flow-next-impl-review
gmickel
Carmack-level implementation review of changes via the configured backend. Use when asked to review code or a diff in a flow-next repo.
CodingClaude Code
691GitHub
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 89 · 15 shown · 2,825 public entries
More filters · 1
Results: 2825
ClaudeCode_GodMode On
cubetribe
Self-orchestrating multi-agent system for Claude Code — you say WHAT, the AI decides HOW. v7.1: 15 AI agents, Smart Routing, parallel quality gates, skills architecture,…
41GitHub
FinSight
RUC-NLPIR
[ACL 2026 Main] FinSight: Towards Real-World Financial Deep Research. 🎯One ticker, one click, one publication-ready report.
CodingReview before use
220GitHub
Agent Skills
gohypergiant
A collection of skills for AI coding agents. Skills are packaged instructions and scripts that extend agent capabilities.
21GitHub
806GitHub
keqian-method
staruhub
胥克谦式AI-Native产品开发方法论。适用于：(1) 使用AI Agent（Claude Code、Codex、Cursor等）进行产品级软件开发，(2) 设计和优化Harness/Skill体系，(3) 文档驱动开发(SDD)流程，(4) 构建自动化质量门禁和eval机制，(5) Token成本优化与缓存策略，(6) 产品人转型开…
707GitHub
threejs-performance
staruhub
Three.js 性能优化指南。当 Three.js/React Three Fiber 项目出现掉帧、内存增长、加载缓慢、绘制调用过多，或需要迁移 WebGPU、实现大规模粒子/实例化渲染、配置资源压缩管线时使用。触发关键词："Three.js 优化"、"WebGPU"、"draw calls"、"内存泄漏"、"TSL"、"Insta…
CodingClaude Code
707GitHub
214GitHub
skillgrade-graders
mgechev
Authors deterministic and LLM rubric graders for skillgrade evaluations. Use when creating scoring scripts, writing evaluation rubrics, or combining multiple graders wit…
CodingClaude Code
696GitHub
skillgrade-setup
mgechev
Sets up and runs skillgrade evaluation pipelines for Agent Skills. Use when initializing eval configurations, running trials, reviewing results, or integrating with CI.…
CodingClaude Code
696GitHub
code-reviewer
zhnnky329
Detect whether approved modeling code is Python or MATLAB/Beita Tianyuan and route it to the matching reviewer using the compact named-check review contract.
CodingClaude Code
695GitHub
matlab-model-code-generator
zhnnky329
Generate and run minimal reproducible MATLAB or Beita Tianyuan compatible code for the human-approved main method and usable baseline, with compact experiment artifacts…
CodingClaude Code
695GitHub
python-model-code-generator
zhnnky329
Generate and run minimal reproducible Python modeling code for the human-approved main method and usable baseline, saving compact experiment artifacts and a canonical ru…
CodingClaude Code
695GitHub
flow-next-export-context
gmickel
Export RepoPrompt context to a markdown file for review with an external LLM (ChatGPT, Claude web, etc.). Use when you want Carmack-level review but prefer an external m…
692GitHub
Codex Agent Team
youngfor-shoot
Codex Skill for choosing and coordinating the smallest safe Agent setup.
14GitHub
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