Agent skills
Skills you can use with AI coding agents, indexed from public GitHub repositories.
-
twitter-cleaner
对 Twitter 采集产出进行二次清洗，自动获取完整推文内容并生成可筛选数据。
majiayu000/claude-skill-registry 163
-
unsee-ability-destroyer
Iteration 22 of Multiplicity Cascade - Makes patterns impossible to unsee
majiayu000/claude-skill-registry 163
-
go-dev
Go 开发规范，包含命名约定、错误处理、并发编程、测试规范等
majiayu000/claude-skill-registry 163
-
job-application-writer
案件応募時の意気込み・PR文を自動生成するスキル。「案件に応募したい」「応募文を書いて」「PRを作成して」「意気込みを書いて」「エントリーシートを作りたい」などのリクエストに使用。募集要項と職務経歴書を照合し、マッチ度分析・最適化されたPR文を複数バリエーションで生成する。
majiayu000/claude-skill-registry 163
-
claude-speak
Speak text aloud using high-quality AI voice synthesis (Kokoro TTS on Apple Silicon). Use when user asks to vocalize, narrate, or speak text out loud.
majiayu000/claude-skill-registry 163
-
goap-agent
Invoke for complex multi-step tasks requiring intelligent planning and multi-agent coordination. Use when tasks need decomposition, dependency mapping, parallel/sequential/swarm/iterative execution strategies, or coordination of multiple specialized agents with quality gates and dynamic optimization.
majiayu000/claude-skill-registry 163
-
issue-compact
Consolidate GitHub issue discussion into clean body for handoff
majiayu000/claude-skill-registry 163
-
worker-benchmarks
Run comprehensive worker system benchmarks and performance analysis
majiayu000/claude-skill-registry 163
-
dev-server-sandbox
Run multiple isolated mux dev-server instances (temp MUX_ROOT + free ports)
majiayu000/claude-skill-registry 163
-
claude-skill-builder
Interactive skill creator for Claude Code. Triggers when user mentions creating skills, building skills, skill templates, skill frontmatter, allowed-tools, or wants to scaffold a new skill.
majiayu000/claude-skill-registry 163
-
video-comparer
This skill should be used when comparing two videos to analyze compression results or quality differences. Generates interactive HTML reports with quality metrics (PSNR, SSIM) and frame-by-frame visual comparisons. Triggers when users mention "compare videos", "video quality", "compression analysis", "before/after compression", or request quality assessment of compressed videos.
majiayu000/claude-skill-registry 163
-
ecomode
Token-efficient model routing modifier
majiayu000/claude-skill-registry 163
-
code-validation-sandbox
Validate code examples across the 4-Layer Teaching Method with intelligent strategy selection. Use when validating Python/Node/Rust code in book chapters. NOT for production deployment testing.
majiayu000/claude-skill-registry 163
-
evaluate-skill
评价 Skill 执行结果的 Skill。当需要评价产出质量、判断是否需要迭代时触发。触发词：评价、evaluate、打分、怎么样、效果如何。
majiayu000/claude-skill-registry 163
-
aws-cloudfront-cdn
Distribute content globally using CloudFront with caching, security headers, WAF integration, and origin configuration. Use for low-latency content delivery.
majiayu000/claude-skill-registry 163
-
confluent-ksqldb
ksqlDB stream processing expert. Covers SQL-like queries on Kafka topics, stream and table concepts, joins, aggregations, windowing, materialized views, and real-time data transformations. Activates for ksqldb, ksql, stream processing, kafka sql, real-time analytics, windowing, stream joins, table joins, materialized views.
majiayu000/claude-skill-registry 163
-
social-playbook-skill
Design and generate complete social media playbooks (scripts, visuals, captions, hooks, thumbnails, transitions) for Synthex clients across YouTube, TikTok, Instagram, Facebook, LinkedIn, and Shorts/Reels. Use when planning multi-platform campaigns or content systems.
majiayu000/claude-skill-registry 163
-
recovering-sessions
Recover from crashed, failed, or interrupted Claude Code sessions. Use this skill when: session crashed during multi-agent parallel execution, need to determine what work was completed vs incomplete, want to generate resumption commands for interrupted tasks, recovering from context window exhaustion, or handling session handoffs. Analyzes agent logs, verifies on-disk state, and creates resumption plans with ready-to-execute Task() commands.
majiayu000/claude-skill-registry 163
-
executive-cto
Executive CTO Agent. 기술 전략, 아키텍처 결정, R&D 리더십을 담당합니다.
majiayu000/claude-skill-registry 163
-
Modal Sheet Debugger
Fix SwiftUI sheet presentation issues in Leavn - competing sheets, dismissal patterns, binding synchronization, enum-based consolidation
majiayu000/claude-skill-registry 163
-
23-understand-ask-ai-150
[23] UNDERSTAND. Consult external AI models when internal sources are exhausted. Build quality prompts using Prompt150 formula (Context + Query + Method + Style). Use when Loop150 exhausts internal sources, need real-world precedents, confidence <75%, or require reasoning from specialized AI models.
majiayu000/claude-skill-registry 163
-
File Path Traversal Testing
This skill should be used when the user asks to "test for directory traversal", "exploit path traversal vulnerabilities", "read arbitrary files through web applications", "find LFI vulnerabilities", or "access files outside web root". It provides comprehensive file path traversal attack and testing methodologies.
majiayu000/claude-skill-registry 163
-
designing-avalonia-customcontrol-architecture
Defines the basic solution structure for AvaloniaUI Desktop Applications using CustomControl. Use when creating new AvaloniaUI projects or designing stand-alone control styles with ControlTheme.
majiayu000/claude-skill-registry 163
-
agentuity-cli-cloud-secret-pull
Pull secrets from cloud to local .env file. Requires authentication. Use for Agentuity cloud platform operations
majiayu000/claude-skill-registry 163