Search Skills
Find the perfect capability for your agent.
document-qa
Extract content from documents (PDF, Word, Excel, PowerPoint) and answer questions with source citations
chapter-translation
Translate textbook chapter content into Urdu on demand while preserving technical accuracy and formatting.
log-to-llm-chunker
Convert large log files into uploadable plain-text chunks sized for LLM review; use when a log is too big for a single prompt/file and you need ~500k-token target parts.
template-miner
過去資料からテンプレ・スタイルガイド・チェックリストを抽出して資産化する。テンプレが無い、文書品質がバラつく、過去資料を活用したいときに使う。
xml-handler
Manipuler TOUS les fichiers XML quelle que soit leur taille. TOUJOURS utiliser ce workflow pour tout fichier .xml. Mots-clés: XML, xpath, xmllint, xmlstarlet, extraction, structure, modification.
urdu-language-support
Implement Urdu language support with RTL layout, translations, and AI responses in Urdu. Bonus feature (+100 points) for Phase 5. (project)
fractal-docs
Automatically add or update documentation following the Fractal Docs Protocol. 自动添加或更新符合分形文档协议的文档。 Use when: - Creating new source files (add [IN]/[OUT]/[POS] headers) - Creating new folders (add .folder.md) - Modifying existing files (update headers and .folder.md) - Running documentation audit - User mentions "fractal", "doc protocol", "add headers", "补全文档"
rag-ingestion-v1
Document ingestion pipeline - docs to chunks to metadata for RAG
analyze-documents
Analyzes all documents in a folder and creates a comprehensive summary. Use when asked to summarize documents, understand a collection of files, get an overview of materials, or analyze what's in a folder.
natural-text-corrector
Corrects English text by removing AI-generated patterns (excessive em dashes, formal phrases), fixing speech-to-text errors (homophones, punctuation, capitalization), and improving natural flow while preserving the author's original voice and intent. Use when user asks to correct, fix, naturalize, or de-AI-ify text from any source.
simple-pdf-skill
PDF processing skill for creating, editing, extracting, and merging PDFs using Python libraries.
youtube-transcript-downloader
Downloads YouTube video transcripts (subtitles/captions) using yt-dlp, with a fallback to Whisper transcription if no subtitles are available. Use when a user provides a YouTube URL and asks for a transcript, captions, or subtitles.
audio-implementation
Use when implementing audio features, adding new instruments, or modifying Tone.js synthesis - ensures proper resource management, prevents memory leaks, and maintains consistent audio quality
image-processing
Smart image processing for resize, compress, and convert operations with batch support. Use when users ask to resize images, compress photos, convert to WebP/AVIF, batch process images, optimize for social media, or create image thumbnails. Supports modern formats and aspect ratios.
video-transcript-downloader
Extract, summarize, and download video/audio/subtitles using yt-dlp/ffmpeg. Use when the user requests downloads or transcripts.
imagemagick
Image manipulation and conversion using ImageMagick inside a secure Docker container
ffmpeg-patterns
FFmpeg video and audio processing patterns. Use when transcoding video/audio, extracting clips, adding filters, merging media, creating thumbnails, or batch processing media files.
gpt-image-1-5
Generate and edit images using OpenAI's GPT Image 1.5 model. Use when the user asks to generate, create, edit, modify, change, alter, or update images. Also use when user references an existing image file and asks to modify it in any way (e.g., "modify this image", "change the background", "replace X with Y"). Supports text-to-image generation and image editing with optional mask. DO NOT read the image file first - use this skill directly with the --input-image parameter.
