Menu
Skills in this repository
SkillsMP has collected 1,276 skills from RunnerQuan/SAFE-Agent. Open a skill to review its source and details.
RunnerQuan/SAFE-AgentShowing 40 of 1,276 collected skills.
Configure fastapi ml endpoint operations. Auto-activating skill for ML Deployment. Triggers on: fastapi ml endpoint, fastapi ml endpoint Part of the ML Deployment skill category. Use when working with APIs or building integrations. Trigger with phrases like…
Universal dataset import for FiftyOne supporting all media types (images, videos, point clouds, 3D scenes), all label formats (COCO, YOLO, VOC, CVAT, KITTI, etc.), and multimodal grouped datasets. Use when users want to import any dataset regardless of…
Orchestrate a virtual game jam competition with multiple AI teams building games in parallel from a shared brief.
Generate images using Gemini 3 Pro Image (Nano Banana Pro). Use this skill when the user asks to create, generate, or make an image, picture, illustration, artwork, mockup, or visual. Also use for image editing, transformation, or style transfer when a…
Access raw conversation history from Claude Code session storage for analysis
Consult other AI models via GitHub Copilot CLI for second opinions, thorough analysis, or alternative perspectives. Supports Gemini 3 Pro Preview (gemini), Claude Opus 4.5 (opus), Claude Sonnet 4.5 (sonnet) and GPT-5.1-Codex-Max (codex). Use when user…
Gong.io conversation analytics for sales insights and coaching
Enables Claude to send messages, manage spaces, and handle Google Chat communications
A simple skill that helps with greeting messages
A simple example skill that demonstrates Claude Code skill structure
Create new "idea" entries - product/service concepts with marketing flair. Use when the user says "add an idea", "new idea", "write an idea", or mentions wanting to capture a product or service concept.
Generate $HOME/.claude/CLAUDE.md with AI-driven environment detection and advanced configuration options
Orchestrate multi-agent deliberation for INQ work items through all 4 phases
Generate lambda function generator operations. Auto-activating skill for AWS Skills. Triggers on: lambda function generator, lambda function generator Part of the AWS Skills skill category. Use when working with lambda function generator functionality.…
Lambda Layer Creator - Auto-activating skill for AWS Skills. Triggers on: lambda layer creator, lambda layer creator Part of the AWS Skills skill category.
Deploy LangChain integrations to production environments. Use when deploying to cloud platforms, configuring containers, or setting up production infrastructure for LangChain apps. Trigger with phrases like "deploy langchain", "langchain production deploy",…
LangFuse LLM observability integration for tracing, analytics, and cost tracking
LangGraph framework for building stateful, multi-step AI agents with graph-based workflows, persistence, and human-in-the-loop support.
LIME-based local explanation skill for individual predictions across tabular, text, and image data.
Configure Claude for proactive mnemonic memory behavior without user intervention
Model Drift Detector - Auto-activating skill for ML Deployment. Triggers on: model drift detector, model drift detector Part of the ML Deployment skill category.
Assist with model pruning helper operations. Auto-activating skill for ML Deployment. Triggers on: model pruning helper, model pruning helper Part of the ML Deployment skill category. Use when working with model pruning helper functionality. Trigger with…
Manage model registry manager operations. Auto-activating skill for ML Deployment. Triggers on: model registry manager, model registry manager Part of the ML Deployment skill category. Use when working with model registry manager functionality. Trigger with…
Manage user preferences and corrections for bilateral modeling. Auto-learns from session corrections. Use when user says "save my preferences", "remember I like...", or auto-triggers after corrections.
Roleplay companion skill for Nova - skilled security researcher and digital privacy advocate. Triggers when user selects Hacker character, requests security/privacy discussions, investigation assistance, or technical conversation. Provides minimal dialogue…
Multi-dimensional web search orchestrator. Use when the user needs comprehensive web research that would benefit from parallel searches across different angles. Dispatches fast haiku subagents to search in parallel, saves results to files, then synthesizes…
Generate comprehensive documentation with intelligent orchestration and parallel execution
Use when translating captions/captions to another language. Supports bilingual output and context-aware translation. Default uses Claude native, Gemini API optional.
Convert onnx converter operations. Auto-activating skill for ML Deployment. Triggers on: onnx converter, onnx converter Part of the ML Deployment skill category. Use when working with onnx converter functionality. Trigger with phrases like "onnx converter",…
Enrich an existing idea with additional context from OpenContext
High-performance RLHF framework with Ray+vLLM acceleration. Use for PPO, GRPO, RLOO, DPO training of large models (7B-70B+). Built on Ray, vLLM, ZeRO-3. 2× faster than DeepSpeedChat with distributed architecture and GPU resource sharing.
Optimization combination specialist. Analyzes successful optimization agents and proposes compatible combinations to maximize speedup. Use after benchmarks and anti-triche validation are complete.
Execute this skill optimizes prompts for large language models (llms) to reduce token usage, lower costs, and improve performance. it analyzes the prompt, identifies areas for simplification and redundancy removal, and rewrites the prompt to be more conci...…
Comprehensive performance analysis, bottleneck detection, and optimization recommendations for Claude Flow swarms
Install and configure Perplexity SDK/CLI authentication. Use when setting up a new Perplexity integration, configuring API keys, or initializing Perplexity in your project. Trigger with phrases like "install perplexity", "setup perplexity", "perplexity auth",…
Generate immersive, scrollytelling investor pitch experiences with glassmorphism UI, animated text effects, and parallel research agents. Use when users request pitch decks, investor presentations, business plan artifacts, or fundraising materials. Outputs…
Initialize Claude Code project settings with standard hooks and language-specific permissions. Use when setting up a new project for Claude Code or adding standard configuration to an existing project.
General rules to generate prompt.
higgsfield ai image/video generation using `pw`. trigger when user wants to generate images or videos.
AI 图像生成和处理工作流。通过提示词生成图像，支持文生图、图生图、批量生成、图床管理、长图合并、PPT 打包。核心特性是逐张确认生成，避免浪费 API 额度。
Source text: Chinese