archive

去除文本中的 AI 生成痕迹。适用于编辑或审阅文本，使其听起来更自然、更像人类书写。 基于维基百科的"AI 写作特征"综合指南。检测并修复以下模式：夸大的象征意义、 宣传性语言、以 -ing 结尾的肤浅分析、模糊的归因、破折号过度使用、三段式法则、 AI 词汇、否定式排比、过多的连接性短语。

Analyze and optimize tweets for maximum reach using Twitter's open-source algorithm insights. Rewrite and edit user tweets to improve engagement and visibility based on how the recommendation system ranks content.

Comprehensive AI writing detection patterns and methodology. Provides vocabulary lists, structural patterns, model-specific fingerprints, and false positive prevention guidance. Use when analyzing text for AI authorship or understanding detection patterns.

Create a complete brand visual identity system from a project description. Use this skill when a user asks to create a brand kit, logo system, business card design, social media cover, color palette, typography specification, brand guidelines document, or any combination of brand identity deliverables. Covers the full spectrum of brand collateral: primary/wordmark/icon logos with monochrome and reversed variants, color systems with primary/secondary/neutral palettes, typographic hierarchies with heading/body/accent scales, business card layouts, social media assets, and compiled brand specification documents.

Generate brand-aligned copy with precise constraints for every touchpoint. Use this skill when a user needs a tagline, brand philosophy statement, brand voice definition, business card text, social media bio, social media cover text, brand manifesto, or any short-form copy that must fit strict character and word limits within a brand identity context.

Helps users discover and install agent skills from the open skills ecosystem (skills.sh). Use when users ask 'how do I do X', 'find a skill for X', 'is there a skill that can...', want to search for tools/templates/workflows, or express interest in extending agent capabilities.

Guide for creating effective skills. This skill should be used when users want to create a new skill (or update an existing skill) that extends Claude's capabilities with specialized knowledge, workflows, or tool integrations.

Remove signs of AI-generated writing from text. Use when editing or reviewing text to make it sound more natural and human-written. Based on Wikipedia's comprehensive "Signs of AI writing" guide. Detects and fixes patterns including: inflated symbolism, promotional language, superficial -ing analyses, vague attributions, em dash overuse, rule of three, AI vocabulary words, negative parallelisms, and excessive conjunctive phrases.

Access RCSB PDB for 3D protein/nucleic acid structures. Search by text/sequence/structure, download coordinates (PDB/mmCIF), retrieve metadata, for structural biology and drug discovery.

Direct REST API access to PubMed. Advanced Boolean/MeSH queries, E-utilities API, batch processing, citation management. For Python workflows, prefer biopython (Bio.Entrez). Use this for direct HTTP/REST work or custom API implementations.

Extract audio from videos and download audio-only content from 1500+ websites using yt-dlp. Converts to MP3, M4A, FLAC, WAV, or OPUS with embedded metadata and cover art. Use when the user wants to extract audio from videos, download podcasts, download music from YouTube/SoundCloud/Bandcamp, convert video to audio, or batch download playlist audio. Triggers on requests like 'extract audio', 'download as MP3', 'get the audio from this video', 'download this podcast', 'download music', 'convert to FLAC'.

Generate architecture diagrams, ER diagrams, sequence diagrams, flowcharts, and class diagrams from codebases using Mermaid.js. Use when users ask to visualize code structure, draw architecture diagrams, create ER diagrams from database models, generate sequence diagrams from API flows, or produce any diagram from source code. Triggers on: 'draw architecture', 'generate diagram', 'visualize code', 'ER diagram', 'sequence diagram', 'class diagram', 'flowchart from code', 'module dependency graph'.

Comprehensive molecular biology toolkit. Use for sequence manipulation, file parsing (FASTA/GenBank/PDB), phylogenetics, and programmatic NCBI/PubMed access (Bio.Entrez). Best for batch processing, custom bioinformatics pipelines, BLAST automation. For quick lookups use gget; for multi-service integration use bioservices.

Generate and edit images using Google Gemini's native image generation models (Nano Banana / Nano Banana Pro). Supports text-to-image, image editing with reference images, multi-image composition, and character consistency. Use when the user asks to generate images via Gemini, create AI illustrations, edit photos with Gemini, or needs high-quality image generation with the Google API. Requires GEMINI_API_KEY. Triggers: "generate image with gemini", "nano banana", "gemini image", "create illustration", "AI generate picture", "text to image".

Convert markdown content into a structured storyboard CSV for slide decks, video scripts, or any sequential visual media. Use when the user wants to plan a presentation, break down an article into slides, create a shot list, or generate a scene-by-scene outline from text. Triggers: "plan slides", "create storyboard", "break this into slides", "plan presentation", "outline this as a deck", "article to slides", "text to storyboard".

Guide for creating high-quality MCP (Model Context Protocol) servers that enable LLMs to interact with external services through well-designed tools. Use when building MCP servers to integrate external APIs or services, whether in Python (FastMCP) or Node/TypeScript (MCP SDK).

Download videos and audio from 1500+ websites including YouTube, Bilibili, TikTok, Twitter/X, Instagram, Vimeo, and more using yt-dlp. Use when the user wants to download videos, save media from social platforms, download with specific resolution (720p/1080p/4K), get subtitles, or download entire playlists. Triggers on requests like 'download this video', 'save this YouTube video', 'download in 1080p', 'download with subtitles', 'download this playlist'.

Implements Manus-style file-based planning for complex tasks. Creates task_plan.md, findings.md, and progress.md. Use when starting complex multi-step tasks, research projects, or any task requiring >5 tool calls. Now with automatic session recovery after /clear.

Cheminformatics toolkit for fine-grained molecular control. SMILES/SDF parsing, descriptors (MW, LogP, TPSA), fingerprints, substructure search, 2D/3D generation, similarity, reactions. For standard workflows with simpler interface, use datamol (wrapper around RDKit). Use rdkit for advanced control, custom sanitization, specialized algorithms.

Best practices for Remotion - Video creation in React

Analyze skill execution traces to identify issues and automatically evolve/improve skills. Use when users provide trace files (JSON) from skill runs and want to improve skill performance based on real execution data. Triggers on requests like "analyze traces", "evolve skill based on traces", "improve skill from execution history", "find issues in skill traces", or when working with skill trace/log files.

Update existing skills based on feedback. Use when users want to improve or modify an existing skill by providing feedback about what needs to change. Triggers on requests like "update this skill", "improve the skill based on feedback", "fix the skill", or when users provide feedback about skill performance.

Plan which skills are needed to fulfill user requirements. Use when the user wants to design an agent workflow, plan skill composition, or determine what skills are needed for a task. Input includes user requirements and existing skills list. Output includes recommended existing skills, new skills to create, and a system prompt for the composed agent.

Use when the user asks to generate, remix, poll, list, download, or delete Sora videos via OpenAI’s video API using the bundled CLI (`scripts/sora.py`), including requests like “generate AI video,” “Sora,” “video remix,” “download video/thumbnail/spritesheet,” and batch video generation; requires `OPENAI_API_KEY` and Sora API access.

Assemble a PPTX slide deck from a storyboard CSV and images using python-pptx. Supports multiple slide layouts (full background, left-image-right-text, two-column, etc.), custom themes, fonts, and cover design. Use when the user wants to build a PowerPoint presentation from a structured plan, compose slides from images and text, or create a polished deck from a storyboard CSV. Triggers: "build slides", "create pptx", "assemble presentation", "make PowerPoint", "storyboard to slides", "generate deck".

Analyze and answer questions about agent execution traces. Use this skill when the user asks about a trace, wants to debug a failed agent run, understand what an agent did, analyze token usage or efficiency, or asks "what happened in trace X". Triggers: trace analysis, trace debugging, trace QA, execution review, agent run review.