Claude Code

Puter MCP enables AI tools to interact with Puter: manage files, websites, workers, and more

Market intelligence MCP: 18 engines, calibrated uncertainty, outcome-verified. Not financial advice

Metacognitive AI agent oversight: adaptive CPI interrupts for alignment, reflection and safety

PromptWizard 前端开发 Skill。适用于 Vue 3 + Vite + Ant Design Vue + axios 场景下的组件开发、页面调整、API 接入和展示层修复。默认遵循当前仓库的 JavaScript 写法，而不是假设 TypeScript、Pinia 或 HeroUI 已经存在。

Generate MantleKit setup plans and launch-ready SaaS blueprints from a product idea.

Authors and updates customization overrides for installed BMad skills. Use when the user says 'customize bmad', 'override a skill', 'change agent behavior', or 'customize a workflow'.

Audio features (BPM, key, mood, genre) for real tracks - a Spotify audio-features replacement.

Provides guidance and best practices on Polygerrit UI development, frontend architecture, and TypeScript/JS coding standards in Gerrit.

Use when a task runs long and the context window is filling -- large files are being read whole, command output is flooding the transcript, or responses are getting verbose and slow.

A flock of AI users tests your deployed app and reports where real people get stuck, with fixes.

Use this skill when the user asks about my own features, configuration, or usage — installation, skills, Web UI, CLI, API config, memory, sessions, encryption, white-label, publishing, pricing, troubleshooting, or restarting the server. Do NOT trigger for general coding tasks unrelated to me.

Run accessibility & contrast audits and file QA issues from Claude Code, Cursor, and Windsurf.

Agentic search over your Dewey document collections from any MCP-compatible client.

Sales prospecting and lead generation from Google reviews: local businesses leaking leads, scored.

Orchestrate task execution via beads and sub-agents. Gets ready work from beads, spawns appropriate agents based on labels, monitors completion, and updates status. Use after /approve-spec has created tasks.

Guide for VS Code extension development from scaffolding to Marketplace publication

Experimental Agent Teams orchestration — run CC_GodMode agents as parallel teammates with SharedTaskList coordination (requires CLAUDE_CODE_EXPERIMENTAL_AGENT_TEAMS=1)

Cross-border payment & banking intelligence for AI agents: SWIFT/BIC, IBAN, sanctions, FX, tracking.

Brainstorm - Requirements Discovery (AI Coding Enhanced)

知乎收藏夹与文章内容抓取：API/Playwright 多级降级、Cookie 持久化与保活、批量正文与图片、断点续传、可选写入 Obsidian。| Zhihu collection scraping, batch article fetch, Obsidian export.

Book medical appointments with French doctors by specialty and city via AI agents.

JSXN encoder/decoder — compact notation for React/Next.js files, optimized for LLMs

Use when implementing any part of the Cortex Notes license/KeyGen system. Loads full plan context, phase checklist, and implementation rules specific to the license feature.

MCP server for Infracost CLI integration - cloud cost estimates for Infrastructure as Code

Use when performing customer data export — template for handling customer data export requests (data portability). Covers request validation, data source identification, extraction and assembly, format standardization, secure delivery, verification, and audit trail maintenance to fulfill data subje…

Turn prototype feedback into product decisions that your whole team can trace.

MCP server for subscribing to and managing on-chain event webhooks via Crypto APIs

Catalog a runbook command option

Siemens TIA Portal MCP server — AI-assisted PLC programming. 16 tools, 166 actions.

Use when working on JhnsonO/ffa-automations' FFA 360 Ball Tracker: planning or implementing a bounded task, reviewing a GitHub Actions run or artifact, diagnosing a failure, or reconciling project state. Enforces summary-first retrieval, one-poll workflow handling, frozen-boundary protection, and c…