Total 50,675 skills, AI & Machine Learning has 8495 skills
Showing 12 of 8495 skills
Claude Code CLI usage for automated/headless execution in Daytona sandboxes. Use when running Claude Code commands, configuring authentication, or setting up non-interactive mode.
Fallout 4 AI game console. Translates natural language into Fallout 4 console commands and executes them in-game. Use when the user mentions Fallout 4 cheats, console commands, items, god mode, carry weight, spawning items, teleporting, or any Fallout 4 game modification. Knows all console commands, item Form IDs, perk IDs, NPC IDs, and quest IDs.
AI可读性审计工具，模拟AI爬虫视角评估网站对大语言模型的友好程度，分析结构化数据、语义HTML和Meta信息
Implement Mistral AI reference architecture with best-practice project layout. Use when designing new Mistral AI integrations, reviewing project structure, or establishing architecture standards for Mistral AI applications. Trigger with phrases like "mistral architecture", "mistral best practices", "mistral project structure", "how to organize mistral", "mistral layout".
Prompt engineering standards and context engineering principles for AI agents based on Anthropic best practices. Covers clarity, structure, progressive discovery, and optimization for signal-to-noise ratio.
Audits AI systems for bias, fairness, and privacy. Analyzes prompts and datasets to ensure ethical and safe AI implementation.
Infers user stress/energy levels from interaction patterns (typing speed, error rate). Adjusts response verbosity and visualizes mood via a "Niko-Niko Calendar."
Create a delightful, unexpected "wow" experience for the user by dynamically discovering and creatively combining other enabled skills. Triggers when the user says "surprise me" or any request expressing a desire for an unexpected creative showcase. Also triggers when the user is bored, wants inspiration, or asks for "something interesting".
Claude Code config optimization skill. Use when: - Editing CLAUDE.md, rules/, skills/, agents/, commands/ - User asks about config best practices - Checking optimization status - User says "claude code changelog" or "claude code updates" - User asks about new features or breaking changes in Claude Code
Generates a 1:1 split-screen (front/back) character reference sheet, mirroring facial, physical, and costume details from an uploaded image.
Load PROACTIVELY when decomposing a user request into parallel agent work. Use when user says "build this", "implement this feature", or any request requiring multiple agents working concurrently. Guides task decomposition into parallelizable units, agent assignment with skill matching, dependency graph construction, WRFC loop coordination across up to 6 concurrent agent chains, and result aggregation.
Load PROACTIVELY when task involves building a complete feature across multiple layers. Use when user says "build a feature", "add user profiles", "create a dashboard", or any request spanning database, API, UI, and tests. Orchestrates multi-agent work sequentially: schema and migrations, API endpoints, UI components, tests, and review. Handles dependency ordering and cross-layer type sharing.