Loading...
Loading...
Found 170 Skills
D7 ORM tablets, ConditionTree queries, Objectify, batch/merge/deleteByFilter writes. Use for entity design, reads, and persistence.
Calculate cryptographic hashes (MD5, SHA1, SHA256, SHA512) for text and files. Compare hashes, verify integrity, and batch process directories.
Handle Evernote API rate limits effectively. Use when implementing rate limit handling, optimizing API usage, or troubleshooting rate limit errors. Trigger with phrases like "evernote rate limit", "evernote throttling", "api quota evernote", "rate limit exceeded".
Transcribe audio and video files to text using OpenAI Whisper. Use when: converting podcasts to blog posts; creating video subtitles; extracting quotes from interviews; repurposing video content to text; building searchable audio archives
Optimize Customer.io API performance. Use when improving response times, reducing latency, or optimizing high-volume integrations. Trigger with phrases like "customer.io performance", "optimize customer.io", "customer.io latency", "customer.io speed".
WPS Office Cross-Application Intelligent Assistant: Unified management of Excel, Word, and PPT, handling cross-application operations and general functions
Convert Mermaid code blocks in .mmd or .md files to animated GIFs with customizable animation styles (progressive, highlight walk, pulse flow, wave).
Production-grade FFmpeg video/audio processing. Convert, compress, trim, merge, resize, and extract audio from media files with progress tracking, comprehensive error handling, and safety limits.
加密货币技术指标服务。支持 27 种技术指标，覆盖 MA/EMA/RSI/MACD/KDJ/布林带/ADX/ATR/CCI/VWAP 等。 当用户询问"BTC RSI""以太坊 MACD""加密货币技术指标""BTC 布林带"时触发。
[Atomic Ingest] Extract local content assets into XY atoms for ingestion — specify a directory (drafts/transcripts/tweets/courseware), extract into jsonl per the atomic standard into incoming/: first audit, extract 3 sample pieces for user confirmation, then batch process, dedupe, validate, and finally prompt build_atoms to ingest. Use when the user says 'make these drafts into atoms', 'ingest my transcripts', 'batch-extract viewpoints'. | Made by Xiaoye
Generates images with Codex (OpenAI's coding agent and its built-in image tool, included in a ChatGPT plan) - YouTube thumbnails, covers, B-roll stills, callout visuals, profile pictures - one Codex job per image, several in parallel, with the creator's photos as reference when the face matters, then copies them into the project with a manifest. Use when the user says generate an image, a thumbnail, a cover, make me a visual, codex images, génère une image, miniature, or when video-publish or video-edit needs an image.
Universal watermark removal with ML-based inpainting and automatic detection. Works on ANY watermark type (Google SynthID, Midjourney, DALL-E, stock photos, logos). Four methods: inpaint (ML, best quality), aggressive (fast), crop (fastest), paint (basic). Auto-detects watermark location in any corner. Use when: (1) Removing ANY type of watermark, (2) Google AI/Imagen/Gemini watermarks, (3) Stock photo watermarks, (4) Logo overlays, (5) Cleaning images for production, (6) Batch processing, or (7) User mentions 'watermark', 'remove watermark', 'clean image', 'SynthID'