Use when the user asks to create, refine, or adapt a creator-content thumbnail or cover for short video, Bilibili, Douyin, WeChat, or similar platforms from a title, summary, portrait, logo, or app reference. It runs a four-concept selection stage followed by five responsive platform ratios. Do not use for book or…
Initialize a Harness Engineering framework in the current project. Use when user says 'harness', 'init harness', 'initialize framework', 'setup harness engineering', '/harness', or wants to set up a Plan-Build-Verify development workflow with specialized agents (planner, generator, evaluator). Creates CLAUDE.md, agent…
Use this agent to audit documentation freshness. Compares docs/ content against actual code state, identifies stale references, missing documentation for new features, and outdated examples. Trigger when user says "doc check", "doc audit", "garden docs", or at the end of each sprint cycle.
Use this agent to test implementations against sprint contracts and specifications. Uses Playwright MCP for E2E testing, Chrome DevTools for UI inspection, and visual tools for verification. Grades implementations and provides specific failure reports. Trigger when user says "test", "evaluate", "qa", "verify", or…
Use this agent to implement features one sprint at a time. Given a specification from docs/specs/, implement the feature following sprint contracts in docs/contracts/. After each sprint, run self-verification before handing to the evaluator. Trigger when user says "build", "implement", or "code".
Use this agent to expand a brief feature description (1-4 sentences) into a comprehensive specification with acceptance criteria, component design, data flow, and edge cases. Trigger when user says "plan", "spec", "design", or when beginning any new feature.
A tool for generating 3D models from text, images, multiple views, or sketches through Tencent's Hunyuan 3D services. It can produce models with different material and topology options when those services support them.
Standalone multi-agent image generation skill for Hermes. Includes an internal design compiler, GPT-Image-2 generation via apimart.ai, case library reuse, interactive reference selection, batch workflows, and style-consistent series generation.
An image-generation agent that uses the repository's built-in design compiler to create images. The description does not specify the image types or controls it supports.
An agent for organising generation records, managing an asset library, and creating traceable metadata. Metadata is information that records details about files or actions.
A guided method for rethinking life plans from the higher levels of neuro-linguistic programming, a framework for examining how beliefs and goals shape actions.
Create a scroll-controlled cinematic product website with rich motion (动效网站) from product materials, reference pages or videos, and brand assets. Use for requests involving 网站动效, immersive product landing pages where scrolling moves a continuous video forward and backward, multi-scene visual storytelling, direct…
Transform ordinary snapshots—including daily moments, portraits, objects, pets, food, interiors, streets, architecture, landscapes, travel, and humanistic scenes—into the restrained Shijing Paper Zine visual style. Use when the user wants any real photo turned into a spacious paper-editorial composition with an…
Fetch recent posts from one or more X/Twitter accounts through twitterapi.io, output structured JSON/CSV records, optionally sync records to Feishu/Lark Bitable through feishu-cli, and optionally guide recurring execution through OpenClaw, Codex automations, cron, or launchd. Use when the user wants to monitor X…
Download videos and extract original post captions, audio transcripts, and metadata from video platform links. Use when the user provides Douyin, Bilibili, WeChat Channels, Xiaohongshu, or YouTube links and asks to save the original video, capture the post text/caption, transcribe the spoken in-video script/copy…