Reading
A modular plugin marketplace designed specifically for Claude Code, offering skills, specialized agents, and domain knowledge bases covering multiple areas such as Git operations, code review, security auditing, and TYPO3 development.
Section 01
A modular plugin marketplace designed specifically for Claude Code, offering skills, specialized agents, and domain knowledge bases covering multiple areas such as Git operations, code review, security auditing, and TYPO3 development.
Section 02
AgentKit is a plugin marketplace designed specifically for Claude Code, consisting of multiple independent plugins—each providing specific skills, agents, or knowledge bases. Unlike single-function AI tools, AgentKit uses a modular design, allowing developers to install and use only what they need, avoiding feature redundancy. Currently, AgentKit includes 9 core plugins covering multiple areas from Git operations to security auditing, and from code refactoring to TYPO3 development.
Section 03
| Plugin | Number of Skills | Number of Agents | Description |
|---|---|---|---|
| ak-git | 1 | 2 | Smart commits, change analysis, conflict resolution |
| ak-improve | — | 2 | Code refactoring and performance optimization agents |
| ak-knowledge | 4 | 1 | Solution documentation, knowledge maintenance, AGENTS.md tool |
| ak-meta | 3 | — | Ideation, changelog generation, AI context handoff |
| ak-notifications | — | — | macOS sound and banner notifications |
| ak-react | 2 | — | React and Next.js best practices, performance optimization, code scanning |
| ak-review | 2 | — | CodeRabbit review, finalization workflow, verification hooks |
| ak-security | 3 | — | OWASP security guidelines, LLM security, Semgrep static analysis |
| ak-typo3 | 5 | 5 | TYPO3 v13.4 content blocks, SitePackage, extensions |
This modular design allows developers to flexibly combine plugins based on project needs and install only the required features.
Section 04
This is one of the most frequently used plugins, providing smart Git workflow assistance.
Skills:
/ak-git:operations — Smart commits, PR/MR creation, conflict resolution, change reviewAgents:
Typical usage: /ak-git:operations --ship can complete commit, push, and PR creation in one click.
Section 05
Focused on improving code quality, providing refactoring and performance optimization capabilities.
Agents:
These two agents can help developers improve code quality without introducing regressions.
Section 06
Captures solved problems into structured, searchable solution documents and keeps them updated.
Skills:
/ak-knowledge:agents-md — Convert CLAUDE.md files to AGENTS.md and create symbolic links/ak-knowledge:agents-md-improver — Audit and improve AGENTS.md files, provide quality scores/ak-knowledge:document — Create documents for recently solved problems for team knowledge base use/ak-knowledge:refresh — Review and maintain solution documents based on the current codebaseAgents:
This plugin is particularly suitable for team knowledge management, avoiding repeated solving of the same problems.
Section 07
Handles project-level meta tasks such as ideation, changelog, and context handoff.
Skills:
/ak-meta:discover — Generate improvement ideas/ak-meta:changelog — Generate changelogs/ak-meta:handoff — AI context handoffThese skills help teams better manage project evolution and version releases.
Section 08
Provides a structured code review process.
Skills:
/ak-review:coderabbit — CodeRabbit-style code review/ak-review:finalize — Task completion workflowThese skills ensure code is fully reviewed before merging.
Keep going with more reads from the same topic.
Splinter is a minimalist, high-performance key-value (KV) and vector storage system enabling zero-latency inter-process communication via shared memory and atomic operations. With only 766 lines of core code, it supports millions of operations per second and 768-dimensional vector storage, offering a new architectural approach for local LLM inference and data-intensive applications.
LiteMind is a Python framework that provides developers with a unified API to integrate mainstream LLM providers such as OpenAI, Anthropic, Google Gemini, and Ollama. It supports multimodal input/output, tool calling, RAG enhancement, and agent construction.
OmniRoute is an open-source AI gateway that integrates over 67 large model providers through a single OpenAI-compatible endpoint. It offers intelligent routing, load balancing, automatic degradation, and quota management, helping developers get the most available AI services at the lowest cost.
This article introduces an open-source multimodal RAG framework based on Google Gemini Embedding 2, which can uniformly handle embedding and retrieval of four media types: text, images, videos, and audio. Combined with Supabase pgvector vector database and OpenRouter large language models, it provides a complete production-level retrieval-augmented generation pipeline.