Total 56,759 skills, AI & Machine Learning has 9442 skills
Showing 12 of 9442 skills
Reflect on the current session and refine skills or CLAUDE.md based on patterns observed. Use when the user says "refine", "what did we learn", or at the end of a session to make skills better through use.
Supports text-to-video and image-to-video (start/end frame). Use when the user needs to generate video, create short videos, or convert text to video. Use cases: (1) Generate video from text description, (2) Use reference images as start/end frame for image-to-video, (3) Customize model, aspect ratio, duration, resolution. Triggers: generate video, text-to-video, image-to-video, AI video.
Fresh-subagent-per-task execution with two-stage review (ADR compliance + code quality). Use when an implementation plan exists with mostly independent tasks and you want quality gates between each. Use for "execute plan", "subagent", "dispatch tasks", or multi-task implementation runs. Do NOT use for single simple tasks, tightly coupled work needing shared context, or when the user wants manual review after each task.
Dispatch independent subagents in parallel for unrelated problems spanning different subsystems. Use when 2+ failures have independent root causes, multiple subsystems are broken independently, or user requests concurrent investigation. Use for "parallel", "multiple failures", "independent bugs", "fix these concurrently". Do NOT use for related failures, shared-state problems, or exploratory debugging where root cause is unknown.
Bridge any AI agent backend to WeChat using the weixin-agent-sdk framework with simple Agent interface, login, and message loop.
Toolkit-first AIClient patterns for generation, text-to-sql, and response parsing.
NotebookLM integration patterns for external RAG, research synthesis, studio content generation (audio, cinematic video, slides, infographics, mind maps), and knowledge management. Use when creating notebooks, adding sources, generating audio/video, or querying NotebookLM via MCP.
Vector embeddings with HNSW indexing, sql.js persistence, and hyperbolic support. 75x faster with agentic-flow integration. Use when: semantic search, pattern matching, similarity queries, knowledge retrieval. Skip when: exact text matching, simple lookups, no semantic understanding needed.
Agent skill for swarm-issue - invoke with $agent-swarm-issue
Agent skill for v3-memory-specialist - invoke with $agent-v3-memory-specialist
Generate infographic images from user descriptions using Gemini API (Nano Banana Pro). Converts natural language descriptions into structured infographic prompts, then calls Gemini image generation to produce PNG images. Supports 11 visual styles (sketchnote, kawaii, professional, scientific, anime, claymation, editorial, storyboard, bento grid, bricks), 3 orientations (landscape/portrait/square), 3 detail levels (brief/standard/detailed), and multiple languages. Use when user asks to create infographics, generate visual summaries, make data visualizations, or produce illustrated explanations. Trigger words include 信息图, infographic, 生成图, 可视化, visual summary, data visualization.
This skill should be used when user wants to access, capture, or reference Claude Code session history. Trigger when user says "capture session", "save session history", or references past/current conversation as a source - whether for saving, extracting, summarizing, or reviewing. This includes any mention of "what we discussed", "today's work", "session history", or when user treats the conversation itself as source material (e.g., "from our conversation").