AI 技能注册表

Sanitize prompts before sending to LLMs. Detects PII, prompt injection, toxicity, and off-topic content. Returns cleaned text + risk score. Use when: sanitiz...

LoRA fine-tuning pipeline for Stable Diffusion on Apple Silicon — dataset prep, training, evaluation with LLM-as-judge scoring. Use when fine-tuning image ge...

Build strategic roadmaps to grow brand's Share of Model (SoM) in AI-generated responses. Identify content gaps, competitive weaknesses, and prompt-level oppo...

Scan QR codes from invoice receipts and automatically fill electronic invoice applications. Use when user asks to scan QR codes from images, complete electro...

Generate and iteratively edit images. Supports storage, UI for manual editing, history, version branching, time travel, reference images, and multiple AI mod...

Convert articles, blog posts, or any text into professional podcast scripts and TTS audio. Use when a user wants to: (1) Transform written content into conve...

Generate images from text prompts using ZenMux API (Vertex AI protocol with Gemini models). Use when: (1) User wants to generate/create images from text desc...

Route tasks to free AI models via OpenRouter to save money. Use when the agent needs to delegate content writing, research, code generation, or other tasks t...

根据消息命令自动路由到子 Agent。**Agent 应该：收到消息时首先检查是否包含 /coder、/writer 等命令，如果是则调用 sessions_spawn 启动对应子 Agent。**

Image Annotation Quality Control Tool - Automatically detect quality issues in bounding box and polygon segmentation annotations, generate visual reports. Su...

Extract web page content from a URL using Felo Web Extract API. Use when users ask to scrape/capture/fetch webpage content, extract article text from URL, co...

Unified QCut media toolkit — organize project files, process media with FFmpeg, generate AI content, control the QCut editor with native CLI commands, genera...

Generate and edit images using the AceData Nano Banana API. Supports models like nano-banana-2, custom aspect ratios (default 16:9), and resolutions (default...

Collect geo-specific data from any country. Scrape localized pricing, search results, ads, and region-locked content using country-targeted residential proxies.

Helps write SDSL shaders for Stride and vvvv gamma — TextureFX, shader mixins, compute shaders, and ShaderFX composition. SDSL is a superset of HLSL, so use...

Draft and publish Hexo posts end-to-end (front matter + SEO polish + deploy)

Guides an AI assistant to redesign SaaS onboarding flows using the Activation Path Method — helping users define their aha moment, map time-to-value, elimina...

Colorize black and white photos using each::sense AI. Bring old family portraits, historical images, vintage photographs, and archival footage to life with i...

Guitar chord toolkit with chord identification, chord diagrams, capo calculation, and more. Features: - Identify chord from notes (reverse lookup) - Look up...

Turn messy recordings, transcripts, voice notes, or brain dumps into clean, team-ready Standard Operating Procedures (SOPs). Use when you have Loom videos, m...

Generate standardized git commit messages following Conventional Commits format. Use this skill when the user asks to commit code, write a commit message, or...

Fetch transcripts from YouTube videos to provide structured multilingual summaries, Q&A, deep dives

Generate music tailored to video content. Use when users request video_soundtrack operations or related tasks.

Nuclear-grade image metadata cleanser. Strip ALL EXIF/GPS/camera data, re-encode with noise injection. Forensically untraceable, reverse image search resistant.