Total 56,744 skills, AI & Machine Learning has 9437 skills
Showing 12 of 9437 skills
Implement comprehensive evaluation strategies for LLM applications using automated metrics, human feedback, and benchmarking. Use when testing LLM performance, measuring AI application quality, or establishing evaluation frameworks.
Transcribe non-realtime speech with Alibaba Cloud Model Studio Qwen ASR models (`qwen3-asr-flash`, `qwen-audio-asr`, `qwen3-asr-flash-filetrans`). Use when converting recorded audio files to text, generating transcripts with timestamps, or documenting DashScope/OpenAI-compatible ASR request and response fields.
Expert in LangGraph - the production-grade framework for building stateful, multi-actor AI applications. Covers graph construction, state management, cycles and branches, persistence with checkpoin...
Review recent work, identify process gaps and repeated mistakes, and produce specific file edits to prevent them. Not a reflection exercise — outputs config and identity changes. Trigger manually after sprints, or automate weekly.
Generate and edit images using AI. Use when users ask to: create/draw/generate images, edit/modify photos, change backgrounds, add elements to images, create avatars, make logos, etc. Covers requests like 'draw a cat', 'change the background to blue', 'generate a logo'. NOT for selfies — use the selfie skill for 'send a selfie', 'send me a selfie', 'take a selfie'.
Comprehensive documentation audit and generation. Launches parallel agents for high-level docs, module-level docs, decision records, and state diagrams. Use when: documentation gaps, post-implementation docs, README updates, architecture docs.
This skill should be used when the agent needs to give a spoken voice update to the user, or when reminded by a Stop hook to provide audio feedback. Use this skill to speak a short summary of what was accomplished.
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.