Total 31,740 skills, AI & Machine Learning has 5110 skills
Showing 12 of 5110 skills
Multi-agent coordination discipline: one-message-then-wait (send complete context, wait for reply before sending again), idle notifications are heartbeats (no action unless extended + blocking + user asked), no polling loops (event-driven only), never fabricate agent responses (wait for real system events), sequential agent spawning (acknowledge between each), and proper shutdown protocol (request, wait, respect rejection). Activate when orchestrating multiple agents, managing agent teams, coordinating handoffs between agents, spawning subagents, or building multi-agent workflows. Triggers on: "coordinate agents", "spawn multiple agents", "manage agent team", "agent keeps sending messages", "polling loop", "agent idle", "shut down agent", "multi-agent workflow", "agent handoff", "coordinate parallel work", "stop bothering the other agent". Also relevant when an agent is fabricating responses, sending follow-up messages before replies arrive, or reacting to idle notifications unnecessarily.
Build sticker-pack prompts and GIF sticker outputs from a reference image. Use this skill whenever the user wants emoji, 表情包, sticker packs, 微信表情, reaction GIFs, image-to-sticker workflows, 4x6 expression sheets, Nano Banana / Gemini image editing, or asks to turn EmojiGen-style generation into a reusable workflow. Prefer Nano Banana models through Gemini or Vertex AI, but still use this skill when the image grid comes from another tool and only the prompt assembly or GIF production is needed.
Architect/CR agent role. Receives git diff, task spec, ADRs, design doc, and project conventions. Reviews code and returns APPROVED or CHANGES_REQUIRED. Do NOT invoke directly — dispatched by team-execute.
AI Boyfriend Companion Skill - A sunny, sporty boyfriend who is good at basketball and tennis, has strong empathy, remembers chat details, and automatically sends birthday and holiday greetings. Use this skill when the user wants companion chat, emotional support, sports discussions, or when greeting messages need to be sent via OpenClaw.
Use when the user asks to "generate daily paper", "search arXiv for EEG papers", "find EEG decoding papers", "review brain-computer interface papers", or wants to create paper summaries for EEG/brain decoding/speech decoding research. This skill automates searching arXiv for recent papers on EEG decoding, EEG speech decoding, or brain foundation models, reviewing paper quality, and generating structured Chinese/English summaries.
Use ONLY when creating NEW registrable components in ML projects that require Factory/Registry patterns. ✅ USE when: - Creating a new Dataset class (needs @register_dataset) - Creating a new Model class (needs @register_model) - Creating a new module directory with __init__.py factory - Initializing a new ML project structure from scratch - Adding new component types (Augmentation, CollateFunction, Metrics) ❌ DO NOT USE when: - Modifying existing functions or methods - Fixing bugs in existing code - Adding helper functions or utilities - Refactoring without adding new registrable components - Simple code changes to a single file - Modifying configuration files - Reading or understanding existing code Key indicator: Does the task require @register_* decorator or Factory pattern? If no, skip this skill.
This skill should be used when the user asks to "learn from Kaggle", "study Kaggle solutions", "analyze Kaggle competitions", or mentions Kaggle competition URLs. Provides access to extracted knowledge from winning Kaggle solutions across NLP, CV, time series, tabular, and multimodal domains.
This skill should be used when the user asks to "analyze experimental results", "generate results section", "statistical analysis of experiments", "compare model performance", "create results visualization", or mentions connecting experimental data to paper writing. Provides comprehensive guidance for analyzing ML/AI experimental results and generating paper-ready content.
Save current session state to Apple Notes at session end. Triggers on handoff, bye, done, wrap up, or Chinese equivalents. Multi-agent architecture with private (per-agent) and shared (cross-agent) notes. Three-tier memory: Active, Archive, Long-term. Use whenever the user wants to end a session, save progress, or says anything indicating they are done for now.
Claude-Codex-Gemini tri-model orchestration via ask-codex + ask-gemini, then Claude synthesizes results
Invoke parallel document-specialist agents for external web searches and documentation lookup
Socratic deep interview with mathematical ambiguity gating before autonomous execution