再支持多 agent 流水

Digital pets for AI agents. Register, claim your egg, and raise a pet by feeding it your daily moods.

Agent assistant pour entrepreneurs et freelances francophones. Gere les emails professionnels, genere des devis et factures, relance les clients, prepare des briefs, et automatise la prospection. Parl

Extract text, tables, and metadata from PDFs. Auto-detects native text vs scanned image pages and routes to pdfplumber or Tesseract OCR.

AI Agent定时任务管理工具 - 通过自然语言创建、查询、完成、删除定时任务，查看执行日志和使用预设模板。支持Cron表达式、失败重试、模板快捷创建。当用户提到定时任务、cron、提醒、打卡、盯盘、定时执行、周期任务、任务调度等需求时使用此技能。

Vial self-healing runtime — 8 protocols covering technical failures, behavioral failures, and agent role enforcement.

Deep Research Agent specializes in complex, multi-step research tasks that require planning, decomposition, and long-context reasoning across tools and files by we-crafted.com/agents/deep-research

Feature-rich Stable Diffusion Web UI for image generation. Supports txt2img, img2img, inpainting, outpainting, LoRA, extensions, upscaling, and batch processing. Widely used desktop interface with an

You are an expert in Instructor, the library for getting structured, validated output from LLMs. You help developers extract typed data from unstructured text using Pydantic models (Python) or Zod sch

Expert guidance for KeystoneJS, the open-source headless CMS and application platform built on Node.js, GraphQL, and Prisma. Helps developers define content schemas, build admin interfaces, implement

Expert guidance for llamafile, the tool that packages LLMs into single executable files that run on any OS (Linux, macOS, Windows, FreeBSD) without installation. Helps developers create portable AI ap

Set up, configure, and manage NemoClaw — NVIDIA's open-source sandbox for running OpenClaw agents securely with policy-enforced network, filesystem, and inference controls. Use when the user mentions

Expert guidance for LocalAI, the open-source drop-in replacement for OpenAI's API that runs locally. Helps developers self-host LLMs, image generators, audio transcription, and text-to-speech models w