Total 56,129 skills, AI & Machine Learning has 9347 skills
Showing 12 of 9347 skills
Configure a Stop hook that surfaces unfinished todos before a session ends and suggests creating GitHub issues for deferred work. Use when you want unfinished Claude Code session tasks automatically flagged for GitHub issue creation at session end.
Receive context from parent, child, or sibling session
Rewrite AI-sounding text into natural, human writing by removing common LLM patterns while preserving meaning and tone.
Optimize and restructure user prompts for better AI responses. Use when user writes in non-English (Chinese, Japanese, Korean, etc.), request is vague/unclear, or user asks to improve their prompt. Triggers on: '帮我', '请帮忙', 'お願い', any non-English complex request. Translates, restructures, and shows optimized prompt before proceeding.
Personality-tuned AI for the Di (The Driver) DISC type. Adapts AI tone, structure, and feedback to be bold, competitive, and action-oriented. Powered by Crystal's DISC framework.
Context-aware progressive module loading with hub-and-spoke pattern for token optimization. progressive loading, lazy loading, hub-spoke, module selection.
Transform AI agents from task-followers into proactive partners that anticipate needs and continuously improve. Includes memory architecture with pre-compaction flush (so context survives when the window fills), reverse prompting (surfaces ideas you didn't know to ask for), security hardening, self-healing patterns (diagnoses and fixes its own issues), and alignment systems (stays on mission, remembers who it serves). Battle-tested patterns for agents that learn from every interaction and create value without being asked.
Quantizes LLMs to 8-bit or 4-bit for 50-75% memory reduction with minimal accuracy loss. Use when GPU memory is limited, need to fit larger models, or want faster inference. Supports INT8, NF4, FP4 formats, QLoRA training, and 8-bit optimizers. Works with HuggingFace Transformers.
Detectar sobreexposición, subexposición e iluminación desigual en frames capturados
Terminal-Bench integration for Mux agent benchmarking and failure analysis
Create and publish proprietary skills for the AIOS system. Use when asked to create a new skill, build a skill, make a skill, write a skill, or publish a skill. Also use when converting a workflow or process into a reusable skill, or when user says new AIOS skill or references the aios-skills repository. Do NOT use for installing marketplace skills or editing existing community skills.
Generate videos from text and image prompts via Together AI. 15+ models including Veo 2/3, Sora 2, Kling 2.1, Hailuo 02, Seedance, PixVerse, Vidu. Supports text-to-video, image-to-video, keyframe control, and reference images. Use when users want to generate videos, create video content, animate images, or work with any video generation task.