Development plugins

Build remote MCP servers that wrap third-party REST APIs and publish them as linux/amd64 Docker images for the MintMCP hosted runtime.

1 skill

Python code intelligence via basedpyright, pointing at the machine-wide binary

LSP

TypeScript/JavaScript code intelligence via vtsls, pointing at the machine-wide binary

LSP

Go code intelligence via gopls, pointing at the machine-wide binary

LSP

Core functionality plugin for the menon ecosystem with feature management and configuration capabilities.

1 skill

Generate beautiful HTML pages that visually explain systems, code changes, and data

1 skill

[Windows] 基本鈴聲 - 在 Claude Code 要求權限、提問或停止時，自動播放提示音通知用戶

hooks

[macOS] 基本鈴聲 - 在 Claude Code 要求權限、提問或停止時，自動播放提示音通知用戶

hooks

[Linux] 基本鈴聲 - 在 Claude Code 要求權限、提問或停止時，自動播放提示音通知用戶

hooks

Astro language server for code intelligence, diagnostics, and formatting in .astro files

hooks

LangSmith-parity observability over Kafka for any LangGraph.js / LangChain.js agent: /add-kafka-observability installs or upgrades a vendored src/observability/ library that attaches a BaseTracer subclass globally through two redundant paths — the configure hook plus the configure-slot LangSmith's own tracer occupies, so it attaches even on platform runtimes that sever async-context ancestry (one startup() call, zero per-node instrumentation) — and publishes EVERY traced run — graph invocation, LangGraph nodes, LLM calls with full prompts/outputs/token usage, tool runs, errors, trace hierarchy, plus opt-in backend HTTP call runs via the traceBackendCall helper — as start/end events to a Kafka topic (standard envelope keyed by event id, thread_id correlation, zod-validated, secret-redacted, 512KB-truncated) over a bounded non-blocking fire-and-forget producer (librdkafka, acks=all, idempotent, bounded shutdown). By default EVERY run is emitted (full LangSmith parity); apps that have payload-verified which of their runs duplicate root/llm/tool content can opt into run filtering (KAFKA_RUN_FILTER_MODE=allow|deny + run_type:name globs, the name side also matching metadata.langgraph_node; the root run always survives — it carries the full invocation input/final state and is the turn-boundary marker for timeline consumers). Disabled by default (KAFKA_ENABLED); runs alongside LangSmith for parallel validation so LangSmith can be unplugged with no code change. Conversation content (prompts, completions, graph state, tool params) is masked by a policy the APPLICATION supplies — startup({ contentMask }) plus digit/deep-walk primitives that compose with a domain masker the project already owns, covering both numeral runs and digits SPOKEN as words (Greek + English packs, inflection/accent-tolerant — how PINs and OTPs actually arrive on a voice channel); the library ships the SEAM, not the policy (which digits are a tax id and which an order reference is a fact about the app's

1 skill

Recover the original goal of a long Claude Code or Codex session with a local, inspectable recovery anchor.

1 skill

Design Unity UI Toolkit screens from a description or a sketch, check the layout headlessly, and hand over a self-contained HTML preview that reports what it could not draw.

1 skill

Talk to other agents in a signed room, and stop for a human's signed approval before a deploy, delete, payment or outbound email. Adds eight room tools and the skill that tells an agent how to use them safely.

1 skill

Expert Claude Code agent that consults official documentation to help create skills, agents, plugins, hooks, and configure Claude Code.

1 agent

Write applications in Aktion, a declarative DSL that renders to a live UI from one web component. Adds /aktion, which builds a complete app from a one-line request, checks it against the 282-component schema, and leaves you a runnable page.

1 skill

Writing, reviewing, and debugging SharpMUSH softcode, alongside the helpfiles it teaches agents to read.

1 skill

On-demand static analysis of AI system prompts: audit a prompt file for contradictions, coverage gaps, priority ambiguities and meta-paradoxes, locally and offline.

1 skill

The gate for the next GTM skill pack: knowledge card, design card, security, README, and plugin checks. For pack authors, not a customer pack.

1 skill

Use when working with mise - creating or editing mise.toml, .mise.toml, mise.local.toml, or file tasks; defining tasks and their usage-spec arguments; managing dev tools, backends, and lockfiles; configuring environments, secrets, hooks, daemons, sandboxing, or settings; machine bootstrap and dotfiles; monorepo workspaces; or running any mise CLI command.

1 skill

Aurelia application development skills for Claude Code and compatible agents.

1 skill

Quantum agentic systems over MCP: IBM Quantum backends and calibration, circuits classified by what their results could ever prove, cost estimates and local simulation. Never submits jobs or spends QPU time.

1 MCP server

Lean 4 proof checking linked to the lean-worker prover: kernel-check Lean and report the axioms a theorem rests on, call a prover node and verify its signed certificate, and seal or open Kant zk-relay envelopes. Runs the Lean compiler locally; never posts to the relay on its own.

1 MCP server

Browser-based code review tool. Shows git diffs in a GitHub-style UI with syntax highlighting, inline comments, and sends formatted feedback back to Claude.

1 command

Framework-agnostic baseline: accessibility, Core Web Vitals, code quality, and UX rules that every other stack skill in this marketplace extends. Install this alongside any stack, or on its own for a project that doesn't fit the other categories.

1 skill

Frontend standards for plain HTML & CSS projects — semantic markup, accessible components, responsive layout, and Core Web Vitals without a framework.

1 skill

Frontend standards for React (Vite/CRA) projects — accessible components, hooks best practices, performance, and file conventions.

1 skill

Горячая замена модулей BSL в 1С:Предприятии (rphost и 1cv8) без перезапуска процессов и сеансов

1 skill

Audit the skills and MCP servers you have installed: context cost, overlapping descriptions, vague or long descriptions, and skills with missing files. Read-only.

1 skill

Move a WordPress site from any host to Spacefast, with managed WordPress as a headless backend, a static Astro front end from GitHub, and a DNS cutover

1 skill