Productivity

Use Gemini from Claude Code to review code or delegate tasks.

Claude Code plugin for Graphite stacked PRs — debug stack CI/review issues, aggregate PR comments, resolve restack conflicts, and manage stack workflows

Plugin de Claude Code: 18 agentes especializados, 60 skills, 25 comandos, 13 hooks, memoria persistente, Memory UI local, quality gates, evidence guard, continuidad operativa y modo autopilot.

Your agents have things to say. Now they have a voice to say them with.

Turn a one-line idea into a branch with tested, reviewed, committed code. The brainstorm-to-commit pipeline for Claude Code.

Claude Code sessions are stateless. Continuum fixes that. 7 skills + 5 zero-cost hooks for crash recovery, session resume, and cognitive checkpoints.

Empower agents with professional capabilities in specific fields (such as full-stack development, complex logic planning, multimedia processing, etc.) through modular Skills definitions, allowing agents to solve complex problems systematically like human experts.

Multi-agent marketplace plugin for Claude Code — delegate coding tasks, reviews, and investigations to Cursor Agent and OpenAI Codex from within Claude Code CLI.

Lightweight multi-agent development workflow plugin for Claude Code

DAG-based Lossless Context Management for Claude Code. Every message preserved, summaries cascade as a DAG, patterns extracted via Lossless Dream — full recall and reflection across sessions.

A skills-driven Agentic Context Engineering workflow for Claude Code.

Claude Code plugin — 18 custom skills for thinking, deciding, and building smarter

A Claude Code plugin for long-horizon TDD coding workflows — persists state via a structured state machine, enforces TDD rhythm, and gates each phase with mandatory human confirmation and automated lint checks. 面向长任务的 Claude Code 插件，通过结构化状态机、TDD 节奏与强制门禁，保证 AI 编码过程的可控性与可追溯性。

Makes Agents produce staff-engineer-quality code

Claude Code plugin with productivity slash commands — Research, dev, and docs

Agent Capability Standard is an open specification for composable AI agent capabilities. It defines 36 atomic capabilities across 9 cognitive layers, a type-safe workflow DSL, and grounded world modeling with trust-aware conflict resolution. Built on the Grounded Agency philosophy, it makes agent reliability structural—not optional.

Entity-anchored, vector-searchable, salience-weighted graph memory MCP server for Claude Code. Local-first, privacy-first, zero-cloud.

Learn practical techniques to enhance your AI-assisted development workflow with Claude Code.

Runtime guardrails for Claude Code. Auto-approve what's safe, gate what's risky, block what's dangerous. Dual enforcement, full audit trail. MIT.

Put up to 8 AI models on every coding task — blind spots surface before you ship. Claude Code plugin.

Token-efficient Claude Code workspace with parallel agents and persistent memory. Research → Plan → Implement → Validate workflow.

Claude Code plugins: your extended memory + your thinking partner. Information theory & cognitive science in pure Python stdlib. Zero setup.

Daemon-based hooks system for Claude Code with lazy startup, auto-shutdown, and project-level handler extensibility

This repository contains a collection of **Agent Skills**—standardized, specialized sets of instructions and workflows designed to enhance AI agents (like Claude Code, Codex, Kimi CLI, and Gemini CLI, etc.) with domain-specific expertise.