Claude
Tools

Sound notification hooks for Claude Code (Stop, PermissionRequest, AskUserQuestion)

Hooks, skills, agents, and MCPs that make Claude Code more autonomous and reflex-driven. Built for AI-first solo founders.

Agent skills for learning — Socratic tutoring with persistent learner state and spaced review. Ships the teach skill. Named after Richard Hamming.

Claude Code skill that scaffolds 8 anchor files + optional hooks for persistent project memory across sessions

Team collaboration protocol skill for OPC collectives — handoff/checkpoint flow, CURRENT/NEXT/RISKS structure, hard constraints for AI agents (Claude Code, Codex CLI, Cursor, Cline, Continue, Gemini CLI). Follows Anthropic Agent Skills open specification.

Claude Code skill that generates and audits ai.txt, robots.txt (AI-crawler rules), llms.txt, and TDM opt-out files for websites.

Opinionated templates for running Claude Code autonomously on enterprise projects: a CLAUDE.md constitution, a universal Technical Requirements template, and 7 Claude Code skills (architecture, product, code review, OWASP, QA, spec validation, UI/UX) with deterministic PASS/WARNING/BLOCKER checklists. With a filled-in fintech-api example.

Evidence-based audit + cleanup for Claude Code installations. Decide what to keep, delete, or refresh across plugins, skills, and rules — grounded in your actual session history.

Measure worst-case skill-context exposure in your Claude Code setup.

Agent skill: read & search IMAP mailboxes from the CLI via myl. For OpenClaw, Claude Code, AgentSkills. Gmail / Yandex / Mail.ru / autodiscovery.

Real-world data science methodology as a Claude Code skill — process, not algorithms, is the work. By Data Science With Dennis.

One portable bundle bringing 7 AI coding CLIs to feature-parity. Universal rules, hooks, MCPs, skills, and slash commands for Claude Code · Codex · Goose · Gemini · Kimi · OpenCode · Claw Code.

Personal Claude Code configuration: CLAUDE.md, custom skills, agents, hooks, and utility scripts.

🎭 Talk to Claude in 100% emoji. A stylized communication mode for Claude Code.

Diagnostic playbook for Midnight Network backend ops. Wallet sync, deploy hangs, three-address confusion, vk mismatches. Works in Claude Code, Codex, Cursor.

Agent Personas for Claude — 10 MCP tools, 8 personas, 3 workflows. Zero API cost. Free tier available.

네이버증권 비공식 read-only 웹 API Agent Skill: stock.naver.com 국내 주식·ETF·지수·뉴스·리서치 데이터 조회

A Claude Code skill for tiered model orchestration across configurable Advisor/Planner/Executor layers

A complete memory loop for Claude — snapshot, recall, and prune project context across sessions

Production-grade Claude Code plugin: control your personal Telegram via MTProto (Telethon). 120 typed MCP-tools, 9 resources, 7 prompts, 6 skills, 4-layer PreToolUse safety net, channel-push & permission relay

Gradle output filter for AI coding agents — strips noise, keeps errors/warnings/status, with Claude Code hook integration

Claude Code skill + rule + hook that cleans rough/voice input into a production-ready prompt before running

A hook-based router for Claude Code: classifies every prompt, dispatches to the right framework, and enforces runtime guardrails.

把飞书豆/飞书妙记的录音转写,提炼成 8 节"信息资产"结构化笔记。会议/访谈/课程/播客通用。By 司徒K.