Claude
Tools

Claude Code skill + knowledge base for authoring X-Ways Forensics X-Tensions (unofficial community project).

Generate a structured system design document from requirements and context.

Lean agentic dev loop for Claude Code: prime → lean-doc → orchestrate → repeat. Eleven standalone skills + an opt-in /flow conductor + a /council decision aid. No hooks, agent-free core — drop in and adapt.

Minimal, type-led HTML/CSS/React design system for slide decks and data-driven presentations. 极简演示文稿设计系统，含7种幻灯片模板与React组件。

Command Autopilot — use 100% of Claude Code while memorizing zero commands. Silent automation, right-moment suggestions with benefits, self-evolving to your habits.

Session memory & orchestration for Claude Code: one index of all your sessions, three modes — finish / handoff / spawn

UX writing skill for Claude. Humanizes AI copy, fixes microcopy, kills em dashes. Writing, not fighting.

Package manager for MCP servers, Agent Skills (SKILL.md), and Claude Code commands, hooks, subagents, and output styles. Installs into Claude Code, Cursor, Codex, Gemini CLI, Copilot, and Cline.

Watch your AI work — replay any Claude Code session like a movie. Prompts, reasoning, tool calls, file edits & context growth on a scrubbable timeline. Zero deps, 100% local.

Fusion — a Claude Code skill: convene a panel of frontier models (Opus 4.8 + GPT-5.5 xhigh), judged into one grounded answer. Deep Thought, with receipts.

An open-source operating system for Claude Code - persistent Obsidian-vault memory, an /open + /close session rhythm, a subagent Pantheon, context hooks, and background daemons. Markdown + shell, no database, no build step. MIT.

Make Claude Opus code like Fable 5: Fable's coding habits as a Claude Code plugin, with one habit (tests never touch live data) enforced by a hook.

A Claude skill making the model an expert in Apple's container CLI — run Linux containers & persistent Linux machines on Apple silicon. Benchmarked: 100% vs 68% vs plain Claude.

A WebSocket server that impersonates an OpenClaw (clawdbot-gateway) gateway so a Rabbit R1 can drive Claude Code / Codex / any agent instead of OpenClaw.

Loop engineering for Claude Code — a skill that turns an idea into a production-grade, memory-backed agent loop. Classify, scope, derive state, emit a /loop-ready prompt. Stop prompting; design the loop.

Personal notification hub for AI coding agents — forwards OpenCode, Claude Code, and Codex hook events as short notifications via Bark/ntfy to your phone or watch.

Portable Claude skill to build beautiful, self-contained HTML presentations: author slides and import brand themes (PowerPoint, image, or description).

One-prompt 3D brain-region figures & rotating glow animations from 200+ BrainGlobe atlases (any species), rendered headless in Blender. A low-token Claude Code skill.

Taplio LinkedIn Cloud Skills: 17 free Claude Skills to write, plan, and grow your LinkedIn presence. Post writing, hooks, carousels, strategy, content calendars, and analytics, powered by the Taplio MCP.

One diff, one thesis — a Claude Code skill that breaks a large change into a stack of small, single-thesis, refactor-first PRs (or diffs/CLs), each buildable and testable on its own.

🏗️ B端产品经理超级工作台 | 11阶段·50+框架·30+交付物 | PRD·SaaS·RBAC·AI产品·RAG·Agent | 多租户·审批流·商业化·PLG | WuKong/Claude/OpenClaw Skill

A Claude Code skill that writes, fixes, and validates OpenTelemetry Collector configs — processor order, core-vs-contrib, pull-vs-push exporters, the works.

A Claude Code skill that front-loads design tokens and rules so AI can only produce on-brand UI, then verifies the output.

💼 The portable memory layer for AI coding tools — one shared brain that follows you across Claude Code, Cursor, Windsurf & Conductor. Install once, never re-explain your project again.