Agent Skills Hub

dynamic

Fullstack development agent for bkend.ai BaaS. Automates project init, auth/db setup, and API integration for Next.js applications.

sales-ai-assistant

An AI-powered sales assistant that transforms business scenarios into optimized prompts, automatically generating high-quality emails, proposals, and analysis reports without requiring prompt engineering skills.

deep-thinking

A deep reasoning protocol that ensures systematic analysis, multi-hypothesis generation, and rigorous verification for complex architectural, debugging, and high-stakes tasks.

mobile-android-design

Master Material Design 3 and Jetpack Compose for native Android UI development. Build adaptive, accessible interfaces using Google's latest standards.

coach

A persistent, adaptive coaching assistant that analyzes your Claude Code session history to recommend personalized skills and improve your AI collaboration patterns.

skill-reinforcement

An automated meta-learning skill that improves agent workflows by capturing patterns, failures, and shortcuts after each task execution.

self-improve

Self-maintaining skill for OpenCode agents to update documentation, capture learnings, and extend tool/agent capabilities dynamically.

mermaid-diagram-generator

Generate, validate, and refine Mermaid diagrams including flowcharts, sequence diagrams, ERDs, and architecture maps to visualize complex software systems and workflows.

context-engineering-expert

Advanced context engineering system for orchestrating AI agents, memory management, and token optimization to improve long-term persistence and project intelligence.

technical-writing

Produce clear, professional technical documentation, blog posts, and tutorials based on real engineering experience, prioritizing value and actionable insights.

mcp-prompts

An intelligent development orchestration skill that provides self-improving code analysis, build error diagnosis, and automated workflow configuration via mcp-prompts integration.

context-degradation

Diagnose, isolate, and mitigate LLM context failures like lost-in-middle, poisoning, distraction, and context clash to improve agent reliability.