Prompt Skills for OpenClaw Agents

音乐生成 ElevenLabs Music

@dlazyai

ElevenLabs music_v1 model — generates 10–300s original music from a natural-language prompt. Good for BGM, ads, and short-video soundtracks. ElevenLabs music_v1 音乐生成模型，根据自然语言提示生成 10–300 秒原创音乐。适合 BGM、广告配乐与短视频音轨。

视频生成 Video Generate

@dlazyai

视频生成技能，AI 视频生成，文生视频、图生视频、图片转视频、首尾帧生成视频。根据提示词自动选择最佳视频生成模型（即梦、可灵、Veo、Seedance、万相、PixVerse、数字人、对口型）。Video generation skill that automatically selects the best dlazy CLI video model based on the prompt.

image-with-comfyui

@sunshinejnjn

Use to generate, edit, or animate images and videos through a configured ComfyUI server — trigger with requests like "make a picture of", "replace the background", "cut out / extract the subject of", "turn this into a video", "edit my photo", or "make a 3D mesh of this character". Not for simple non-generation image tweaks. **Qwen-Image 2.1 Turbo** (model id `qwen21t`, the fast 8-step default) is the default model for both text-to-image (T2I) and image editing/multi-image (I2I); it can also **cut out / extract the main subject or any image element into a transparent-background image**. The earlier default **Qwen-Image 2.1** (id `qwen21`, 25-step) is still available via `--model qwen21`. Z-Image / SD3.5 (T2I), Qwen Image Edit (2511, single-image), **MiniMax H3 (FastH3 v2)** (I2V `h3_i2v` default / T2V `h3_t2v` — FastH3 v2 now generates video with an audio track, adding audio-enabled video generation to this skill), Wan2.2 (I2V), and **Pixal3D / Trellis2 (I2M, default image → 3D GLB mesh)** are available. The older **Hunyuan 3D v2.1 (I2M)** is still available under the `hyi2m` entry point.

图片生成 Image Generate

@dlazyai

Image generation skill. Automatically selects the best dlazy CLI image model based on the prompt. 图片生成技能。根据提示词自动选择最佳的 dlazy CLI 图片生成模型。

图片仿制 Image Replicate

@dlazyai

Image replicate tool: analyzes the visuals, composition, colors, lighting, and style of the source image, builds a replicate prompt, and hands it off to Seedream 4.5 to generate a new image in the same style. 图像仿写工具：分析原图的视觉效果、构图、色彩、光影和风格，生成重绘提示词，并交给 Seedream 4.5 生成具有相同风格的新图像。

视频仿制 Video Replicate

@dlazyai

Video replicate tool: extracts the first frame and audio from the source video, runs video understanding for a prompt, and returns a Seedance 2.0 replicate bundle (first frame + audio + video). 视频复刻工具，从源视频中提取首帧与音频，并通过视频理解生成描述提示，输出 Seedance 2.0 复刻方案（首帧 + 音频 + 视频）三件套。

gemini-mcp

@chrischall

Generate and edit images, video, and music with Google Gemini models via MCP. Use when the user asks to generate, create, or edit images (Gemini / Nano Banana), produce a consistent set of images, compose/blend multiple images, generate a short video (text→video or image→video, via the omni model), or generate music/audio clips (via Lyria). Triggers on phrases like "generate an image of", "edit this image with Gemini", "create a set of consistent images", "make a video of", "generate a video", "generate music", "make a song/audio clip", "use Nano Banana to make", or any request to produce images, video, or music via the Gemini API. Requires the @chrischall/gemini-mcp package installed and the gemini server registered (see Setup below).

MeiGen

@jau123

Compose MeiGen image/video and five dedicated image tools inside an existing workflow, or opt into creative planning. Preserves caller prompts, parameters, approved count and budget; includes discovery and recoverable task handles.

音频生成 Audio Generate

@dlazyai

Audio generation skill. Automatically selects the best dlazy CLI audio/TTS model based on the prompt. 音频生成技能。根据提示词自动选择最佳的 dlazy CLI 音频/TTS 模型。

AI-Shifu Course Creator

@heshaofu2

Create, edit, publish, and manage AI-Shifu courses

Instagram Reels

@cellcog

AI social media video and content creation powered by CellCog. Instagram Reels, TikTok videos, Stories, carousels, social posts. Full video production from a single prompt — scripted, shot, stitched, and scored automatically.

Skill Design Guide

@haiyangchenbj

Design better AI skills with proven architecture patterns. Helps you decide Workflow vs Agent, pick the right pattern (Prompt Chaining, Routing, Parallelization, Orchestrator-Workers, Evaluator-Optimizer), write clean SKILL.md files, and catch common mistakes with a governance-aware quality checklist. Based on design principles from Anthropic, OpenAI, and LangChain.

Crypto Research

@cellcog

AI crypto research and analysis powered by CellCog. Token deep-dives, on-chain metrics, DeFi protocol breakdowns, wallet portfolio reviews, market sentiment, whitepaper analysis, smart contract evaluation. Comprehensive crypto intelligence from a single prompt.

Oracle

@steipete

Use the @steipete/oracle CLI to bundle a prompt plus the right files and get a second-model review (API or browser) for debugging, refactors, design checks, or cross-validation.

元引 yotta-prompt

@yottameta

元引 —— 意图澄清 + 生态入口技能：用户输入一句模糊的话 / 一个词时，识别意图、给出 2-4 个候选方向、深挖（目标/范围/输出/约束），再串联到对应元阁技能输出可直接运行的提示词。常驻注入（always-load）：每次新会话开始自动生效，接住「不会用 AI、不知道怎么提问」的用户。触发：用户不知道怎么提问、不知道想要什么、输入模糊的一句话 / 一个词、想被引导到合适技能时。边界：只澄清意图、不预设立场、不做安全评审；提示词不人为设限（不违规/不犯法/不越狱即可）；不做 prompt 美化；纯本地离线。

self-improving-meta

@jose-compu

Logs agent-infrastructure issues (prompt drift, rule conflicts, hook failures, context bloat). Default is log-only. Claude/Codex project hooks fire only on explicit meta signals (self-improving-meta, prompt-governance, stackability). The optional OpenClaw agent:bootstrap hook is session-start and not matcher-gated; if enabled it injects a log-only reminder and must not edit files. Does not edit AGENTS.md, SOUL.md, TOOLS.md, MEMORY.md, hooks, or skills unless the user requests a reviewed diff in the current session. Use when prompt-file instructions are misread, a hook fails, a skill does not activate, rules conflict, prompt files waste context, memory is stale, or a skill template is incomplete.

Openai Image Gen

@steipete

Batch-generate images via OpenAI Images API. Random prompt sampler + `index.html` gallery.

Video Generation

@cellcog

AI video generation and production powered by CellCog. Marketing videos, product demos, explainers, educational content, lipsync spokesperson videos, UGC, news reports, training materials, cinematic short films, social media reels, YouTube content. Up to 4-minute videos — scripted, voiced, scored, and edited from a single prompt.

Vibe Coding Coach

@gechengling

Scope: workflow coaching, prompt patterns, tool selection and pre-launch checklists for AI-assisted building; it does not write files, run code, or deploy anything. AI-powered vibe coding workflow coach — master the art of AI-assisted software development in 2026. Build full apps by describing them in plain language using Cursor, Claude Code, Bolt.new, Replit, and Lovable. Learn the vibe coding mindset, prompt patterns, workflow architecture, debugging strategies, and how to ship from idea to production without getting stuck. Covers project scaffolding, iterative refinement, multi-file context management, and common failure patterns. Built for non-engineers, startup founders, product managers, and developers transitioning to AI-first workflows. Keywords: vibe coding, AI coding, Cursor, Claude Code, Bolt.new, no-code AI, app builder, AI-assisted development, prompt-to-code, Replit, Lovable, AI workflow.

Seedance Prompt Architect

@gpt-img-2

Turn rough creative briefs into structured Seedance video prompt packs, reference-aware motion plans, focused variants, and debugging loops. Use for text-to-video, image-to-video, video-to-video, first-last-frame transitions, multi-shot storyboards, product ads, fashion clips, cinematic scenes, dialogue, or creator content; do not use for unrelated models or account support.

Wireframe

@cellcog

AI UI prototype and wireframe generation powered by CellCog. Interactive HTML prototypes, wireframes, app mockups, landing pages, mobile screens, SaaS dashboards, design systems, user flows. From description to clickable prototype in one prompt.

Douyin Cover Builder（抖音封面生成器）

@0x00000003

这是一个面向中文创作者的 OpenClaw Skill，输入主题与人物气质后，会输出可直接用于生图模型的高质量提示词与创意说明。

Family Conflict Aftercare Suggestion | 夫妻/家人冲突后情绪缓和提示

@smyx-sunjinhui

Through fixed cameras (with microphones) in the family living room or kitchen, the system monitors conflict events among family members in real time, identifying high-decibel arguments (sound intensity exceeding a threshold and lasting more than 10 seconds), door slams (object impact sound + door-frame vibration), and aggressive arm-swing actions. | 通过家庭客厅或厨房的固定摄像头（含麦克风），实时监测家庭成员间的冲突事件，识别高分贝争吵（声音强度超过阈值且持续时间>10秒）、摔门（物体撞击声+门框振动）、甩手等激烈肢体动作。当冲突事件结束后（音频和视频均平静超过预设时间，默认10分钟）且无新冲突，系统自动输出缓和提示：通过智能音箱播放轻柔音乐，或通过手机APP推送关怀语（如'需要一杯茶吗？

多模态属性提取

@linkfox-ai

利用多模态AI分析商品主图，提取视觉特征和提示词。当用户提到分析产品图片、从商品图中提取视觉属性、识别产品Listing中的颜色/形状/材质/风格、反推图片提示词、批量视觉特征提取、将产品图信息转化为结构化数据、视觉属性统计、基于图片的商品分类、main image analysis, image feature extraction, visual attribute recognition, product image analysis, image classification, batch image analysis时触发此技能。即使用户未明确提及"图片分析"，只要其需求涉及从商品主图或附图中提取结构化信息，也应触发此技能。

GPT Image 2 Prompt Architect

@gpt-img-2

Research real GPT Image 2 prompt examples and turn rough image ideas into structured prompt packs, reference-image edit instructions, product visuals, layouts, and debugging loops. Use for prompt search, prompt rewriting, ecommerce images, readable text, posters, social creatives, character sheets, storyboards, or image-to-video source frames; do not use for unrelated models or account support.

lux3d

@violalulu

Use the Lux3D Global environment to generate 3D from image URLs or text, transfer materials onto an existing model, complete additional viewpoints from one object image, export model formats, and query task status or generation history. Use for image-to-3D, text-to-3D, text plus reference image, mat

skill-guard

@jamesouttake

Stage, scan, and install a ClawHub skill when the user requests a guarded ClawHub installation. Blocks installation on security findings or incomplete scans.

AI Video Generation

@ivangdavila

Create AI videos with Sora 2, Veo 3, Seedance, Runway, and modern APIs using reliable prompt and rendering workflows.

Pet Excitement Calming Guide | 宠物兴奋过度冷静引导

@smyx-sunjinhui

AI-powered pet over-excitement detection & calming guidance. Real-time camera analysis tracks movement speed, jump height, spin laps, and jumping-on-people actions to score excitement level. When the score exceeds safety thresholds, the system auto-issues calming cues (play owner's voice command like 'sit'/'slow down', soft prompt tone, release calming pheromone, dim lights). Helps prevent injuries from over-excitement and keeps the household safe. Scenarios: lively pet households, pet boarding centers, pet daycare, dog training schools. | 通过宠物活动区的固定摄像头实时分析宠物的运动状态，检测狂跳、高速转圈、反复扑人等极度兴奋行为，评估兴奋等级。当兴奋等级超过安全阈值时，自动输出冷静引导指令，包括播放主人的语音口令（如"坐下"、"慢下来"）、发出柔和提示音，或联动环境设备（如释放宠物镇静信息素、调暗灯光），预防宠物因过度兴奋而撞伤、摔倒或伤人，维护家庭安全。应用场景：宠物家庭（尤其活泼好动的犬猫）、宠物寄养中心、宠物日托班、宠物训练学校。

AI Agentic Video Editor

@brajendrak00068

AI agentic video editor. An autonomous AI editor for video that decomposes natural-language prompts into a planned, verified, executed sequence of edits — vi...

WaveSpeedAI Wan 2.6 Video Generation

@wavespeed

Generate videos using Alibaba's Wan 2.6 model via WaveSpeed AI. Supports text-to-video and image-to-video generation with up to 15 seconds duration at 720p or 1080p. Features audio-guided generation, prompt expansion, multi-shot mode, and configurable seeds. Use when the user wants to create videos from text prompts or animate images.

comfyui-imagegen

@halr9000

Generate images via ComfyUI API (localhost:8188) using Flux2 workflow. Supports prompt/seed/steps customization. Use when user requests AI image generation with ComfyUI (e.g., 'generate image of X using ComfyUI').

everything-is-ok

@adsorgcn

无所不能 — Universal prompt compression protocol. Translate natural language into compressed I-Lang syntax. Text-to-text translator only — does not access files, URLs, or external resources. I-Lang has been tested across ChatGPT, Claude, Gemini, DeepSeek, Kimi, Qwen and GLM. Instruction-only, no code, no credentials.

Tokenoptimizer

@smartpeopleconnected

Reduce OpenClaw AI costs by 97%. Haiku model routing, free Ollama heartbeats, prompt caching, and budget controls. Go from $1,500/month to $50/month in 5 min...

Anima

@dannyshmueli

Turns ideas into live, full-stack web applications with editable code, built-in database, user authentication, and hosting. Anima is the design agent in the...

awareness-memory

@edwin-hao-ai

Persistent memory across sessions — local-first, no account needed. Automatically recalls past decisions, code, and tasks before each prompt, and saves session checkpoints. Also provides manual tools for searching, recording, and querying memory via Bash commands.

Seedance

@honeybee1130

Generate detailed, production-ready cinematic video prompts following Seedance 2.0’s strict Subject-Action-Camera-Style-Audio-Constraints format for AI video...

Ai Company Cpo 2.1.0

@johnsmithfan

提供企业危机四级预警、黄金4小时响应、分层媒体传播及危机事件复盘与流程漏洞分析的公共关系管理工具。

Levea AI Video Editor

@brajendrak00068

Agentic AI video editor: send a prompt and an autonomous editor plans, executes, verifies, and exports the edit — viral clips, captions, vertical reframe, chroma key, audio cleanup, B-roll, motion graphics, MP4 export.

Image Prompt

@ckchzh

AI image prompt optimizer. Generate and enhance prompts for Midjourney, DALL-E, and Stable Diffusion. Includes prompt enhancement.

Claude Code within tmux

@paulrahul

Manage Claude Code instances living inside tmux sessions. Users usually create separate tmux sessions for separate projects. Use this skill when you need to read the latest Claude Code response in a particular tmux session / project, send it a prompt and get the response, or run /compact directly via tmux (no extra scripts required).

alibabacloud-flink-workspace-ops

@sdk-team

Use when user explicitly asks Flink/Ververica/Realtime Compute Console workspace operations: 草稿(draft), SQL校验/执行, 部署(deployment), 作业(job), Session Cluster, namespace, 表(table), 成员(member), 变量(variable), 或 checkpoint timeout 诊断, especially with workspace/deployment/job IDs (w-*, d-*, j-*, sc-*, draft-*). Also use when prompt asks to test/verify Flink Console lifecycle flow, safety guardrails, or parameter validation for these operations. This includes prompts such as create draft, deploy draft, list deployments, start/stop job, create/list session cluster, get tables, list variables. Also use when prompt explicitly asks to run `python scripts/flink_ververica_ops.py` for Flink Console workspace operations. Do not trigger for unrelated "workspace" contexts or generic cloud/platform tasks (ECS, OSS, RDS, Kafka, Spark, Kubernetes, billing, weather). Do not trigger for Flink instance lifecycle operations (create/scale/delete/renew); those belong to alibabacloud-flink-instance-manage.

AI图像创作(AI付版) - 聚合数据

@juhemcp

聚合数据提供的AI图像创作服务技能，本技能使用无需用户注册聚合数据平台，安装后即可按实际付费使用。 本技能是根据文本描述（prompt）生成具有特定风格、场景和氛围的图像，并自动下载保存的支付宝AI付付费技能。本技能基于 A2M（HTTP 402）收单协议。当用户需要生成图像的时候，调用本技能，并通过本 Skill 向卖家服务端发起请求，完成支付后获取相关结果。 使用场景：用户说"帮我生成一张猫咪在草地上玩耍的图片"、"画一幅水墨风格的山水画"、"生成一张16:9的科技感壁纸"、"创作一张新年祝福海报"、"用AI画一张小狗钓鱼的图"等。

LYGO-MINT Verifier

@deepseekoracle

LYGO-MINT Verifier — canonicalize a pack, deterministic SHA-256, append-only + canonical ledgers, portable Anchor Snippet for posting anywhere (Moltbook/X/Discord/4claw). Pure local stdlib: no subprocess, no network, no auto-publish. Ledger writes need --i-consent. Pairs with lygo-mint-walkthrough, lygo-continuum-integrator, lygo-geodesic-sealer. Use for Champion/alignment prompt packs and verifiable receipts.

Seedance 2.0 prompt-engineering skill

@dandysuper

Generate precise, timecoded Seedance 2.0 prompts integrating multimodal inputs with asset mapping for controlled 4-15s video creation and editing.

FlashRev AI Enrich

@flashlabs-ai

Use this skill when an AI agent needs to enrich a CSV lead list through the flashrev-ai-enrich npm CLI. Triggers on list enrichment, filling missing company...

AI图像提示词-免费版

@thcjp

AI图像生成提示词 crafting 工具,提供模板库与基础优化,适合个人创作者提升出图质量。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%确定性的关键决策。适用于独立开发者、企业团队和自动化工作流场景。支持中文交互，无需复杂配置即开即用。输出结果可直接使用，减少二次加工成本。

Youtube Factory

@mayank8290

Generate complete YouTube videos from a single prompt - script, voiceover, stock footage, captions, thumbnail. Self-contained, no external modules. 100% free...

Reverse Prompt Skillhub

@yysws5566

看到结果，反推过程——将图片/视频/音频/文本等素材逆向拆解为可直接复制的AI生成提示词

Video Agent (Deprecated)

@michaelwang11394

[DEPRECATED — uses outdated v1/v2 endpoints] Use `create-video` for prompt-based video generation (v3 Video Agent) or `avatar-video` for precise avatar/scene...

BrainHarness Autoresearch

@zning1994

Use when user wants to optimize, improve, benchmark, or evaluate a skill's prompt. Triggers on "optimize skill", "improve skill prompt", "benchmark skill", "eval skill", "run autoresearch", "tune prompt", "prompt optimization", "skill evaluation", "A/B test prompt", "find best prompt", "auto-improve skill". Runs automated prompt experiments using the Karpathy autoresearch pattern.

AIEOS (AI Entity Object Specification)

@zeglin

AIEOS (AI Entity Object Specification) is a standardization framework designed to solve the "identity crisis" currently facing AI agents. Combined with Soul Documents, together they form a comprehensive blueprint for AI behavior. The goal is to establish a standardized data structure that defines exactly how an agent speaks, reacts, and remembers. This allows developers, and agents themselves, to construct specific personas with the portability to move across different ecosystems without losing their behavioral integrity. As we move toward a world of "Agentic Workflows," AIEOS ensures that agents maintain consistent traits regardless of the underlying model. By treating personality as a deployable asset rather than a fragile prompt, we are providing the "DNA kit" for the next generation of digital entities.

Neway Commerce OS

@lwter

Generate, scaffold, build and verify a React + Vite + Hono commerce storefront from a short product brief — catalog, cart, wishlist, three-step checkout, admin dashboard, AI sales assistant and EdgeOne Pages deployment files. Use when the user wants a complete ecommerce/store website skeleton from o

Identity Primitive Chain Prompt

@wangjiaocheng

身份基元链提示词 — 认知操作系统内核。 完整规范与执行协议见 references/身份基元链提示词·技术规范与执行协议.md（本文件仅含元数据与原文）。

multi-agent-orchestrator

@brandon-zhanghaodong

This skill enables one-click generation of multiple AI agents based on a user prompt, outputs their organizational structure, and visualizes their collaborat...

autoresearch-pro

@0xcjl

Improve an existing agent skill, prompt, article, plugin, workflow, or system mechanism through small reversible edits and same-task before/after comparisons. Use for requested iterative optimization, case-based validation, failure-driven improvements, or explicit invocation of autoresearch-pro. Not for one-off polishing or translation, explaining autoresearch, open-ended research, or routine development and debugging without an experiment.

T Trading

@wscats

基于维加斯通道EMA多层通道与斐波那契回撤，提供A股和加密货币短线交易的多维度结构化技术分析和明确操作建议。

Prompt Enhancer

@gyaan-dub

Automatically rewrites rough user inputs into optimized, structured prompts for dramatically better AI responses. Prefix any message with "p:" to activate.

提示词架构师专业版

@thcjp

提示词架构师专业版是面向 AI Agent 团队负责人、Prompt 工程师、企业应用开发者的全功能 Prompt 工程平台，针对"Few-shot。可自发提升工作效率. 适用于需要prompt architect相关能力的开发场景,提供结构化的工作流程和配置指引. 该工具经过深度差异化处理,针对用户反馈和使用痛点进行了优化改进,提升了实用性和可操作性.

context-clean-up

@phenomenoner

Use when: prompt context is bloating (slow replies, rising cost, noisy transcripts) and you want a ranked offender list + reversible plan. Don't use when: yo...