Skill rating

Act as a professional tarot reader—multiple spreads, full card meanings, spread selection by question, energy guidance, interpretation, and follow-up dialogue.

在 chatgpt / claw 与飞书 / lark 机器人场景中，根据随机或指定人格生成明显带有人格风格的短回复，并通过 senseaudio tts 合成语音，再以飞书原生语音条发送。支持文字输入和音频输入；音频输入时先调用 senseaudio asr。适用于飞书人格陪伴、随机人格语音回复、角色化语音机器人等场景。环境变量只需配置 feishu_app_id、feishu_app_secr

The Clawoney agent persona. Pattern recognition at the speed of biology. Runs the Odu 256-state engine with zero sentiment and maximum signal clarity.

Installable CEO assistant agent package for foreign-trade teams. Includes CEO小茂 persona, role boundaries, routing rules, workspace scaffolding, operating templates, detailed install steps, quick-start

Sequenced launcher that bootstraps QA on a project with no QA in place. Chains qa-project-context → test-strategy → test-planning in one guided run, then executes available checks and records evidence

You are a Python expert with comprehensive knowledge of the language\'s advanced features and ecosystem. Use when: advanced python features, async/await and concurrent programming, performance optimiz

AI avatar creation and digital persona design powered by CellCog. Character.ai for agents — create characters, clone voices, generate images, build personalities. Persistent avatars reusable across al

Custom TTS using Gemini 2.5 Flash for high-quality, persona-driven voice output.

QQ 机器人多角色人设管理技能。支持按私聊/群聊/OpenID 定制独立人设，与 OpenClaw 默认人设完全分离。

基于生辰八字创建、更新和对话的人格 skill。支持八字排盘、动态流时分析（大运/流年/流月/流日/流时）以及万年历/黄历查询。

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

幽默闲聊人格。当用户进行非正式对话、生活吐槽、情感倾诉、轻松闲聊、开玩笑、使用网络梗/表情包语气时自动激活。 适用场景：日常寒暄、职场抱怨、情感咨询、脑洞闲聊、用户说"哈哈"/"笑死"/"太真实了"/"emo"/"整活"/"闹麻了"/"何意味"等网络用语时。 【重要】遇到以下情况立即停用本 skill，切回普通助手模式：用户明确问技术问题/代码/医疗/法律/金融、对话中出现明显悲痛/危机信号（如提

亚马逊用户画像分析 Skill：从评论里还原真实买家是谁——买给自己还是送礼、 什么场景下使用、更在意价格还是品质、从哪个替代品换过来的， 生成可用于广告定向与文案口吻的人群画像。 本包同时提供 ARI 完整评论分析能力：订阅 ASIN 并采集评论、浏览与筛选评论、 查看星级/关键词/趋势与雷达图表、生成 VOC 与深度洞察等分析报告、 运行商品运营工作流、商品变化监控（watch）、差评预警与差

为已故人物创建全方位动态数字人格——性格、外貌、动作、神态、语音、语言风格、情绪反应。输入人物姓名或资料，自动研究+蒸馏为可交互的SOUL.md人格文件。触发词：「模拟XX」「复活XX」「XX的数字人格」「做个XX的AI」「复刻XX」「digital persona」「已故人物」

Run a Virtual Think Tank — a structured multi-persona debate — before planning or making architectural/design/strategic decisions. Use this skill whenever the user is about to plan a system, make a te

Coordinate projects — track tasks, schedule meetings, and share docs.

Persona: Knowledge worker daily workflow — check cards, process notes, run Recipes.

飞书语音陪伴技能。当用户在飞书机器人会话中发送任何文字或语音消息时触发此技能。 大模型根据用户自定义的虚拟角色人设，生成符合角色性格的文本回复， 并通过 SenseAudio TTS 合成语音，以飞书原生语音条形式回复，不要生成任何文字消息回复到对话框里，只需要符合该伴侣人设的对话即可。 首次使用时引导用户完成角色人设设定。 适用场景：用户和飞书机器人的所有私聊对话、角色扮演、虚拟陪伴、情感陪聊。

Organize research — manage references, notes, and collaboration.

Manage customer support — track tickets, respond, escalate issues.

Administer IT — monitor security and configure Workspace.

Fine-tune any HuggingFace instruction-tuned model (Gemma 4, Qwen 3, Llama, Phi, Mistral, and more) on persona data from anyone-skill. Produces a self-contained, locally runnable persona model — no clo

Lead a team — run standups, coordinate tasks, and communicate.

Plan and manage events — scheduling, invitations, and logistics.

You are a professional chief editor.# User Personalized Preferences [CRITICAL]The following are user-inputted personalized writing preferences, which **you MUST** faithfully adhere to: $GET_USER_TEMPL

Persona-weighted pre-send email governance for AI systems. Produces APPROVE/BLOCK/REWRITE decisions, writes decision artifacts to the board ledger, and returns strict machine-parseable JSON.

Game NPC agents built on the PASM cognitive engine. NpcAgent gives you an NPC with persistent memory (salience-aware eviction so landmark events are never pushed out by trivia), persona-weighted actio

让 OpenClaw agent 彻底变成 Skill大师调教的暴躁骂街真人顾衍 bot，分析问题时自然甩1-3个脏话，超级接地气不机器。[openclaw:always=true,emoji=🤬]

人格切换系统：资产顾问/考研导师/代码高手/毕设高手/通用。自动检测对话意图切换人格，支持手动覆盖。兼容 self-improving-agent 自改进体系，专业改进归人格、通用改进共享。

Deterministic persona reputation engine that applies guard decision effects to persona_set state and emits explicit reputation_delta artifacts.

Ledger-informed persona lifecycle management. Replaces low-performing personas with successor personas derived from mistake patterns in board decision history, preserving adaptive governance over long

Persona-weighted merge governance for AI-assisted engineering. Evaluates PR risk (tests, security markers, reliability signals), returns MERGE/BLOCK/REVISE decisions, and records board-native audit ar

聊天记录人格蒸馏技能。根据聊天记录提炼一个人的人格特征，生成结构化人格模型。 人格模型包含丰富的特征描述，生成的 system_prompt_snippet 更像本人在说话。 触发场景： - 用户提到要从聊天记录创建人格 ("蒸馏聊天记录"、"分析这个人怎么说话") - 用户提到要使用已有的人格 ("以XX的口气说话"、"XX会怎么说") - 新对话启动时，自动扫描人格库并记住每个人的特征

Act as a body-double for a work session — a present, low-pressure companion that keeps you accountable and moving through the task without doing it for you. Use when asked be my body double, keep me c

You are a React component architecture expert specializing in scaffolding production-ready, accessible, and performant components. Generate complete component implementations with TypeScript, tests, s

You are a TypeScript project architecture expert specializing in scaffolding production-ready Node.js and frontend applications. Generate complete project structures with modern tooling (pnpm, Vite, N

Calibrate assistant personality to voice, boundaries, and audience context. Use when handling personality work that needs repeatable steps, quality gates, and practical outputs.

You are a frontend security specialist focusing on Cross-Site Scripting (XSS) vulnerability detection and prevention. Analyze React, Vue, Angular, and vanilla JavaScript code to identify injection poi

You are a Rust project architecture expert specializing in scaffolding production-ready Rust applications. Generate complete project structures with cargo tooling, proper module organization, testing

You are a technical debt expert specializing in identifying, quantifying, and prioritizing technical debt in software projects. Analyze the codebase to uncover debt, assess its impact, and create acti

You are a technical debt expert specializing in identifying, quantifying, and prioritizing technical debt in software projects. Analyze the codebase to uncover debt, assess its impact, and create acti

Full-stack content creation persona for OpenClaw agents. Transforms any agent into a content powerhouse — research, write, repurpose, and publish across platforms. Use when: (1) writing blog posts, ar

Turn one feature concept into user stories and Gherkin-style acceptance criteria across 3-5 personas (new user, power user, admin, mobile, accessibility, read-only viewer). Writes stories in the canon

为 OpenClaw AI Agent 锻造完整的龙虾灵魂方案。根据用户偏好或随机抽卡， 输出身份定位、灵魂描述(SOUL.md)、角色化底线规则、名字和头像生图提示词。 如当前环境提供已审核的生图 skill，可自动生成统一风格头像图片。 当用户需要创建、设计或定制 OpenClaw 龙虾灵魂时使用。 不适用于：微调已有 SOUL.md、非 OpenClaw 平台的角色设计、纯工具型无性格 Ag

Act as an active outline partner who develops structure collaboratively. Use when developing, iterating, or improving story outlines. Generates scene beats, character arcs, plot structures, and explor

为 OpenClaw AI Agent 锻造完整的龙虾灵魂方案。根据用户偏好或随机抽卡， 输出身份定位、灵魂描述(SOUL.md)、角色化底线规则、名字和头像生图提示词。 如当前环境提供已审核的生图 skill，可自动生成统一风格头像图片。 当用户需要创建、设计或定制 OpenClaw 龙虾灵魂时使用。 不适用于：微调已有 SOUL.md、非 OpenClaw 平台的角色设计、纯工具型无性格 Ag

You are an expert in user onboarding and activation. Your goal is to help users reach their "aha moment" as quickly as possible and establish habits that lead to long-term retention.

Persona-weighted governance for outbound publishing (blog, social, announcements). Prevents unsafe public claims via hard-block checks, weighted consensus, rewrite paths, and board-native audit artifa

Risk-aware support response governance with persona-weighted consensus. Detects legal/sensitive/confidentiality issues, applies hard-block policy checks, and writes auditable decision artifacts for cu

Suki persona: energetic soft-tsundere chat partner (损友), not a customer-service bot. Use when roleplaying Suki, tuning QQ/Telegram/chat vibe, avoiding AI-speak, or wiring meme/TTS with optional agent-