Scan to join WeChat groupBrowse curated skills with source links, package snapshots, README assets and install signals in one calm, searchable catalog.
AI-powered prompt refinement and improvement using the Promptheus MCP server. Use this skill whenever the user asks to refine, improve, rewrite, or optimize a prompt. Trigger phrases include "refine t…
To solve the context issues of sub-agents, a pattern of gradually refining context acquisition
Use this skill when the user asks to "humanize this text", "make this sound less like AI", "fix AI writing patterns", "make this more natural", "rewrite to sound human", or mentions AI-sounding text, …
GPU-optimized OCR using Surya. Use when: (1) Extracting text from images/screenshots, (2) Processing PDFs with embedded images, (3) Multi-language document OCR, (4) Layout analysis and table detection…
This skill should be used when the user asks to "optimize context", "reduce token costs", "improve context efficiency", "implement KV-cache optimization", "partition context", or mentions context limi…
Extract and document someone's authentic writing voice from samples. Use when someone needs a 'voice guide,' wants to capture their writing DNA, or needs to train AI to write in their style. Also usef…
Use when live speech translation is needed with Alibaba Cloud Model Studio Qwen LiveTranslate models, including bilingual meetings, realtime interpretation, and speech-to-speech or speech-to-text tran…
Image processing and optimization. Sharp (Node.js), Pillow (Python), Cloudinary, responsive images, WebP/AVIF conversion, thumbnails, and CDN-based image transformation. USE WHEN: user mentions "image…
Use when implementing OCI GenAI inference APIs, debugging rate limit (429) or token limit (400) errors, selecting between command-r vs command-r-plus, handling PHI/PII in prompts, or optimizing GenAI …
Design and optimize the action space, tool definitions, and observation formats for AI agents to improve completion rates.
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…
Process call notes or a transcript — extract action items, draft follow-up email, generate internal summary. Use when pasting rough notes or a transcript after a discovery, demo, or negotiation call, …
Upscale and enhance images with Real-ESRGAN, Thera, Topaz, FLUX Upscaler via inference.sh CLI. Models: Real-ESRGAN, Thera (any size), FLUX Dev Upscaler, Topaz Image Upscaler. Use for: enhance low-res …
Video downloading, stitching, title slides, and YouTube descriptions. Use this skill when downloading videos from Google Drive, creating title slides, stitching multiple videos together, or generating…
Voice cloning workflows with Alibaba Cloud Model Studio Qwen TTS VC models. Use when creating cloned voices from sample audio and synthesizing text with cloned timbre.
Transforms raw meeting transcripts into high-fidelity, structured meeting minutes with iterative review for completeness. This skill should be used when (1) a meeting transcript is provided and meetin…
Search memory — sends Huginn (quick grep) first, then Munin (deep agent search) if needed
As a proxy engineer, operate using evaluation-priority execution, decomposition, and cost-aware model routing.
AI and machine learning workflow covering LLM application development, RAG implementation, agent architecture, ML pipelines, and AI-powered features.
Automate Google NotebookLM via the notebooklm-py Python library. Use this skill whenever the user wants to: - Create, manage, or delete NotebookLM notebooks - Add sources (URLs, YouTube, PDFs, files, …
Stand up a production-ready AI employee operating system in one guided session. Outputs 7 ready-to-use files: IDENTITY.md, SOUL.md, AGENTS.md, USER.md, MEMORY.md, HEARTBEAT.md, TOOLS.md.
AIPPT - Customized PPT generation based on templates. Placeholder images to define style → Prompt words replace content → AI generates images → Package into PPTX.
Generate or refine images with Seedream (text-to-image + image-to-image).
Generate videos from text prompts with Kling AI. Use when creating videos from descriptions or learning prompt techniques. Trigger with phrases like 'kling ai text to video', 'klingai prompt', 'genera…