Skills, subagents, slash commands, hooks, settings, plugin bundles and MCP servers that install into Claude Code. 390,276 indexed, measured the same four ways as everything else here.
Write to (or read) the user's BonsAI board — the spatial idea canvas in the BonsAI macOS app. Use when the user asks to put / drop / add / send something to their BonsAI board, capture an idea or note on the board, sketch a diagram or architecture onto the canvas, evolve an idea already on the board, or read what's…
Persuasive GPT image deck-planning skill. Uses extracted DESIGN.md, user files, and the user's goal to decide slide ordering, page count, evidence placement, and narrative flow in JSON.
Skill "release" from mahmoud/lithoxyl, covering release lithoxyl, pre-flight checks, release steps, 1. determine the release version and 2. update version for release.
Run adversarial bug hunting on your codebase. Uses 3 isolated agents (Hunter, Skeptic, Referee) to find and verify real bugs with high fidelity. Invoke with /bug-hunt, /bug-hunt [path], or /bug-hunt -b [--base ].
A testing workflow for a role called spec-tester. It creates an HTML test plan, runs tests after implementation, and produces an HTML test report; it can also recheck fixes made by a spec-debugger.
A local knowledge-base search and question-answering assistant. It first navigates the directory structure, learns how to handle file types such as PDFs and spreadsheets, and then searches the relevant files.
Apply this skill whenever writing, reviewing, or refactoring Laravel PHP code. This includes creating or modifying controllers, models, migrations, form requests, policies, jobs, scheduled commands, service classes, and Eloquent queries. Triggers for N+1 and query performance issues, caching strategies, authorization…
Turn any system architecture into an interactive, pannable/zoomable canvas diagram (dark by default with a light switcher, JetBrains Mono, plane-coloured bands, click-to-isolate focus, PNG export) — the "architecture canvas" style — and optionally publish it to artifact.cafe for review. Use whenever the user asks for…
Debug and trace ColecoVision and Super Game Module games using the Gearcoleco emulator MCP server. Provides workflows for Z80 CPU debugging, breakpoint management, TMS9918A VDP/SN76489/AY-3-8910 hardware inspection, disassembly analysis, execution tracing, and rewind/time-travel debugging. Use when the user wants to…
Guide for creating effective skills. This skill should be used when users want to create a new skill (or update an existing skill) that extends Claude's capabilities with specialized knowledge, workflows, or tool integrations.
Use when a user asks how many tokens (or how much context/cost) ContextPilot has saved, or wants a ContextPilot savings status/summary inside Hermes Agent — e.g. "how much did ContextPilot save?", "show ContextPilot token savings", "ContextPilot status", "savings in the last 24h / all time", or "give me the raw…
GPT Image 2 CLI as a Claude Code skill: OpenAI gpt-image-2 + Codex imagegeneration under one command surface, with masks, transparent backgrounds, custom sizes up to 4K, and structured JSON / JSONL progress output.
★not rated 146▲
+2
changed yesterdayA
tokens not measured
originalMIT
Optimise a three.js or raw WebGL scene for phones, 120 Hz panels and low-end devices — device tiering, prewarm-everything-under-the-loader so nothing compiles mid-scroll, in-view-only render loops, DPR and particle/bloom budgets (never a fixed phone frame cap), the 60 fps desktop cap, OffscreenCanvas worker scenes…
Source b-roll for a video edit — classify each moment, scope the search, return vetted candidates, place on the word. Use when the user says "find b-roll", "/find-broll", "source clips for this edit", or wants footage/memes/screenshots to lay over a talking-head video.
Query and write durable debugging memory recorded by MemoryWhale. Use when debugging a failure that may have happened before, when you need the exact error/flags/output from an earlier attempt, when the user asks "how did we fix this last time?", or once you've figured out why something failed / how a fix worked and…
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: