Development plugins

Skills for analysing AI-evaluation data with HiBayES: installing and running the five-stage pipeline (load, process, model, check, communicate), the YAML config and component registries, and the Bayesian workflow — estimand, pooling choice, priors, diagnostics, model comparison, reporting — with a plain-language concepts reference for explaining results.

2 skills

LangChain 1.0 使用指南。提供 Agent、Tool、Memory、Middleware 等核心概念的快速参考。

1 skill

Agent Teams 智能编排决策引擎。自动分析任务复杂度，判断使用 Subagent 还是 Agent Teams。

1 skill

Search the aixplain marketplace and build, run, and deploy agents, models, knowledge bases, and tools with the aixplain-builder skill, from one plugin.

1 MCP server

Full SDD framework for Claude Code. Iron-law TDD, 72+ commands (/dc:*), 14 skills, 15 reasoning models, and i18n (ES/EN/PT).

Autonomous spec-driven development loop for Claude Code. Three commands: brainstorm, plan, execute.

10 skills · 13 commands · 9 agents · hooks

Evolves LLM agent code using multi-agent proposers, LangSmith experiments, and git worktrees

9 skills · 6 agents · hooks

MCP server for AI coding agents to create, manage, and interact with Quarkus applications. Provides tools for project scaffolding, dev mode lifecycle, extension skills, Dev MCP proxy, and documentation search.

1 MCP server

GMC-aware skills for authoring, debugging, reviewing and testing GMAS gameplay

12 skills · hooks

Skills for building UIs with Mateu: screens in Java (@UI), C# ([UI]), Python (@ui) or YAML (specs/ui), static bundles, project scaffolding, running and screenshotting, federation.

8 skills

Routes Claude Code tasks to focused prompts and adds deterministic documentation, skill, release, safety, and capability-audit workflows.

6 skills · hooks

AI-assisted deep planning with research, interview, external LLM review, and TDD approach

1 skill · 2 agents · hooks

Implement code from /deep-plan sections with TDD, code review, and git workflow

1 skill · 1 agent · hooks

Split vague project requirements into well-scoped units for /deep-plan

1 skill · hooks

Mobile device automation for Android and iOS - control devices with natural language

1 MCP server

Enforce module boundary contracts (readonly, no-new-exports) on Claude Code edits.

1 skill

AI-powered development workflow with planning, implementation, and review commands

14 skills · 13 commands · 12 agents · hooks

Project lifecycle toolkit: initialization, cross-agent user-instruction setup, tracked project memory, tiered model routing, epic/sprint workflow, PR review, onboarding, planning, debugging, engineering loop, manager loop with a live board, agent fan-out, CI/CD, Docker, security, and document processing

17 skills · 5 commands · 3 agents

Machine-learning training and benchmarking on rented cloud GPUs: prebaked RunPod images that boot in seconds instead of minutes, pod lifecycle scripts, GPU selection and pricing ladders, and the provisioning pitfall catalog

1 skill

Design, draw and run AI agent flows that mix providers and agent types, and build assistants with memory and RAG over vector databases, with the Intelli Python library.

1 skill

Core Capacitor skills — app creation, development, upgrades, expert reference, plugin setup, desktop platforms, and MCP server setup.

Capacitor feature integration skills — push notifications (FCM) and in-app purchases.

Framework-specific Capacitor skills — Angular, React, and Vue patterns and best practices.

Roboflow computer vision skills and MCP tools for datasets, annotation, training, workflows, inference, and deployment.

13 skills · 1 MCP server

ATProtocol-specific skills for Claude Code: lexicon design, DID resolution, XRPC, DAG-CBOR, MST/repo inspection, OAuth flows, record parsing. Use when the user is working with Bluesky, at:// URIs, com.atproto.*, app.bsky.*, or any AT Protocol concept.

7 skills

Taiwan e-invoice, payment gateway and logistics API integration skills

3 skills

Professional coding assistant principles inspired by Uncle Bob

1 skill

I realized I let the agent start coding before I was sure it was working on the right thing, so I built this. Now it doesn't get to write code before there's a reason. The agent asks who this is for. It asks what you're assuming, and what would show you wrong. The rules run as hooks, so once you have started it in a repo the build stays shut until the answers are there. Purpose, strategy, opportunities, then delivery and market feedback. It adds skills and hooks, keeps its own state in a .claude/ folder, and won't edit the files already in your repo unless you ask it to.

63 skills · hooks

Write, check and run FratmScript (JavaScript with Neapolitan keywords)

1 skill · 1 MCP server

Build web3 applications, scripts, CLIs, bots, and mobile/desktop clients that read blockchain data through the Blockscout PRO API — a single HTTP API spanning 100+ EVM chains.

1 skill