Every Claude Code tool you need :)

obsidian-ai

npm install -g @anthropic-ai/claude-code

49

@spencermarxView Plugin→

recursive-decompositio…

Decompose dense codebase-wide, multi-document, PDF, and aggregation work even when the input fits the context window, following Recursive Language Models…

fromrecursive-decomposition48

@massimodeluisaView Skill→

gemini-rescue

Proactively use when Claude Code is stuck, wants a second implementation or diagnosis pass, needs a deeper root-cause investigation, or should hand a…

fromgemini-plugin-cc47

@abiswas97View Agent→

clean

Remove the git worktrees review checked PR code out into. Each one is a full checkout on disk; nothing else is touched.

fromopen-pr46

@tomosia-vietnamView Command→

auvik

Monitors network devices, maps topology and tracks configuration changes for managed service provider clients.

frommsp-claude-plugins46

@wyre-technologyView MCP→

procedural-clouds-thre…

A Claude Code skill for generating beautiful procedural clouds in Three.js, emphasizing artistic quality across all major cloud types with WebGPU raymarching and WebGL fallbacks. Part of the Teaching Three.js skill series.

1 skill47

@ck42bbView Plugin→

a11y-check

Accessibility audit, scoped to the surfaces a product actually has. Detects web / rendered_markdown / terminal / native_app / video_audio / document /…

frommycelium46

@haabeView Skill→

architect

System architecture, data modeling, API contract design, and the creation of structured implementation blueprints for development teams

fromatelier46

@martinffxView Agent→

convert-to-wp-theme

Convert a complete HTML/CSS/JavaScript project into a production-ready WordPress block theme (Full Site Editing).

fromwp-block-theme-converter46

@siddik-webView Command→

context7

Fetches current, version specific documentation and code examples for a library, so the agent stops working from stale training data.

fromclaude-token-reducer46

@madhan230205View MCP→

jsapi-skills

This repository provides AI assistant Skills for Baidu Map JSAPI. Use them with Claude, Cursor, or other clients that support skills so the AI can reference accurate API docs and examples when you work with Baidu Map.

4 skills46

@baidu-mapsView Plugin→

code-review-levels

Reference documents for deep code review (Level 3) and architecture review (Level 4). Used by code-reviewer agent for advanced review levels.

fromwigtn-plugins45

@wigtnView Skill→

stitch-kit

Use this agent for anything Stitch-related: ideating designs through conversation, generating UI screens from text, editing/iterating designs, generating…

fromstitch-kit45

@gabelulView Agent→

tokenless-style-chat

Set Tokenless style to chat: shortest readable output

fromtokenless45

@maxforaiView Command→

vaaya

fromvaaya43

@vaaya-aiView MCP→

evilmartians-agent-ski…

Agent Skills we build and use at Evil Martians, packaged so you can install them into your own AI coding agent.

5 skills45

@evilmartiansView Plugin→

agents-standards

Standards for authoring SDD plugin agents — frontmatter, self-containment, skill references, and no-user-interaction rules.

fromsdd44

@liorcohenView Skill→

code-explorer

Delegate to this agent for deep codebase exploration — semantic search, exact symbol lookup and reference tracing over a Beacon index. Use when the question…

frombeacon44

@sagarmkView Agent→

ai-governance

Generate and enforce policy gates for AI coding agents (Copilot, Claude Code) — real-time session hooks that deny protected-path edits and dangerous commands,…

fromplatform-skills44

@nitinjain999View Command→

outsystems

fromoutsystems34

@outsystemsView MCP→

aurakit

One command. Full stack. Zero compromise. — All-in-one Claude Code skill with 33 modes, 6-layer security, 23 hooks, and 75% token savings. Works on Codex, Cursor, Manus, Windsurf.

3 skills43

@smorky850612View Plugin→

evaluator

TandemKit Evaluator — verify the Generator's work against the spec with Codex as a second opinion. Fully autonomous. Invoked explicitly.

fromtandemkit42

@flinedevView Skill→

kimi-ask

Use this agent when the user wants Kimi to answer a free-form question about the repository in prose — explain a module, trace a flow, compare alternatives, or…

fromkimi39

@linxuleView Agent→

v-adr

Capture one genuine architecture decision as a thin, human-confirmed ADR under docs/superpowers/adr/NNNN-slug.md — decision-with-alternatives-and-consequences,…

fromsuperpowers-v38

@procodersView Command→