Claude
Tools

A Claude Code skill that runs a disciplined, evidence-grounded UI/UX redesign — screen by screen.

Run one request through several Claude Code skills in parallel isolated subagents, then merge or judge the best answer.

Agent skill that removes documented AI-writing patterns — two modes, register awareness, voice calibration, and a deterministic linter. Works in Claude Code, Cursor, Copilot, Codex, or any harness that reads SKILL.md

One command sets up Claude Code (and any AI coding agent) on a Laravel project: engineering rules, a quality gate (PHPStan · Pint · Pest), skills, git hooks, and stack-aware frontend tooling.

Ship an iOS app to App Store review end-to-end via the App Store Connect API — an agent skill. ~90% automated, config-driven, SOLID clean-architecture.

Re-inject the working state Claude Code loses when it compacts context — a local, zero-dependency SessionStart hook

Claude Code runs long agentic sessions in your terminal or VS Code. You switch to the browser, and… did it finish? Is it stuck waiting for you to press Allow? ClauCat is a tiny always-on-top bubble in the corner of your screen — above Chrome, Slack, everything, on every Space and fullscreen app — that answers those questions without you ever tabbin

A Claude Code skill for discovering your unknowns (unknown unknowns / unknown knowns) before, during, and after implementation.

PM-friendly, tool-agnostic agent skills for Claude Code, Codex, and other coding agents

Distill any public figure's thinking into a structured, sourced profile — then apply it as a lens on your real decisions. 9 profiles included (Buffett, Jobs, Voss, Feynman, Altman...). Works with Claude, ChatGPT, Open WebUI, and any AI.

以 @helloianneo 老师的 ian-xiaohei-illustrations skill 为灵感，根据其底层项目逻辑（构图纪律+IP承担核心动作+留白+QA清单）复用改造，做出以自己原创 Q版女孩为固定主人公的中文文章正文配图 skill。

Token governance for Claude Code: the top model directs, execution goes to the cheapest adequate means. Routing kernel, hook-enforced pre-budget, telemetry, statusline with plan quotas.

Keep AI coding sessions under a context budget with automatic cross-session handoffs. Hooks for Cursor and Claude Code.

Run Claude Code against any OpenAI-compatible endpoint (official OpenAI, Azure, or gateways). Anthropic ↔ OpenAI translation with streaming, tools, prompt caching, and a built-in dashboard. Zero dependencies.

Claude Code skill that clones Fable 5's reasoning habits — the playbook Fable wrote about itself. A/B validated: 20/20 convergence, blind-judge parity. One-line install.

Capture a live webpage's design system, motion, and interaction state machines, then reconstruct it as verified React — with per-node pixel verification and an honest skip-reason taxonomy.

claude fable 5 anthropic mythos-class model large language model artificial intelligence claude code free subscription window zenmux open source agent 1m context window adaptive thinking autonomous coding bug patching refactoring api console setup guide tutorial benchmarks safeguards developer tool command line interface

Audit your Claude setup for drift: redundant skills, dead plugins, bloated CLAUDE.md, session-start pile-up.

Claude Code skill + zero-dependency Node toolkit for running Apple Search Ads with a competitor-conquesting strategy (research TikTok/IG-marketed rivals, build conquest keywords, create campaigns, audit daily).

Make Claude Code CLI sessions appear in the Claude Desktop Code sidebar — auto-sync hook + one-time backfill

A local, read-only web dashboard for your Claude Code session logs — track API cost, token usage by model, tool & skill usage, and activity patterns, all on your machine.

Claude Code plugin — a behavioral charter, on-demand checklists, and enforcement hooks that make Opus act with Fable 5's discipline: autonomy, verified-done, honest reporting, scope control.

Claude Code & Codex skills for AI reports, decks and client sharing: publish agent-made research as live tracked web reports, recurring client reports, view-tracked proposals and slide decks via the ReportRoom MCP. Beautiful by default, analytics back to the agent.

Native macOS SwiftUI dashboard for inspecting your ~/.claude config — skills, agents, settings, hooks, MCP servers, slash commands.