Claude Skills
MarketplacesSpecificationSubmit
Sign inSign up
© 2026 Claude Skills·Learn more about Agent Skills

Claude Skills

aka. Agent Skills

Discover skills for AI coding agents. Works with Claude Code, OpenAI Codex, Gemini CLI, Cursor, and more.

Claude Code
OpenAI Codex
Gemini CLI
Cursor
GitHub Copilot
+more
1875 MarketplacesSpecification
13225 verified skills
#SkillStars
1721
#1721

spec-kit-skill

verified

GitHub Spec-Kit integration for constitution-based spec-driven development. 7-phase workflow. Triggers: "spec-kit", "speckit", "constitution", "specify", ".specify/", "规格驱动开发", "需求规格".

feiskyer/claude-code-settings
1.2k
1722
#1722

youtube-transcribe-skill

verified

Extract subtitles/transcripts from YouTube videos. Triggers: "youtube transcript", "extract subtitles", "video captions", "视频字幕", "字幕提取", "YouTube转文字", "提取字幕".

feiskyer/claude-code-settings
1.2k
1723
#1723

kiro-skill

verified

Interactive feature development workflow from idea to implementation. Creates requirements (EARS format), design documents, and task lists. Triggers: "kiro", ".kiro/specs/", "feature spec", "需求文档", "设计文档", "实现计划".

feiskyer/claude-code-settings
1.2k
1724
#1724

kiro-skill

verified

Interactive feature development workflow from idea to implementation. Creates requirements (EARS format), design documents, and task lists. Triggers: "kiro", ".kiro/specs/", "feature spec", "需求文档", "设计文档", "实现计划".

feiskyer/claude-code-settings
1.2k
1725
#1725

deep-research

verified

深度调研的多Agent编排工作流:把一个调研目标拆成可并行子目标,用 Claude Code 非交互模式(`claude -p`)运行子进程;联网与采集优先使用已安装的 skills,其次使用 MCP 工具;用脚本聚合子结果并分章精修,最终交付"成品报告文件路径 + 关键结论/建议摘要"。用于:系统性网页/资料调研、竞品/行业分析、批量链接/数据集分片检索、长文写作与证据整合,或用户提及"深度调研/Deep Research/Wide Research/多 Agent 并行调研/多进程调研"等场景。

feiskyer/claude-code-settings
1.2k
1726
#1726

insforge-schema-patterns

verified
database

Database schema patterns for InsForge including social graphs, e-commerce, content publishing, and multi-tenancy with RLS policies. Use when designing data models with relationships, foreign keys, or Row Level Security.

InsForge/InsForge
1.2k
1727
#1727

hera

verified

Hera log detail query toolkit for querying log details by spaceId, storeId, tailName and time range. Use this when you need to query Hera log information programmatically.

XiaoMi/mone
1.2k
1728
#1728

trace

verified

Use when errors occur deep in execution and you need to trace back to find the original trigger - systematically traces bugs backward through call stack, adding instrumentation when needed, to identify source of invalid data or incorrect behavior

udecode/dotai
1.1k
1729
#1729

draft-pr

verified

Use when creating or updating draft pull requests without code review - streamlines draft PR workflow with meaningful descriptions and commit messages, focusing on work-in-progress documentation

udecode/dotai
1.1k
1730
#1730

tdd

verified

Use when implementing complex logic that needs test coverage - write the test first, watch it fail, write minimal code to pass; ensures tests actually verify behavior by requiring failure first; NOT for UI components, simple CRUD, or straightforward code

udecode/dotai
1.1k
1731
#1731

create-pr

verified

Use when creating or updating pull requests with comprehensive descriptions and meaningful commits - streamlines PR workflow with branch management and commit best practices

udecode/dotai
1.1k
1732
#1732

debug

verified

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes - four-phase framework (root cause investigation, pattern analysis, hypothesis testing, implementation) that ensures understanding before attempting solutions

udecode/dotai
1.1k
1733
#1733

learn

verified

Continuous learning system that extracts reusable knowledge from work sessions. Triggers: (1) /learn command to review session learnings, (2) "save this as a skill" or "extract a skill from this", (3) "what did we learn?", (4) After any task involving non-obvious debugging, workarounds, or trial-and-error discovery. Creates new Claude Code skills when valuable, reusable knowledge is identified.

udecode/dotai
1.1k
1734
#1734

review-pr

verified

Use when reviewing pull requests with comprehensive code analysis, incremental or full review options, and constructive feedback - provides thorough code reviews with severity ratings

udecode/dotai
1.1k
1735
#1735

dig

verified

Look up documentation and source code for libraries and packages. Use when the user asks a question about a library, needs to understand a library's API, or when you need information about a library that you don't know about. Triggers on questions like "How do I use X library?", "What's the API for Y?", "Show me how Z library handles this", or when encountering unfamiliar library usage.

udecode/dotai
1.1k
1736
#1736

supabase-postgres-best-practices

verified

Postgres performance optimization and best practices from Supabase. Use this skill when writing, reviewing, or optimizing Postgres queries, schema designs, or database configurations.

supabase/agent-skills
1.1k
1737
#1737

supabase-postgres-best-practices

verified

Postgres performance optimization and best practices from Supabase. Use this skill when writing, reviewing, or optimizing Postgres queries, schema designs, or database configurations.

supabase/agent-skills
1.1k
1738
#1738

osgrep

verified

Semantic code search. Use alongside grep - grep for exact strings, osgrep for concepts.

Ryandonofrio3/osgrep
1.0k
1739
#1739

video-master

verified

视频生成主控 - 自动生成视频场景提示词,支持动态效果、转场、运镜等

huangserva/skill-prompt-generator
987
1740
#1740

eventbridge

verified

AWS EventBridge serverless event bus for event-driven architectures. Use when creating rules, configuring event patterns, setting up scheduled events, integrating with SaaS, or building cross-account event routing.

itsmostafa/aws-agent-skills
986
Previous
Page 87 of 662
Next