Plugins

Comprehensive PR review agents specializing in comments, tests, error handling, type design, code quality, and code simplification

from varaku1012/aditi.code

from MartinGonzalez/claude-plugins

from franchiseai/claude-code-plugins

AI-generated screenshots and walkthrough videos for pull requests: desktop + mobile, light + dark, annotated with captions.

Three-phase GitHub PR pipeline: script-first review with structured findings, automated preparation with CI gates, and deterministic squash merge with co-author trailers

from marxbiotech/pr-review-toolkit

Practical skills that teach AI agents to get things done — Gmail organization, morning triage, meeting minutes, code review, design planning, and more.

Reasoning methodology layer for AI agents — classifies problems, routes to reasoning protocols, and validates designs before execution

Decomposes a Product Requirements Document (PRD) into domain-specific specs for AI Agent consumption

Build a structured PRD connecting problem, users, solution, and success criteria.

Manage Product Requirements Documents (PRDs) to gate feature development behind structured requirements and track implementation status

12 parallel subagent checks + 3 auto-fixers for Supabase + Vercel + Next.js security and reliability

Systematically identify how a plan or design could fail before committing to it.

Plugin from lgtm-hq/ai-skills

Precision Agriculture specialist team — 4 agents, 5 skills, 4-file cited knowledge bank, 3 templates, 5 commands, 8 best-practice rules, 1 advisory hook. An agronomy-and-farm-operations team for a grower, farm manager, or ag retailer — it manages inputs to agronomic and economic return (not maximum yield), reads yield by management zone rather than field average, times operations to the agronomic and weather window, and reads the farm P&L per acre the way an operator who lives the margin does. Inherits ravenclaude-core protocols.

FEP/World-Models scaffolding for stable LLM coding agents: predict-before-act, inspectable belief state, and surprise-triggered reflection.

Version-aware Prefect 3 guidance: a live docs-lookup protocol, CLI-first instance queries, and house standards. Prefect 2.x out of scope.

Preferencias de comunicación + principios de trabajo.

ユーザー入力待ちの直前に、次に必要となる読み取り主体の作業をバックグラウンドで先行実行し、回答後の待ち時間を短縮する

Honest self-assessment skill that surfaces incomplete work, missing verifications, bugs, and improvement ideas before shipping.

Presentation builder: create interactive Reveal.js presentations from JSON with Mermaid diagrams, LaTeX math, code highlighting, and animated reveals

Plugin from greglamb/claude-gcode-tools

from oneqmethod/skills

Skills for click-driven web video presentations and screen-recorded explainers.

Preset CLI skills for explicit shell, scripting, and CI/CD workflows driven by the `sup` CLI (PyPI package `superset-sup`). Use only for CLI workflows; do not use for MCP-only work or as a substitute for direct API calls when the user wants HTTP/SDK code.

Write an Amazon-style press release that defines customer value before building.

from TheBushidoCollective/han

Set up and triage preuser on a repo: /preuser:setup writes .preuser/config.yml targets and journeys; /preuser:status checks GitHub App connector visibility; /preuser:validate checks shape; /preuser:seal encrypts login values; /preuser:rescue diagnoses config, deploy handoff, reachability, auth, and run evidence; /preuser:feedback sends consented setup pain reports.

Amazon Working Backwards PR/FAQ process — generate professional LaTeX documents for product discovery and decision-making