Skills, subagents, slash commands, hooks, settings, plugin bundles and MCP servers that install into Claude Code. 386,050 indexed, measured the same four ways as everything else here.
Set up an ICM (Interpretable Context Methodology) workspace on any project — generating IDENTITY.md (Layer 0), CONTEXT.md (Layer 1), and config/ (Layer 3) files tailored to the project's domain, folder structure, and workflow.
Drives browser automation with advai browser for navigation, DOM actions, extraction, screenshots, cookies, tabs, and network capture. Invoke when a task needs live browser interaction or web scraping.
Skill "testing_framework" from calesthio/PhantomReach, covering phantom reach — agentic testing framework, how this skill works, first steps (every session), 1. read this skill and 2. read the project context.
Build AI phone agents with AgentPhone API. Use when the user wants to make phone calls, send/receive SMS, manage phone numbers, create voice agents, set up webhooks, or check usage — anything related to telephony, phone numbers, or voice AI.
Web search, extraction, crawling, mapping, and deep research via Tavily API. Five tools for finding information, extracting content, exploring websites, and generating research reports.
Design review grounded in Checklist Design's 100+ published checklists. One skill, two modes: /checklist-design audit for a systematic item-by-item check, /checklist-design critique for quick honest feedback.
A framework for building web apps where the server drives page updates while the browser reacts to changes. It uses server-sent events, a way for servers to send updates to browsers over a connection, plus signals and DOM updates.
Workspace OS charter for Auto — runtime governor of the agent organisation, routing, cadence, authority, governance, and full platform operations reference.
Create shareable markdown links for collaboration with humans. Share plans, documents, reports, and drafts as beautiful editable web pages. Use when the user needs to review, comment on, or iterate on markdown content in a browser — such as project plans, proposals, meeting notes, or any document that benefits from…
Use PitlaneMCP for token-efficient codebase exploration, symbol discovery, execution-path tracing, change-impact analysis, and indexed documentation lookup when its MCP tools are configured and available.
Manage Actual Budget accounts, transactions, budgets, rules and reports from an AI assistant. Runs locally from the actual-mcp-server npm package. Needs 5 environment variables to run.
★not rated 76 yesterdayASocket: warn
tokens not measured
originalMIT
Use when a new request might involve repo work, tracked changes, workspace-specific decisions, or durable coordination and you must decide whether Superplan should engage before exploring or implementing.
Crea automatizaciones inteligentes (agentes de IA) en la nube de Cloudflare, paso a paso, en español sencillo, sin necesidad de saber programar. Úsalo cuando alguien escriba "/crear-agente", "quiero hacer un agente", "quiero automatizar [X]", "quiero un sistema que me [Y]", "ayúdame a construir una automatización"…
Create a test user (with explicit permission) to audit what authenticated users can access vs anonymous users. Detects IDOR, cross-user access, and privilege escalation.
Autonomous incident detection, root-cause analysis, and self-healing for Linux/Docker production environments. Activate when the user mentions: server down, high CPU, memory leak, disk full, service crash, deployment failure, alert firing, on-call page, or any infrastructure emergency. Also activates on scheduled…
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: