claude-code

24 self-contained Claude Code skills, each distilled from one real engineering failure, with sanitised case studies and pre-flight checklists.

Web directory that indexes Claude Code plugin marketplaces themselves, so you can discover sources rather than individual plugins.

Visual whiteboard that lets you annotate screenshots and feed the marked-up feedback straight back into the coding agent.

Open-sourced skill set behind ClaudeKit covering research, planning, shipping and repo hygiene for Claude Code projects.

The largest curated index of Claude Code resources: guides, skills, statuslines, hooks, clients, security tools and CLAUDE.md files.

Lightweight meta-prompting system for Claude Code that structures work into planning and execution passes without heavy scaffolding.

MCP server and CLI that injects current, version-specific library documentation and code examples into an agent's prompt.

Configuration framework adding thirty slash commands, twenty specialist agents, seven behavioural modes and eight MCP integrations to Claude Code.

Claude Code plugin that converts raw terminal output and logs into styled, readable HTML explanations.

Hook that intercepts destructive shell commands before an autonomous agent executes them.

Agent workflow that drives Claude Code or Codex to build Godot, Bevy and Babylon.js games, running the engine and iterating on screenshots.

Community-maintained list of plugins extending Claude Code with commands, agents, hooks and MCP servers.

Planning layer that lets several coding agents share specs, tasks and decision history inside one workspace before they write code.

Production-oriented Claude Code skill marketplace repo with installable skills for day-to-day development workflows.

Template teaching the PRP workflow — global rules, feature specs, example patterns and /generate-prp and /execute-prp commands.

Anthropic's curated directory of vetted Claude Code plugins, used as the default marketplace source.

Browser automation harness that lets a coding agent open, drive and visually verify the app it just wrote.

Statusline that streams live World Cup football scores into your Claude Code terminal.

Regularly updated extractions of Anthropic, OpenAI, Google and xAI system prompts including Claude Code and Codex.

Slash-command system that interrogates your codebase, asks two rounds of yes/no questions, then writes a concrete requirements document.

Project template that adds pre-commit hooks, CI, linting, type checks, file-length limits and test-drift inventories to LLM-assisted work.

Curated list of Claude Code slash commands, subagents, MCP servers and hooks packaged as installable plugins.

Sprawling toolkit bundling agents, skills, commands, plugins, hooks, rules, templates and MCP configs in one repo.

Battle-tested Claude Code skill library covering brainstorming, TDD, debugging and code review, installed as a plugin marketplace.

Statusline showing live rate-limit consumption, token spend and cost so you can see budget burn in real time.

Experimental staging repo where new agent-skill techniques get prototyped in public before graduating into the main superpowers library.

Claude Code skill that writes and runs Playwright automation on demand instead of exposing a fixed MCP tool surface.

Highly customisable Claude Code statusline with powerline rendering, themes and configurable widgets.

All parts of the Claude Code system prompt, versioned and updated on each release for diffing.

Reference project demonstrating every Claude Code hook event with runnable example implementations and explanations.

Web and mobile progressive web app for driving Claude Code sessions remotely from a phone or browser.

Reference library of hook-based skill activation, modular skills, ten specialist agents and documentation patterns that survive context resets.

Starter kit of commands for priming context, reviewing work, syncing docs and blocking secrets across Claude Code sessions.

Converts Claude Code session transcripts into an interactive HTML replay you can scrub and share.

Focused collection of Claude Code plugins bundling specialised agents, skills and slash commands for development workflows.

Statusline that reacts to what the agent is doing with kaomoji expressions and mood states.

Curated collection of Claude Code hooks for event-driven automation across the agent lifecycle.

Walkthrough of the Ralph technique: running a coding agent in a repeating loop against a spec until every item is finished.

Plugin that turns CSS selectors into generated visual documentation of a component's states and variants.

Community gallery of Claude Code status lines where every card preview is rendered from the real script before you copy it.

Browsable catalogue of Claude Code plugins and marketplace collections with install commands and categorisation.

Cozy pixel-art game teaching the whole Rust Book across 25 islands and 187 levels, compiled with your own rustc and tutored by Ferris via Claude Code.

Claude Code plugin pane plus a local Codex dashboard showing the agent and subagent tree, live status, token use and the current request's stage-grouped task flow.

Mac app (Windows preview) where you hit a hotkey, talk, click and draw over your screen or a plugged-in iPhone, then paste the keyframes and transcript into your coding agent.

Handwriting font built by Claude Code from 120 pages of college notes, with three rotating variants per letter, two weights and a documented photo-to-font pipeline.

Agent skill for launch films and brand stings that animates with eases measured from pro motion work, then renders locally and grades itself with scripted gates.

Catalogue of 24 named motion graphics effects with the exact term to ask an AI for, scene recipes, demo videos and a Claude Code skill.

Turns Claude Code, Codex and Mistral Vibe sessions into a live animated team call with characters, local voices, shared screens, sub-agent trees and replay.

MCP server plus Figma plugin that lets Claude Code, Cursor and Codex read and edit the open Figma Desktop file as XML with CSS, tokens and components.

Claude Code skill plus runtime that takes a live UI component apart into paint layers, states and tokens, measured from the real DOM rather than redrawn.

Interface design skill for AI agents that explores several distinct visual directions side by side, then refines the chosen one against real screenshots.

Agent skill that turns a short JSON spec into animated, explorable diagrams in one HTML file, exportable as SVG, PNG, GIF or MP4.

Claude Code plugin that shows images and plays videos inside the Ghostty terminal: design options side by side, Playwright test recordings, before and after QA.

Claude Code mod that picks reasoning effort per prompt with a Haiku judge, and adds a bar showing context fill, prompt cache warmth and one-click compaction.

Agent skill that turns hard questions into a readable one-page offline HTML explainer, rendered by a bundled CLI from a short Markdown draft.

Claude Code plugin with writing rules that cut reply length roughly in half and strip mannered prose from replies, docs, commits and subagents.

Native macOS video editor on AVFoundation with a Claude Code or Codex terminal docked beside the timeline, fully drivable through a CLI or MCP.

macOS CLI plus Claude Code and Codex skill that lets agents draw big click-through arrows, boxes and text over any window, then vanish.

A free public tracker for Claude Code usage reset timing and status.

Marketplace of hook-based Claude Code plugins: context bar, usage meter, review watcher, Markdown preview, rm -rf blast radius, Spotify now-playing and more.

MCP server plus Figma plugin that turns Claude Design output or HTML into editable Figma layers with Auto Layout and your components, and frames back into React.

Skills, a CLI and a fal MCP server that let coding agents mod PC games: detect the engine, read the code, build the mod, generate assets and test it in-game.

Saves decisions, rules and failed approaches from Claude Code chats to a JEVMEM.md in your repo, recalls them next session, and checks commands against saved rules.

Agent skill that opens your running local app as live iframe screens on a design canvas, so you can compare routes and push visual edits back through your coding agent.

Claude Code skill that clones a website from a URL: Playwright captures three viewports, extracts fonts, tokens and keyframes, rebuilds section by section, then grades the clone by pixel diff.

Claude Code plugin of rules, hooks and skills that makes the agent answer ten questions about a change against real code, scope its work, and prove it before claiming done.

Claude Code plugin that opens a Doom deathmatch pane beside the transcript while Claude works, with everyone else waiting on Claude, and hands you back when it finishes.

Local-first desktop app that tracks Claude Code and Codex tokens, cache hits, models, and cost across machines via a self-hosted hub.

Claude Code skills that turn a Lichess game plus think-aloud audio into Stockfish-checked annotated PGN, HTML board, and narrated video.

Menu-bar and TUI app that switches every local coding agent's model through one local gateway and shared catalog.

Multi-agent orchestrator that turns one goal into an ordered graph of coding-agent tasks with per-task runners and verified markers.

Research workspace where chat, files, PDFs, and notebooks share one dock, and the agent can spawn custom panes when needed.

Claude Code status line that shows session context size, next-turn cost, and rate-limit headroom before you type.

Open-source extractor that pulls chat histories from Claude Code, Cursor, Windsurf, Aider, Cline, and related coding assistants.

Local desktop app that detects, configures, and runs coding-agent CLIs like Claude Code, Codex, Gemini, and OpenCode in one workspace.

Agent skill that turns an idea into an explorAble Three.js or Blender scene, with hundreds of recipes and runnable studies.

Native macOS workspace that keeps one local knowledge graph shared across Claude Code, Codex, OpenCode, and Cursor.

Agentic loop where coding agents draw in p5.js, then refine via adversarial visual review — skills for Claude Code and Codex.

Claude Code org chart of 16 independently installable departments and 172 skills, addressed as department:skill so names never collide.

Local macOS voice loop for Claude Code and Codex: say hey Bol, dictate into the cursor, send it, and optionally hear talk-back summaries.

Pair of agent skills that build a slide deck from a repository, citing exact file line ranges and hashes so a script can flag slides that drifted.

Claude Code skill for long-form generative art: hash-seeded PRNGs, trait and rarity tables, plus scripts that render contact sheets and check determinism.

Claude Code skill that builds scroll-driven sites using eight mutually exclusive page grammars, then screenshots its own scroll to grade contrast and dead scroll.

Claude Code skill pack that rewrites agent output as plain-language reports, straight yes/no verdicts on completion, and numbered steps you can follow.

Claude Code skill that reads your local session logs to explain where tokens went, why you hit a limit, and what to change.

Paste a public GitHub repo of SKILL.md files and get a stable streamable-HTTP MCP URL for Claude Code, Cursor or Codex.

Local read-only dashboard for token usage and reported cost across OpenCode, Claude Code, Codex and Cursor sessions, with per-call cache-miss drilldown.

macOS app that floats a strip of eight virtual LEDs beside the Dock, signalling whether coding agents are working, waiting, finished or broken.

Maintained index of seventy-five-plus high-quality Claude Code repositories with descriptions and categories.

Forty-six-plus documented Claude Code techniques plus status-line scripts, conversation utilities and a bundled developer-experience plugin.