Claude
Tools

Sound like you, not AI — feed it one sample of your writing and get a Claude Code skill that rewrites any text in your own voice. Korean & English.

Resume Radar: a Claude skill that audits & optimizes your resume against LLM resume-screening bots (reverse-engineered from HackerRank hiring-agent). Surfaces the open-source signal the screener misses. Honest signals only.

Turn a one-line idea into a production-grade, copy-paste-ready AI image prompt for posters, landing and UI mockups, ads, game art, and logos. A Claude Code skill optimized for gpt-image-2. MIT.

Test suites + deterministic Python for your agent skills' decision logic. Adversarial persona reviewers write the tests; the generated code must keep passing them — zero LLM calls at inference. Try: uvx temper-skills audit <skill.md>

Claude skill: compresses heavy AI-coding-agent prompts into lean, TOON-encoded, token-efficient specs

The code idlepay runs on your machine — editor extension + Claude Code status line. No network in the hook, verifiable builds.

The missing brain for AI coding agents — verification gates written before the code, Reflexion-style memory that learns from every failure, and self-correction loops with real anchors. One command install for Claude Code; copy-paste prompts for any AI.

VS Code extension — plays a sound and shows an OS notification the moment your AI agent needs your attention

Switch Claude Code between Anthropic, DeepSeek, GLM, Kimi, Qwen & MiniMax; Manage your skills conveniently

A set of Claude Code Skills modeled after distinct human thinking patterns (brainstorm, thinking, idea, explore, create, guide, study, try).

A desk companion for Claude Code: the orange Clawd mascot on a Cheap Yellow Display (ESP32) that mirrors your live Claude Code activity and usage stats — driven entirely by Claude Code hooks over Bluetooth LE, with no WiFi, no network setup, and no always-on PC process

Global Claude Code setup: opinionated skills, the instructions they follow, and the hooks that enforce them

CLI and MCP server that take an iOS app all the way to App Store review over the App Store Connect API — readiness report, idempotent pipeline, metadata, screenshots, pricing, age rating, subscriptions, submission. Zero dependencies, no install step.

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

⌘ Zero-dependency local dashboard for Claude Code — commands, skills, agents, plugins, workflows, sessions & a ccusage-accurate usage dashboard

MCP & Claude Code security scanner — threat-models plugins, MCP servers, hooks, skills & connectors with an LLM before you trust them. Catches prompt injection, tool poisoning & credential exfiltration.

Claude Code plugin marketplace. audit: a manifest-driven audit/fix pipeline with enforced plan-first and TDD gates — deterministic hooks, not prompt suggestions — token spend attributed to phases and tasks, and a shareable HTML report. Zero dependencies.

Claude Code skills that analyse short-form videos (TikTok, Reels, Shorts) against a binary checklist and build a searchable creative asset library.

한국 세법·법령 통합 검색 MCP 서버 — 국세청·지방세·법제처의 심판례·판례·조문·부칙을 Claude에서 도구 17개로 (Korean tax & law MCP server for Claude)

Self-learning loop for Claude Code — corrections and failures become skills, behind a human gate. MCP + hooks, Windows-native, zero background LLM calls.

Shareable taste for AI coding — recipes injected into Claude Code prompts

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

Skills for Claude Code and Codex: durable goal loops, parallel review, research, investigation and implementation, and research grounded in your own knowledge base

Universal SEO skill for Claude Code. 25 sub-skills + 18 sub-agents covering technical SEO, E-E-A-T, schema, GEO/AEO, backlinks, local SEO, maps intelligence, semantic clustering, e-commerce SEO, international SEO, Google APIs, and PDF/Excel reporting. Optional DataForSEO, Firecrawl, and Banana extensions.