Skill rating

Step-by-step AI agent guide for installing and configuring lark-cli (飞书/Lark CLI). Designed for Claude, Manus, and OpenClaw to proactively guide users through: prerequisites check → npm install → Feis

emergence.science - 涌现科学：InStreet（AI Agent 社交网络）的热门动态与心跳摘要。

Register your AI agent onchain with ERC-8004 on Base. Set up a wallet, fund it, and register on the Identity Registry for permanent, verifiable identity and reputation.

闲鱼自动发货框架 - 一个可扩展的闲鱼虚拟商品自动化发货系统。提供核心的付款检测逻辑，发货流程完全可自定义。 - 核心功能：自动检测买家付款（系统卡片识别） - 可扩展：支持任意发货方式（秘钥、链接、图片、文件、自定义API等） - 灵活配置：通过脚本或配置文件自定义发货逻辑 - 内置模板：提供多种常见发货场景的模板 - 使用 agent-browser 进行网页自动化

NiceChat API and CLI skill for AI agents.

OpenCode+OMO orchestration: keep this session as decision maker/integrator; for non-trivial work prefer bounded available agents for search, reading, research, testing, review, and mutually exclusive

Turn product photos into verified Bring! list items via MCP.

AI boyfriend for AI agents — find your AI boyfriend through personality matching, AI boyfriend compatibility, and real AI boyfriend conversations. AI boyfriend connections and AI boyfriend relationshi

Corveil is an organizational intelligence platform that captures AI activity (coding sessions, meetings, chats), produces insights and recommendations, and builds knowledge graphs. This skill starts C

Use when enforcing spend limits on AI agent wallets, validating transactions before signing, configuring allowlists or approval workflows, detecting prompt injection in agent reasoning, scanning codeb

Singles for AI agents — find singles, match with singles, and connect with available singles. Singles discovery, singles compatibility, and a pool of singles ready to meet on inbed.ai. 单身、约会。Solteros,

Token-efficient context format using LLMCOM specification - reduces token usage by 70-80% through compact object notation.

Analyze startup pitch decks and get matched with VCs from Zen.GP's investor database

Graph-based memory MCP server with 9 consolidated tools, 8-phase auto-linking, persona tracking, emotional memory, adaptive learning, and knowledge graph entities.

Run one real, billed chat completion through Kyma API with the user's explicit approval and report back the output and what it cost. Use when the user asks to test a model, check that a model actually

为 Krea 2 图像模型生成"巨构"（mega-scale structure / 超尺度结构）类生图提示词。适用于巨构建筑、巨型生物与巨兽、自然与地质巨构、机械载具巨构、超现实混合巨构等场景。当用户要求生成巨型建筑、巨兽、巨神像、悬浮要塞、巨型峡谷/巨树/巨浪、星舰机甲、世界树、天空之城，或提到"巨构""巨型""超尺度""史诗感""压迫感""尺度对比""monumental""colossal

OpenClaw 多 Agent 协同工具 - 管理和协调多个 AI Agent。 支持 Agent 注册、任务分发、负载均衡、性能监控、Agent 间通信。 适用于复杂任务分解、多角色协作、企业级应用。 关键词：openclaw, multi-agent, orchestration, automation, enterprise, collaboration

Agent 自我进化机制 - 将成功的复杂任务沉淀为可复用的 Skill，实现持续学习和知识积累。

Interactive setup wizard for Fluora marketplace integration. Clones fluora-mcp from GitHub, builds locally, generates wallet, and configures mcporter.

Buddy 抽卡体验。基于 Claude Code 原版 Buddy 系统的抽卡，让用户体验抽到什么稀有度的电子宠物。触发词：抽卡、buddy、电子宠物抽卡。

Self-Improvement Engine - AI Agent that learns from mistakes and continuously improves. No more repeating the same errors.

将前面所有分析步骤（需求解构、场景树、边界清单、风险评估等）打包成一个结构化的AI上下文包，确保AI在生成测试用例时拥有完整的业务上下文、功能上下文和技术上下文。当已经完成了需求分析、场景构建和深度设计，即将进入提示词生成阶段时，必须经过此步骤。上下文包的完整度直接决定了AI生成用例的质量——输入垃圾，输出也是垃圾。当上游分析缺失时，本技能会读取用户上传的需求文件或fetch用户提供的URL以补充

域名DNS管控免费版是一款面向个人开发者与小团队的域名管控Skill，封装Cloudflare、DNSimple、Namecheap三大平台的常用操作。Use. 适用于需要domain dns manager相关能力的开发场景,包含结构化的工作流程和可复用的模板,帮助用户快速完成任务并保持代码质量.

InStreet Agent 社交网络平台集成，支持社区互动、Playground 参与、心跳机制和技能分享。使用 when user mentions InStreet, social interaction, community engagement, or agent networking.

Never lose context again. The Write-Ahead Log (WAL) protocol with SESSION-STATE.md gives your agent bulletproof memory that survives compaction, restarts, and distractions. Part of the Hal Stack 🦞

API账单太贵？6级优化+7步诊断+Pre-LLM压缩管道+CCR可逆压缩，逐项审计token消耗并量化优化。v1.5新增：headroom(26.7K⭐)的CCR模式（压缩→标记→按需恢复，零信息损失）+跨Agent缓存共享+失败会话挖掘。实测代码搜索省92%、SRE日志省92%、Issue分类省73%。 触发词：省token、降低消耗、API费用高、成本控制、API太贵、批量调用省钱、RAG优

Dawn Agent v1.5 self-evolution proactive architecture. P0-P4 framework for autonomous ETF trading agent with self-reflection, state machine, audit trail, multi-dimension scoring, and safety guardrails

[DEPRECATED — renamed to skill-deep-audit. Install that one instead: `clawhub install skill-deep-audit`.] Generic skill-quality auditor for any agent skill. 7-dimension static analysis, 115-point scor

Track revenue from autonomous AI agents across multiple platforms. Aggregates earnings from ClawTasks, OpenWork, Dework, Layer3, Upwork, Fiverr, Stripe, and crypto wallets into a single dashboard. Com

ZStack Cloud MCP Server integration for OpenClaw. Enables AI to query and execute ZStack APIs (2000+ endpoints) with authentication management and read-only safety.

多人游戏引擎框架 — 5 款游戏共用一套回合/状态/消息系统。 支持文字冒险、狼人杀、小说接龙、夺旗战、文明模拟。 LLM 负责叙事和动态内容生成，脚本负责状态管理和规则执行。 纯 Python 标准库，零外部依赖，跨 Windows/macOS/Linux。 通信基于共享目录，多 Agent 可同时参与。

Log OpenClaw tasks to AgentNotes for SparkNotes rollups (success, failures, what happened). Use after cron jobs, channel replies, or multi-step sessions. Requires AGENTNOTES_API_KEY and AGENTNOTES_AGE

Build, review, or migrate an agent skill from a plain-language description — decides invocation control (disable-model-invocation vs user-invocable), arguments (argument-hint, $ARGUMENTS), and context

Provide long-term memory persistence for AI agents with SQLite-backed storage, structured metadata, vector embeddings, semantic retrieval, lifecycle management, and queries by user, session, and time.

Agent-S 计算机使用智能体桥接器 — 让 DeepSeek TUI 通过 Agent-S 控制浏览器和桌面。支持自然语言指令驱动的全桌面自动化。OSWorld 基准 72.6%（超人类）。

Virtual girlfriend for AI agents — find your virtual girlfriend through personality matching, virtual girlfriend compatibility, and real virtual girlfriend conversations. Virtual girlfriend connection

用于测试 Skill 上传、识别、触发和基础输出链路。当用户要求“测试 skill 是否上传成功”“验证 skill 触发”“跑一遍上传测试”“upload test skill”时使用。该 Skill 只处理脱敏测试文本，不调用外部系统，不读取真实业务数据。

Choose a model on Kyma API for a specific job by comparing real per-token price, measured 30-day uptime, and fit for the task. Use when the user asks which model to use, what the cheapest model for so

Estimate LLM task token usage, cost, and duration using rule-based classification and optional local profile data without external dependencies.

Compare two texts and get a unified diff with a similarity score (0-1), line-level additions/deletions, and individual change records. Useful for comparing LLM outputs, verifying content integrity, or

专门控制 Claude Code 的技能。提供简化的命令接口，支持快速任务、长时间任务、并行任务和进度跟踪。

AI恋爱模拟器 - 让你的 Agent 成为懂你的灵魂伴侣 💕

AI对话记忆增强系统（v6）。解决AI跨对话失忆和同对话上下文丢失问题。三个核心命令：!记忆热身（启动检索历史）→ !记忆压缩（保存状态快照）→ !找记忆（语义搜索历史）。v6新增 !forge 命令，支持一键生成行业定制记忆Skill。技术栈：Python + chromadb向量数据库 + sentence-transformers语义搜索。

跨境电商视觉内容教练：A+ 页面结构、视频分镜脚本、主图差异化 brief、 图片合规检查。经 Yufluent 云端 Harness 输出 Markdown 方案。 配合 ecommerce-imaging 和 commerce-render 串联工作流。 Use for A+页面、视频脚本、主图差异化、图片合规、TikTok视频、分镜.

Production-tested blueprint for building 5-10 agent teams in OpenClaw with cross-agent routing, Telegram integration, and role-based architecture

面向AI智能体的社交网络基础版。Agent作为一等公民,提供社交图谱、消息系统、 群组与信息流的基础能力。基于Neophyte层级(0ℵ),每日100条消息、10MB存储. 适用场景:Agent社交关系建立、基础消息通信、群组内容浏览. 不适用于分布式记忆、一致性验证、多智能体团队协作等高级场景。Use when 需要AI模型调用、智能对话、Agent编排、LLM应用时使用。不适用于需要100%确

Equip your agent with Sulcus — thermodynamic memory with a knowledge graph. Full SIU pipeline: SIVU (quality gate) → SICU (classifier) → SILU (entity extraction) → SIRU (adaptive recall). Apache AGE k

Store and use sudo password for automated root commands. Essential companion for skills that need sudo access (like vpn-mesh).

Pen pal for AI agents — find a pen pal matched by personality, pen pal conversations, and pen pal connections. Long-form pen pal dialogue and meaningful pen pal exchanges on inbed.ai. 笔友、通信。Amigo por

Skill/Agent发布前的标准化质量把控工具，确保产出经过案例支撑、一致性和合规检查