Development plugins

Generate fully self-contained interactive HTML architecture diagrams with zoom, click-through, and detail panels for any software project.

11 skills

Guide for creating high-quality MCP (Model Context Protocol) servers with best practices and templates. Covers Python (FastMCP) and Node/TypeScript (MCP SDK).

11 skills

Scaffold MCP server projects with correct schema, validation, and deployment configuration — prevents common errors on first run.

11 skills

Generates visuals that are unique to the product they are for, and builds them on the right stack. Five skills: product-brief turns an idea into surfaces and capabilities; stack-route picks the best technology per capability against one shared byte and main-thread budget, with a platform-primitive-first rubric and a fidelity ladder for 3D, particles, data viz, editors, realtime and AI UI — every choice recorded with its rejected alternative and its fallback; frontend-design commits to a design contract that separates 'make it unique' (falsifiable originality gates, provenance tracing every color and typeface to a fact about the subject) from 'as good as Stripe' (borrow the craft bar, never the look) from 'match our system'; a spectacle doctrine decides when 3D, shaders, particles and ambient motion are actually earned — every effect must reveal a mechanism, respond to the person, or repay attention, priced by visit frequency, derived from the subject's own verb and specified with a mapping, a degrade path and a cut line; build-surface implements semantics and states before the happy path, with heavy capabilities behind a lazy boundary; ship-audit verifies Core Web Vitals, WCAG 2.2 AA, the state matrix and the bundle budget before anything is called done. Design is judged on the rendered page, not on its source: both frontend-design and ship-audit serve the surface, screenshot it at 390/768/1440 and score seven weighted axes against the images — composition, type, color, density, usability, signature and content, weighted into one 0-10 total under a jury-shaped profile for expressive surfaces and a usability-led one for product surfaces, reporting 'not rendered' rather than a verified design when no browser is available. Landing pages get their own doctrine — the page as an argument, a hero taxonomy, proof that is real or absent, and the tightest performance budget in the plugin — and a repertoire of named devices on five axes — composition, type, color and material,

5 skills · 6 commands

Comprehensive toolkit for developing Claude Code plugins with 7 specialized skills and guided workflow

7 skills · 1 command · 3 agents

AutoCAD MCP server plus the skills and hooks that teach Claude the EPLUS CAD workflow

10 skills · hooks

Web scraping and crawling powered by Firecrawl. Turn any website into clean, LLM-ready markdown or structured data. Scrape single pages, crawl entire sites, search the web, and extract structured information.

10 skills · 1 command

marimo reactive notebook 全方位技能包 — 撰寫 notebook、即時配對程式設計、轉換 Jupyter/Streamlit、論文實作、anywidget、WASM 相容性檢查等 11 個技能。

11 skills

Sanity content platform integration with MCP server, agent skills, and slash commands. Query and author content, build and optimize GROQ queries, design schemas, and set up Visual Editing.

6 skills · 4 commands · 1 MCP server

Run Claude on any model the local Superagent Gateway serves, across five surfaces. A headless lens returns a different-vendor answer as one JSON object on stdout, with failure classes distinguishable by exit code. An interactive launch materializes an attachable session on a named alias and prints a resume handle that never carries the token. A background agent runs unattended under a fixed repo-bounded permission ceiling and is judged against a contract written up front — deliverables measured against a pre-job baseline, an optional verify command the supervisor runs itself — never against the model's account of its own work. A team runs several named members at once, each in its own worktree on its own alias against its own contract, dispatched in bounded rounds from one record on disk that carries every member's probed state, its cause of failure and the model that actually answered it. The plugin owns its own gateway control layer (liveness by probing the model-list endpoint, idempotent locked start, append-only log, runtime install-dir resolution) and setup rewrites the existing gw wrapper to delegate to it and to read its token from the Keychain instead of carrying a hardcoded one.

5 skills · 6 commands

General-purpose development skills and commands: documentation (Diataxis), Fastify, Node.js, TypeScript best practices, and TIL knowledge management.

10 skills · 1 command

Give Claude Code persistent semantic search over your entire project — even 10,000 files — using CustomGPT.ai's RAG engine. Index your codebase, documents, or any file collection once, then ask questions across everything instantly. No context overflow, no re-reading files. Use /create-agent to index a folder, /query-agent to search it, and /refresh-agent to keep it current. Requires only curl — no Node.js, no Python, no dependencies.

11 skills

Ten skills for FiveM and RedM resource development — scaffolding, oxmysql, NUI, state bags, txAdmin, performance, and more.

11 skills

A growing collection of reusable Claude Code skills. Includes skill-creator for building, testing, and benchmarking new skills.

11 skills

Bootstrap and build web apps the Matt way: /stack:setup, /stack:new-app, /stack:start, /stack:feature, /stack:ship, /stack:status, /stack:undo, /stack:db-change, /stack:deploy, /stack:doctor. Encodes the architecture so you can focus on product.

10 skills · hooks

Evidence-backed Knowledge MCP retrieval, learning and guarded separate review using host-exposed tools; no bundled MCP.

5 skills · 6 agents

Code rules, session hand-offs, working rules, parallel builders, dev-server keeper and quality gate for Next.js projects.

10 skills · hooks

Engineering judgment for AI coding agents: reuse before creating, place code correctly, critique and audit structure, and distill, consolidate, harden or polish with the project's own tests.

10 skills · hooks

Next.js + Supabase + Playwright specifics: scaffolding, E2E runs, PR test-plan verification, and subagents for RLS, migrations, accessibility, error handling and test authoring.

3 skills · 8 agents

imlargo's opinionated skills: working style, code conventions, git/release workflow, frontend, backend, Svelte and Go.

11 skills

Comprehensive toolkit for developing Claude Code plugins. Includes 7 expert skills covering hooks, MCP integration, commands, agents, and best practices. AI-assisted plugin creation and validation.

7 skills · 1 command · 3 agents

Comprehensive toolkit for developing Claude Code plugins. Includes 7 expert skills covering hooks, MCP integration, commands, agents, and best practices. AI-assisted plugin creation and validation.

7 skills · 1 command · 3 agents

Default web stack expertise for the AIDLC pipeline: TypeScript standards + strict tooling baseline (ESLint/Prettier/tsconfig/.gitattributes + optional husky/lint-staged) + enterprise project structure (scaffold + dependency-cruiser boundary gate) + the Node/TS CI half (templates, the npm gate, isolated-checkout dependency resolution, cross-platform lockfiles) + the Prettier auto-format hook, Next.js, NestJS, Postgres, MongoDB, DB migrations, Docker, API design.

10 skills · hooks

Comprehensive toolkit for developing Claude Code plugins. Includes 7 expert skills covering hooks, MCP integration, commands, agents, and best practices. AI-assisted plugin creation and validation.

7 skills · 1 command · 3 agents

Stack skills for React, Next.js, Fastify, Drizzle, PostgreSQL, Zod, TypeScript, onion architecture, frontend architecture and security

11 skills

Git workflows for branches, worktrees, and authorized change delivery.

10 skills · hooks

ChittyOS Development: engineering workflows, governance, MCP routing, recursive development and Manifest Forge publishing.

11 skills

Guards, per-session worktrees, session bus, handoff, cold start, close-out and writing skills for Claude Code sessions.

10 skills · hooks

Enforces Red-Green-Refactor with hooks, inside-out or outside-in, and explains the rule behind every block

1 skill · 6 commands · 3 agents · hooks

Repository setup through decision layers (5 app stacks and Claude Code plugin marketplaces, service-api / modular-monolith, MCP, container), ontology → types/API/agent tools, autonomy tiers. Stops at setup.

11 skills