Agent skills
Skills you can use with AI coding agents, indexed from public GitHub repositories.
-
llm-judge
LLM-as-judge methodology for comparing code implementations across repositories. Scores implementations on functionality, security, test quality, overengineering, and dead code using weighted rubrics. Used by /beagle:llm-judge command.
majiayu000/claude-skill-registry 163
-
ui-design
Comprehensive UI design skill covering fundamentals, patterns, and anti-patterns. Layout, typography, color, spacing, accessibility, motion, and component design. Use when building any web interface, reviewing design quality, or creating distinctive UIs.
majiayu000/claude-skill-registry 163
-
rayden-use
Build and maintain Rayden UI components and screens in Figma via Figma MCP with full design token enforcement
majiayu000/claude-skill-registry 163
-
retro
Quick-capture a learning. For full retrospectives, use /post-mortem. Trigger phrases: "quick learning", "capture lesson", "retro quick".
majiayu000/claude-skill-registry 163
-
sabx
Control SABnzbd download manager via CLI. Use when users need to check download queue/history, add NZBs, manage priorities, control speed limits, pause/resume downloads, configure RSS feeds, run scheduled tasks, or automate Usenet workflows. Triggers include "sabnzbd", "sabx", "downloads", "nzb", "usenet", "download queue", "download status".
majiayu000/claude-skill-registry 163
-
prisma-query-optimizer
Analyze Prisma queries for performance issues and suggest optimizations. Use when asked to optimize, analyze, audit, or review Prisma queries, or when investigating slow database operations in a Prisma-based project.
majiayu000/claude-skill-registry 163
-
pre-mortem
Validate a plan or spec before implementation using multi-model council. Answer: Is this good enough to implement? Triggers: "pre-mortem", "validate plan", "validate spec", "is this ready".
majiayu000/claude-skill-registry 163
-
af-playwright-e2e
Write Playwright E2E tests from Markdown scenario specifications or debug existing E2E tests. Use when creating end-to-end test files, generating tests from mini-PRD scenarios, configuring Playwright, or using Page Object Model patterns.
majiayu000/claude-skill-registry 163
-
weaviate-query-agent
Search and retrieve data from local Weaviate using semantic search, filters, RAG, and hybrid queries
majiayu000/claude-skill-registry 163
-
reflexion
Use when roundtable returns ITERATE verdict in the Forged workflow. Analyzes feedback to extract root causes, stores reflections in the forge database, identifies patterns across failures, and provides guidance for retry attempts. Prevents repeated mistakes across iterations.
majiayu000/claude-skill-registry 163
-
maxim
Maxim Integrated (now Analog Devices) MPN encoding patterns, suffix decoding, and handler guidance. Use when working with Maxim/Dallas components or MaximHandler.
majiayu000/claude-skill-registry 163
-
libsupervision
libsupervision - Process supervision system. Supervisor manages process tree inspired by s6-svscan. LongRunner handles persistent processes with restart. OneShot handles single-execution tasks. ProcessState tracks process lifecycle. LogWriter manages process logging. Use for service management, process control, and graceful shutdown handling.
majiayu000/claude-skill-registry 163
-
ReasoningBank Intelligence
Implement adaptive learning with ReasoningBank for pattern recognition, strategy optimization, and continuous improvement. Use when building self-learning agents, optimizing workflows, or implementing meta-cognitive systems.
majiayu000/claude-skill-registry 163
-
django-pro
Master Django 5.x with async views, DRF, Celery, and Django Channels. Build scalable web applications with proper architecture, testing, and deployment. Use PROACTIVELY for Django development, ORM optimization, or complex Django patterns.
majiayu000/claude-skill-registry 163
-
backend-architect
Expert backend architect specializing in scalable API design, microservices architecture, and distributed systems. Masters REST/GraphQL/gRPC APIs, event-driven architectures, service mesh patterns, and modern backend frameworks. Handles service boundary definition, inter-service communication, resilience patterns, and observability. Use PROACTIVELY when creating new backend services or APIs.
majiayu000/claude-skill-registry 163
-
humanizer
Remove signs of AI-generated writing from text. Use when editing or reviewing
text to sound natural and human-written. Based on Wikipedia's
"Signs of AI writing" guide. Detects and fixes patterns including:
inflated symbolism, promotional language, superficial -ing analyses, vague
attributions, em dash overuse, rule of three, AI vocabulary words, negative
parallelisms, and excessive conjunctive phrases.
majiayu000/claude-skill-registry 163
-
sentiment-analyzer
Analyze text sentiment (positive/negative/neutral) with confidence scores, emotion detection, and visualization. Supports single text, CSV batch, and trend analysis.
majiayu000/claude-skill-registry 163
-
react-modernization
Upgrade React applications to latest versions, migrate from class components to hooks, and adopt concurrent features. Use when modernizing React codebases, migrating to React Hooks, or upgrading to latest React versions.
majiayu000/claude-skill-registry 163
-
pr-wordy-main-omega
{{ 𝛀𝛀𝛀 }} Create a pull request to main
majiayu000/claude-skill-registry 163
-
subagent-driven-development
Use when executing implementation plans with independent tasks in the current session
majiayu000/claude-skill-registry 163
-
user-permissions
Linux user and permission management
majiayu000/claude-skill-registry 163
-
af-enforce-glossary
Enforce glossary compliance in BDD scenarios and documentation. Use when checking domain terminology, adding glossary entries, or validating terminology consistency across specifications.
majiayu000/claude-skill-registry 163
-
broll-prompting
Generate AI image prompts for YouTube video B-roll using Imagen.
majiayu000/claude-skill-registry 163
-
retro
Weekly engineering retrospective. Analyzes commit history, work patterns,
and code quality metrics with persistent history and trend tracking.
Team-aware: breaks down per-person contributions with praise and growth areas.
Use when asked to "weekly retro", "what did we ship", or "engineering retrospective".
Proactively suggest at the end of a work week or sprint.
majiayu000/claude-skill-registry 163