context-optimization
Safe 76Optimize Context for Longer Conversations
by muratcankoylan
Limited context windows constrain complex tasks and increase API costs. This skill provides proven techniques to double or triple effective context capacity through compaction, observation masking, KV-cache optimization, and context partitioning.
context-fundamentals
Safe 76Master Context Engineering Fundamentals
by muratcankoylan
Context is the foundation of effective AI agent performance. This skill teaches you how to understand, design, and optimize context in agent systems. Learn the principles of progressive disclosure, attention mechanics, and context budgeting to build more capable AI agents.
context-degradation
Safe 76Diagnose AI Context Degradation
by muratcankoylan
AI agents lose performance as conversations grow longer. This skill diagnoses lost-in-middle problems, context poisoning, and attention failures to restore optimal agent performance. It provides patterns for recognizing and mitigating context degradation.
context-compression
Safe 78Compress conversation context
by muratcankoylan
Long agent sessions generate millions of tokens that exceed context limits. This skill provides structured compression strategies that reduce token usage while preserving file paths, error messages, and decisions so agents can continue working without re-fetching information.
bdi-mental-states
Safe 71Model AI Agent Mental States with BDI Ontology
by muratcankoylan
Transform RDF data into cognitive agent architectures using formal Belief-Desire-Intention patterns. Enable AI systems to model rational agency with traceable reasoning chains and semantic interoperability for multi-agent systems.
advanced-evaluation
Safe 77Evaluate LLM outputs with reliable scoring
by muratcankoylan
Manual evaluation of LLM outputs is slow and inconsistent across reviewers. This skill provides production-grade techniques for automated evaluation using LLMs as judges. It includes direct scoring rubrics, pairwise comparison with position bias mitigation, and confidence calibration.
generating-solana-projects
Low Risk 67Generate Solana Blockchain Projects
by MSzgy
Creating Solana blockchain projects from scratch requires understanding Anchor framework conventions, Rust smart contract structure, and Next.js frontend integration. This skill generates complete production-ready projects with proper structure, configuration, and wallet integration.
opentui
Safe 73Build Terminal UIs Faster with OpenTUI
by msmps
Building terminal user interfaces from scratch requires deep knowledge of TUI rendering, keyboard handling, and layout. This skill provides comprehensive OpenTUI reference documentation covering the core API, React reconciler, and Solid reconciler so you can develop TUIs efficiently.
pitchcraft
Low Risk 73Write executive briefings that get decisions made
by moshuying
Most status updates and pitches describe work instead of persuading. PitchCraft turns scattered notes into Hook→Context→Proposal→Evidence→Ask briefings that win approval, funding, or renewals in five reusable scenarios.
modelarts-skill
Low Risk 79Manage Huawei Cloud ModelArts AI Platform
by modelarts-agent
Cloud AI teams struggle with managing complex ModelArts resources through web consoles and fragmented scripts. This skill provides a unified command interface to manage notebooks, training jobs, inference services, resource pools, VPC networks, and KMS keys through natural language.
huawei-cloud-modelarts-skill
Safe 74Manage Huawei Cloud ModelArts Resources
by modelarts-agent
Simplify AI model development and deployment on Huawei Cloud ModelArts. This skill provides unified resource management for training jobs, models, inference services, and notebooks with built-in security features.
diasporic-intelligence
Safe 76Cite And Apply Diasporic Intelligence With Source Credit
by MinistaJazz
Teams using cultural AI terminology often strip source credit, consent, and revocation requirements, which flattens the framework into generic diversity language. This skill keeps Diasporic Intelligence attached to its author, governance requirements, and lineage boundaries when writing, reviewing, or implementing AI systems.
vision-analysis
Low Risk 67Analyze and describe images with AI vision
by MiniMax-AI
Extract meaning from images without manual effort. This skill analyzes photos, screenshots, charts, and mockups using the MiniMax vision MCP to provide detailed descriptions, text extraction, and design feedback.
slide-making-skill
Medium Risk 52Slide Making Skill
by MiniMax-AI
An AI skill for Claude, Codex, and Claude Code
shader-dev
Medium Risk 49Shader Dev
by MiniMax-AI
An AI skill for Claude, Codex, and Claude Code
react-native-dev
Medium Risk 54React Native Dev
by MiniMax-AI
An AI skill for Claude, Codex, and Claude Code
pr-review
Low Risk 75Review pull requests for skill quality
by MiniMax-AI
Manual review of pull requests in the MiniMax Skills repository can miss structural issues and quality standards. This skill provides automated validation and guided content review to ensure every skill meets repository standards before merging.
pptx-generator
Low Risk 70Create and edit PowerPoint presentations with AI
by MiniMax-AI
Generate professional PowerPoint presentations from scratch or edit existing templates using PptxGenJS and XML workflows. This skill handles slide creation, design system application, content extraction, and template-based editing without requiring PowerPoint software.
ppt-orchestra-skill
Medium Risk 51Ppt Orchestra Skill
by MiniMax-AI
An AI skill for Claude, Codex, and Claude Code
ppt-editing-skill
Medium Risk 51Ppt Editing Skill
by MiniMax-AI
An AI skill for Claude, Codex, and Claude Code