MCP App StoreMCP App Store
from agentscope-java2,679
Reactive Java framework skill for building non-blocking, agent-oriented LLM applications using Project Reactor and AgentScope conventions.
AgentScope Java provides concrete guidance and best-practice patterns for writing reactive, message-driven agents in Java using Project Reactor. The skill instructs the agent on non-blocking patterns, correct imports, hook and pipeline usage, testing with StepVerifier, tool definitions, and common pitfalls to avoid when integrating LLM models and tools in production Java services. It includes conventions for project setup (Maven), coding standards, and examples for building ReAct-style agents and toolkits.
Use this skill when a user asks for Java code or guidance targeting the AgentScope framework, when they request reactive (Mono/Flux) examples, when they mention AgentScope, ReActAgent, Project Reactor, or need help converting blocking examples to non-blocking code. It's appropriate for production-ready agent design, hooking tools, and pipeline composition in Java 17+.
Designed for Claude Code and Cursor (per frontmatter). The guidance and examples are standard Java and applicable when generating code for Copilot/Codex-style environments as well.
Instructional skill for AgentScope Java framework — a reactive, message-driven multi-agent system built on Project Reactor. No scripts to execute; the skill is purely a comprehensive coding guide with detailed correct/incorrect patterns, API corrections, and best practices. Very well-written with security-conscious defaults (env vars for keys, SSRF validation in examples), though the npx -y pattern in MCP integration is a minor concern.
Exceptionally detailed framework skill. Explicitly prohibits hardcoding keys, blocking ops, and other antipatterns. Shows SSRF protection in examples. The npx -y usage is the only minor security deduction. Architecture is well-structured but monolithic — a single large SKILL.md without scripts/ or references/ directories. Usefulness is moderate: very valuable for AgentScope Java users but the audience is niche.
Yielding Bear — Unified LLM Routing
A unified LLM routing API that automatically routes requests to the cheapest capable model across providers to reduce inference cost by ~60-80%.
Starlark Dev
Create, debug, and test Kurtosis Starlark packages — write package structure, run dry-runs, and inspect plan execution for reliable orchestration.
Run Execute
Orchestrates execution of work items across modes (autopilot, confirm, validate) with scripted init/complete tooling, plan/test/report artifacts and strict gati
Markdrop
Convert PDFs to structured Markdown or interactive HTML and generate AI-powered descriptions for images and tables using multiple LLM providers.
Alpha Forge Pre-Ship Quality Gates
Pre-merge quality gates for PRs that validate RNG determinism, forked URLs, runtime parameter ranges, and manifest synchronization to reduce review cycles.
OpenTestAI
Automated, high-confidence AI testing: bug detection, persona feedback, and prioritized test-case generation using many specialized tester profiles.
Blender Build-Go (bgo)
Automate build → remove → install → enable → launch cycle for Blender extensions or add-ons to speed up iteration and CI workflows.
Overnight — Autonomous Long-Running Coding
Orchestrates long-running coding goals: decomposes objectives into atomic tasks, dispatches isolated worktree workers, verifies acceptance criteria, and merges
