超级榜单

An agentic skills framework & software development methodology that works: planning, TDD, debugging, and collaboration workflows.

Harness-native ECC workflows for Codex: shared skills, production-ready MCP configs, and selective-install-aligned conventions for TDD, security scanning, code review, and autonomous development.

Behavioral guidelines to reduce common LLM coding mistakes, derived from Andrej Karpathy's observations on LLM coding pitfalls

n8n Claude Code plugin — shared skills, commands, and agents for n8n development

Lazy senior dev mode. Forces the simplest, shortest solution that actually works: YAGNI, stdlib first, no unrequested abstractions.

Claude Agent SDK Development Plugin

AGENTS.md as project instructions, by one option. Under claude-md-or-agents-md a project with no instruction files of its own gets its AGENTS.md files instead: a prompt.context hook asks $.fs.ancestors for every AGENTS.m

Migrate your code and prompts from Sonnet 4.x and Opus 4.1 to Opus 4.5.

Automated code review for pull requests using multiple specialized agents with confidence-based scoring

Streamline your git workflow with simple commands for committing, pushing, and creating pull requests

The diff pane as a plugin: /diff opens the session's uncommitted changes beside the transcript, file by file with their hunks, refreshed as Claude edits and runs commands; the first edit opens it where the terminal is wi

Adds educational insights about implementation choices and codebase patterns (mimics the deprecated Explanatory output style)

Comprehensive feature development workflow with specialized agents for codebase exploration, architecture design, and quality review

Frontend design skill for UI/UX implementation

Easily create hooks to prevent unwanted behaviors by analyzing conversation patterns

Interactive learning mode that requests meaningful code contributions at decision points (mimics the unshipped Learning output style)

Comprehensive PR review agents specializing in comments, tests, error handling, type design, code quality, and code simplification

Implementation of the Ralph Wiggum technique - continuous self-referential AI loops for interactive iterative development. Run Claude in a while-true loop with the same prompt until task completion.

Security default for organizations: seated outermost, it keeps the organization's classic hooks, prompt content, settings and tool policy out of reach of the plugins a person installs, and adds no policy of its own; one

Security review for Claude-generated code. Pattern-based warnings on edits, LLM-powered diff review on Stop, and an agentic commit reviewer that catches injection, XSS, SSRF, hardcoded secrets, and 25+ other vulnerabilit