Scan to join WeChat groupBrowse curated skills with source links, package snapshots, README assets and install signals in one calm, searchable catalog.
Adapt and reproduce Jupyter notebooks, Colab notebooks, GitHub tutorial notebooks, or local notebook folders in ModelScope Notebook. Use when a coding agent must port a tutorial to ModelScope, replace…
HarmonyOS ArkTS application development with ArkUI declarative UI framework. Use when building HarmonyOS/OpenHarmony apps, creating ArkUI components, implementing state management with decorators (@St…
Comprehensive GitHub code review with AI-powered swarm coordination
Generate elegant cover images for articles. Analyzes content and creates eye-catching hand-drawn style cover images with multiple style options. Use when user asks to "generate cover image", "create a…
Manages free AI models from OpenRouter for OpenClaw. Automatically ranks models by quality, configures fallbacks for rate-limit handling, and updates openclaw.json. Use when the user mentions free AI,…
TDesign Mini Program UI component library by Tencent. Use for building WeChat mini apps with TDesign components, design system, and best practices.
API development expert. REST API, FastAPI, Flask, authentication, documentation.
Local LangChain AI documentation reference. Use when asked about LangChain, LangGraph, agents, chains, prompts, memory, tools, retrieval, RAG, vector stores, document loaders, or building LLM applicat…
Identifies common abnormal pet behaviors such as scratching, biting, destructive chewing, jumping, digging, chasing, and separation anxiety, helping owners understand their pet's habits. | 宠物行为识别技能，识别…
Structured debugging methodology using hypothesis-driven investigation, log analysis, and bisection to isolate and resolve defects.
Expert guidance for data analysis, data science, and machine learning projects. Covers Python data tools, SQL/databases, visualization, statistics, ML/AI, data engineering, and MLOps. Use when working…
Local Whisper: audio transcription, multi-language, word timestamps, speaker diarization
Efficiently add, configure, and use shadcn/ui components. Use this skill when the user wants to add UI components, fix styling, or needs the list of available shadcn components.
Create, modify, and manage PowerPoint presentations.
Default to this skill for nearly all external web-access tasks before Firecrawl, browser-use, Playwright, or generic browser CLIs. Use it for fetching pages, reading docs and articles, markdown or tex…
Senior scientific author for literature review synthesis with authority to restructure, rewrite, and add analysis across outline creation, introduction framing, and final synthesis
Comprehensive Flutter performance optimization covering build optimization, rendering performance, memory management, profiling tools, isolates/concurrency, and app size reduction. Use when optimizing…
Remove AI writing patterns from prose. Use when drafting, editing, or reviewing text to eliminate predictable AI tells.
Implements the NOWAIT technique for efficient reasoning in R1-style LLMs. Use when optimizing inference of reasoning models (QwQ, DeepSeek-R1, Phi4-Reasoning, Qwen3, Kimi-VL, QvQ), reducing chain-of-t…
After entering the links of various video websites/podcast platforms, the corresponding media files are automatically downloaded and delivered to the user. Preferentially use yt-dlp to cover common vi…
Mermaid diagram syntax reference for all diagram types — flowchart, sequence, class, state, ER, gantt, git graph, mindmap, timeline, user journey, pie, quadrant, XY chart, block, sankey, C4, kanban, a…
Create Trae IDE rules (.trae/rules/*.md) for AI behavior constraints. Use when user wants to: create a project rule, set up code style guidelines, enforce naming conventions, make AI always do X, or c…
Operate DingTalk messaging APIs through UXC with a curated OpenAPI schema, app-token bearer auth, and robot/service-group guardrails.
Create/update .agent/constitution.md. Use when commands/boundaries/constraints must be confirmed before baseline or code changes. Draft v0 from repo evidence, then interview user.