Claude
Tools

Behavioural protocol package for Claude Code enforcing quality and transparency

An institutional-grade working standard for Claude. Forces truth-first reporting, evidence-based decisions, and no guessing.

⚡ Persistent Memory OS for Claude Code — Auto-indexes codebases, records session decisions, and injects relevant context automatically. Zero-config VS Code extension + React dashboard.

Universal toolkit for building, discovering, reviewing, testing, and securing Claude skills. 7 scripts, 10 reference docs, 6 workflows. Includes quality scoring, auto-testing, prompt injection detection, quarantine-based install, and conflict detection.

Live standup automation. Cadence joins the call, follows the conversation, and syncs your tools as decisions are made.

An interactive course based on Anthropic's Complete Guide to Building Skills for Claude (April 2026). 10 lessons, 9 hands-on exercises, capstone that outputs a real SKILL.md.

Bootstrap the 45ck agent stack with shared skills, Claude and Codex agents, project tooling, and embedded packs

Claude Code skills for generating images via ComfyUI, plus a Windows setup skill. Independent, community-built; not affiliated with Anthropic or Comfy Org.

Claude-Skill für Lehrkräfte. Erzeugt fertige AIS.chat-Konfigurationen (Lernszenarien, Dialogpartner, Assistenten) mit eingebauten Knappheitsbausteinen gegen schwätzige KI-Antworten.

Pro-grade lifecycle for creating, testing, versioning, and iterating on Claude Code skills — fuses Anthropic's skill-creator, lovstudio's pro-skills, and superpowers' writing-skills.

一个半理性、半情绪、略带文学感的恋爱关系分析 AI Skill。不是算命，不是结论机——它让一段模糊的关系，变得能被看一看。

Fast ≠ efficient. A Claude Code skill + pre-push hook that makes AI coding agents check the math before `git push` — so they stop trading the user's two hours for their own twenty seconds.

Regression-safe OSS contribution pipeline as a Claude Code skill — dedupe, reproduce, attest, throttle, follow-up. Encodes 10 rules so AI-drafted PRs land instead of getting filed as noise.

OpenRelik worker that runs Claude (via the Claude Agent SDK) with a user-selected cybersecurity skill from mukul975/Anthropic-Cybersecurity-Skills and the uploaded workflow files as the target artifacts.

Personal Tools for tracking Anthropic Courses and Claude Cookbooks.

Claude Pro Max对比、成本分析、ROI、费用对比，2026年国内用户完整指南：Claude在国内如何使用？Claude怎么充值？怎么使用Claude不会被封号？

AI-powered video extraction platform - CrewAI agents, MCP/SSE tools, Claude (Anthropic), AWS Bedrock, Angular, Node.js, Python, FFmpeg, Azure Container Apps

An enterprise-grade execution protocol for Claude Code agents running in autonomous mode. Enforces sacred file boundaries, 7 mandatory safety checks, structured emergency exits, and a 6-phase auditable workflow — making unattended AI execution safe and reproducible.

Self validating LangGraph agent pipeline: every agent output passes through a checkpoint node that scores it and routes to pass, retry with feedback, or halt. Includes rule based, LLM as judge, and semantic validators plus MCP-style fact-check and schema-check tools.

Persistent project assistant for Claude Code. Bootstrap new projects or adopt existing ones via gap analysis. Quiet background hooks maintain wiki, pick the right model per task, and surface past decisions. Built for vibe-coders.

Embedded visual workspace for Claude Code — Excalidraw, tldraw, and Markdown with MCP tools and inline PNG previews

Claude Code skill: enrich Linear backlog tickets with parallel research agents before implementation

Turn any video link into a polished AI article. Markdown + images, multi-LLM.

HTML → PC + Mobile side-by-side screenshot composer. A Claude Code skill that renders local HTML at desktop and mobile viewports, then composites the two into one PNG/JPEG. Powered by Playwright + auto local HTTP server. Height-normalized panels, 14 background presets, custom gradients, full-page mode, folder batch.