Find plugins

by Seth Hobson

End-to-end feature orchestration with testing, security, performance, and deployment

by Seth Hobson

End-to-end feature orchestration with testing, security, performance, and deployment

by Adam Perlis

Systematic full-stack web development guidance for architecture, debugging, quality, testing, security, and deployment.

Guideline and reference implementation for web apps: Django system of record plus FastAPI realtime/streaming service, Vue 3 + Vite + TypeScript, PostgreSQL, Redis, Celery, login for internal staff (company SSO over OpenID Connect, e.g. Entra ID), external users (verified accounts with MFA) or both, Docker, Task, SOPS, MkDocs docs site, platform-neutral CI and pinned-version deploys to staging and production from the same images. Adds the /fullstack-engineering guideline, the /fullstack-scaffold repo generator and the fullstack-engineer agent.

by Seth Hobson

Functional programming with Elixir, OTP patterns, Phoenix framework, and distributed systems

by Seth Hobson

Functional programming with Elixir, OTP patterns, Phoenix framework, and distributed systems

by Eduardo Furihata

Skills de construção do Furihata — /solve, /principles, /front, /method e /proto: do problema ao commit local, com QA. Funciona sozinho, em qualquer repositório.

by Eduardo Furihata

Skills de entrega do Furihata — uma escada só: os alvos /work, /pull-request, /homolog e /prod levam o trabalho de onde estiver até o próprio estágio, cada um invocando o anterior quando falta algo atrás; os modificadores /repro e /card compõem com qualquer alvo, em qualquer ordem; /infra mapeia a infra do projeto; o processo mora em .claude/ship/setup.md, uma seção por skill. Funciona sozinho, sem depender de outro pacote.

by Eduardo Furihata

Ferramentas avulsas do Furihata — /brain (o parecer: entender o problema e decidir), /blind (a sessão que não vê nada: só o texto que você mandou), /ask, /chat, /save, /sync, /make-dev, /make-skill, /ctt, /video-teams e mais. Cada uma funciona sozinha, sem depender de outra skill.

by r4ge-quit

AI agent skills supporting FusionX business-analysis work — user manuals, functional testing, requirement documentation, and more.

by Fyxer

Search authorized email and meeting context, retrieve summaries and transcripts, resolve contacts, and draft personalized email through Fyxer's official hosted MCP.

by zhengzhongbiao

Game Atelier — 游戏项目资产工坊，本地 Web UI + AI 美术 / 游戏 UI / 视频工作流

by Clint Day

Generate a structured 'what you missed' recap for a game you haven't played in a while

by xiaomi867

Professional game design suite covering systems, gameplay, combat, skills, balance, formula verification, simulation, telemetry experiments, meta balance, economy, progression, level design, UX, configuration auditing, code verification, design review, and GDD workflows. Every independent formal result uses a visible Professional Context Header by default.

by Seth Hobson

Unity game development with C# scripting, Minecraft server plugin development with Bukkit/Spigot APIs

by Seth Hobson

Unity game development with C# scripting, Minecraft server plugin development with Bukkit/Spigot APIs

by OpenAI

Design, prototype, and ship browser games with guided 2D and 3D workflows, asset pipelines, and playtesting support.

by Viktor Gamov

Coding policy for Viktor Gamov's AI agents: language-agnostic quality rules, autonomous shipping discipline, and stack defaults for JVM, Swift, TypeScript, and Python

by Durun

Claude の舐めた返答に頑固オヤジがツッコミを入れる。入れると ON。/gankooyaji で ON/OFF を切り替える。

by Amir Arad

Explicit commands for any git repo that has or is a knowledge base: init, survey, tend, maintain, review, capture, restructure, dream.

by Ghast AI

Research crypto markets, news and on-chain data, and connect a Gate exchange account through OAuth.

by Hiroyuki

Gate-oriented spec-driven development: spec -> clarify -> implement -> reviewer -> worklog, one pull request per issue, with the review gate enforced by a hook rather than requested by prose.

by astrosteveo

Context, cost and rate limits in the footer, warnings at thresholds you set, a compact helper, and /gauge for per-turn figures, the context breakdown and spend history.

by yukineko

Local LLMOps telemetry for Claude Code: a Stop hook that reads each session's transcript and records token usage, cache hits, tool calls, latency, and estimated cost to a local store — then `gauge report` rolls it up by project, model, and day. `gauge subagents` attributes cost to each individual sub-agent (Task) live from its transcript, so callers like condukt can record true per-task cost instead of a lumped session total. v0.3.9: `gauge subagents --json` now also emits `tokens_input`/`tokens_output` per sub-agent, so callers can record real token usage alongside cost. Observability for your own agent runs, subscription-native (one hook + bundled Rust binary, no API key, nothing leaves the machine).