debugging-strategies
sangrokjung
Master systematic debugging techniques, profiling tools, and root cause analysis to efficiently track down bugs across any codebase or technology stack. Use when investi…
CodingClaude Code
822GitHub
OPENAGENTSKILL / DIRECTORY
AI Agent Skills
Find a skill for your next task. Explore tools for Codex, Claude Code, Cursor and more.
Browse all public registry entries, one page at a time. Counts include resources; MCP-only resources are omitted from displayed skills. Listing is not a safety or compatibility guarantee.
Full directory
Page 86 · 16 shown · 2,825 public entries
More filters · 1
Results: 2825
eval-harness
sangrokjung
Formal evaluation framework for Claude Code sessions implementing eval-driven development (EDD) principles
CodingClaude Code
822GitHub
extract-errors
sangrokjung
Use when adding new error messages to React, or seeing "unknown error code" warnings.
CodingClaude Code
822GitHub
frontend-code-review
sangrokjung
Trigger when the user requests a review of frontend files (e.g., `.tsx`, `.ts`, `.js`). Support both pending-change reviews and focused file reviews while applying the c…
CodingClaude Code
822GitHub
Codex Workflows
shinpr
Controlled, reviewable agentic coding workflows for OpenAI Codex CLI with task-specific subagents, explicit planning, TDD, and quality gates.
28GitHub
creating-skills
AgentWorkforce
Use when creating new Claude Code skills or improving existing ones - ensures skills are discoverable, scannable, and effective through proper structure, CSO optimizatio…
CodingClaude Code
813GitHub
review-fix-signoff-loop
AgentWorkforce
Use when writing Agent Relay or Ricky workflows that must loop review, fix, and validation with fresh agent context until independent signoff agents, typically Claude an…
813GitHub
working-with-dbt-mesh
dbt-labs
Use when changing a dbt model in a way that could break its consumers — renaming, removing, or retyping a column, or changing a model that downstream models, exposures,…
CodingClaude Code
701GitHub
925GitHub
api-tester
laolaoshiren
依据真实 OpenAPI、路由实现和现有测试生成并验证 API 测试。用于用户要求测试接口、补集成测试、验证 API 契约、生成回归用例或排查接口兼容性时；区分“生成测试”和“执行请求”的授权，不猜测状态码、响应结构或 SLA，不在未确认环境中发送写请求。
CodingClaude Code
812GitHub
skill-curator
laolaoshiren
中文 Skill 收录评估器。用于核验 GitHub 上的 Claude Code、Codex、Agent Skills、Plugin、MCP、CLI 或 Agent 工作流是否值得加入精选列表；检查真实资产、安装方式、活跃度、重复项和安全边界，并生成分类、中文描述与可追溯证据。
812GitHub
test-generator
laolaoshiren
依据真实代码契约生成并验证单元测试或集成测试。用于用户要求为函数、类、接口或缺陷补测试、提高覆盖率、生成回归用例或完善测试策略时；先读取现有测试与调用方，不猜测空值、异常或超时行为，不自动安装框架或访问生产依赖。
CodingClaude Code
812GitHub
812GitHub
A/B Test Validation
PramodDutta
Validating A/B test implementations including traffic splitting accuracy, statistical significance calculation, metric tracking, and experiment cleanup.
CodingClaude Code
215GitHub
godot-audio-systems
thedivergentai
Expert patterns for Godot audio including AudioStreamPlayer variants (2D positional, 3D spatial), AudioBus mixing architecture, dynamic effects (reverb, EQ,compression),…
CodingClaude Code
659GitHub
Claude Code Spinner Verbs
wynandw87
2,500+ curated spinner verbs and spinner phrases for Claude Code across 98 themed categories
65GitHub
External platform skills
Browse external directory →Owner-curated external sources. Not filtered by the scores or compatibility controls above; excluded from GitHub rankings and automatic installation.
RedSkill · 流白Livo · 1.0.0
p5.js animations: rain, branches & swallows →
Describe a rain curtain, growing flowering branches or a flock of swallows. This RedSkill package adapts three p5.js templates into sketch.js code with custom colors, density and speed.
Noncommercial use only · Local runtime recording · Use on the source platform