Agent skills
Skills you can use with AI coding agents, indexed from public GitHub repositories.
-
skill-creator
Design and create Claude Skills using progressive disclosure principles. Use when building new skills, planning skill architecture, or writing skill content.
majiayu000/claude-skill-registry 163
-
brand-typography-systems
Provides brand typography selection and hierarchy development frameworks including the Brand-First Typography Selection Process, Modular Scale System, Font Classification Matrix, Serif vs. Sans-Serif Decision Framework, Typeface Evaluation Criteria, Font Pairing Principles, WCAG accessibility requirements, and typography design tokens. Auto-activates during brand typography development, font selection, type hierarchy creation, and typography system work. Use when discussing brand typography, font selection, font pairing, type hierarchy, modular scale, typography accessibility, WCAG typography, or typography guidelines.
majiayu000/claude-skill-registry 163
-
nuxt-architecture
Foundational architecture for Nuxt 4 + Vue 3 + Nuxt UI applications. Use when starting new projects, understanding project structure, or making architectural decisions about directory organization, technology choices, and pattern selection.
majiayu000/claude-skill-registry 163
-
tailwind-config
Update Tailwind CSS configuration, custom themes, and design tokens across packages. Use when adding new colors, spacing scales, or customizing the design system.
majiayu000/claude-skill-registry 163
-
Browser
Debug-first browser automation with always-on visibility. Console logs, network requests, and errors captured by default. USE WHEN browser, screenshot, debug web, verify UI, troubleshoot frontend.
majiayu000/claude-skill-registry 163
-
non-disturbance-expert
Expert in SNDA agreements (Subordination, Non-Disturbance, and Attornment) that protect tenants from eviction if the landlord's lender forecloses. Use when tenant is negotiating lease for major space requiring significant investment, lender is requiring subordination, analyzing tenant's foreclosure protection, drafting three-party SNDA agreements, evaluating whether tenant can survive foreclosure, or negotiating with lenders for non-disturbance protection. Key terms include SNDA, non-disturbance, attornment, subordination, foreclosure, lender priority, tenant protection, mortgage, charge, tripartite agreement, lease survival
majiayu000/claude-skill-registry 163
-
monitoring-alerting
アプリケーションとインフラの監視・アラート設計を専門とするスキル。
ゴールデンシグナル（レイテンシー・トラフィック・エラー・飽和度）に基づくメトリクス戦略、
構造化ログ設計、SLI/SLO定義、アラート閾値設定、ダッシュボード構成を統合的に提供する。
Anchors:
• Observability Engineering (Charity Majors) / 適用: ログ設計とメトリクス戦略 / 目的: 高カーディナリティ観測の実現
• Site Reliability Engineering (Google) / 適用: SLI/SLO設計 / 目的: ビジネス価値に基づく監視体系
• Golden Signals / 適用: 4指標（Latency・Traffic・Errors・Saturation） / 目的: 効果的な監視指標の選定
Trigger:
Use when designing monitoring strategy, defining SLI/SLO, configuring alerts, implementing structured logging, or building observability dashboards.
monitoring, alerting, observability, metrics, logging, SLI, SLO, golden signals, dashboard, Grafana, Prometheus, Discord webhook
majiayu000/claude-skill-registry 163
-
frontend-design-review
Design principles and review methodology for UI/UX work. Use when building new interfaces, reviewing visual changes, or validating design quality. Contains best practices for visual polish, accessibility (WCAG 2.1 AA), responsive design, component standards, and interaction patterns. Works both as a development guide and a review checklist. Produces structured reports with prioritized findings.
majiayu000/claude-skill-registry 163
-
cupertino-ui-consistency
Maintain Cupertino + Lumina visual consistency for the AERA frontend. Use when creating or modifying UI, CSS/tokens, layouts, components, menus/overlays, tables, charts, or interaction states in this repo.
majiayu000/claude-skill-registry 163
-
analytic-philosophy
Master Analytic philosophy methods, debates, and key figures. Use for: logical analysis, philosophy of language, philosophy of mind, metaphysics, epistemology in the analytic tradition. Triggers: 'analytic', 'Frege', 'Russell', 'Wittgenstein', 'logical positivism', 'Vienna Circle', 'possible worlds', 'modal logic', 'qualia', 'functionalism', 'physicalism', 'Kripke', 'Putnam', 'Davidson', 'Quine', 'ordinary language', 'thought experiment', 'conceptual analysis', 'naturalism', 'supervenience'.
majiayu000/claude-skill-registry 163
-
gpt5.2-spec-writer
Guide for writing effective prompt specifications (specs) for the GPT-5.2 Codex agent. Use when the user asks to "write a prompt spec", "create a system prompt for GPT-5.2", "design a spec for an agent", or "how to prompt GPT-5.2".
majiayu000/claude-skill-registry 163
-
gp-ui
Use when building React UIs for TheGP applications, migrating existing UIs to @gp/ui components, integrating Tailwind v4 with @gp/ui theme, or answering questions about available components, design tokens, icons, or setup. Activate when user mentions @gp/ui, TheGP design system, or asks about GP-specific UI patterns and components.
majiayu000/claude-skill-registry 163
-
collaboration-hub
Develop and modify the AILANG Collaboration Hub UI. Use when user asks to add features to the monitoring dashboard, modify the approval queue, update the message center, or make changes to the React frontend.
majiayu000/claude-skill-registry 163
-
dagu-workflows
Guide for authoring Dagu workflows including YAML syntax, steps, executors, scheduling, dependencies, and workflow composition
majiayu000/claude-skill-registry 163
-
env-var-manager
Manages environment variable additions and updates across all project files. Use when adding new environment variables, updating PORT configuration, modifying deployment configurations, or documenting configuration requirements.
majiayu000/claude-skill-registry 163
-
create-observability-config
Setup observability platform configuration (Datadog, Prometheus, Splunk) with REQ-* dashboards and alerts. Creates monitors for each requirement with SLA tracking. Use when deploying to production or setting up monitoring.
majiayu000/claude-skill-registry 163
-
trial-conversion
Trial optimization and conversion patterns for SaaS. Covers trial design, activation metrics, conversion funnels, and win-back strategies.
majiayu000/claude-skill-registry 163
-
functional-designer
Designs functional architecture and detailed specifications for PHP/CakePHP applications based on analyzed requirements
majiayu000/claude-skill-registry 163
-
radius-scale
Generates border-radius tokens from sharp to pill shapes. Use when creating corner rounding systems, button radius, card corners, or input styling. Outputs CSS, Tailwind, or JSON.
majiayu000/claude-skill-registry 163
-
performance-budgeting
Allocate latency budgets and performance targets across system components
majiayu000/claude-skill-registry 163
-
prototype
Create quick React prototypes that bundle to a single HTML file. Use for demos, interactive experiments, or shareable artifacts - NOT for full apps (use audreygen/Next.js for those).
majiayu000/claude-skill-registry 163
-
research
Multi-source comprehensive research using perplexity-researcher, claude-researcher, and gemini-researcher agents. Three modes - Quick (3 agents), Standard (9 agents), Extensive (24 agents with be-creative skill). USE WHEN user says 'do research', 'quick research', 'extensive research', 'find information about', 'investigate', 'analyze trends', 'current events', or any research-related request.
majiayu000/claude-skill-registry 163
-
apex-os-design
Generates premium dark-mode UI for Apex OS wellness app (React Native + Expo 54). Use when designing screens, creating components, making layout decisions, generating data visualizations, or writing frontend code. Covers color system, typography, motion, haptics, and component patterns for a Bloomberg-meets-Calm aesthetic. References APEX_OS_PRD_v8.1.md for product logic and APEX_OS_BRAND_GUIDE.md for voice.
majiayu000/claude-skill-registry 163
-
scaffold-experiment
Set up complete experimental infrastructure for all runs in a designed experiment. Orchestrates parallel generation of fine-tuning configs (via scaffold-torchtune) and evaluation configs (via scaffold-inspect). Use after design-experiment to prepare configs before running experiments.
majiayu000/claude-skill-registry 163