miles-rl-training
miles-rl-training is a production-ready RL framework optimized for large-scale model post-training, supporting features like FP8 quantization-aware training and train-inference alignment.
★ 0
⑂ 0
Data
Browse data workflow skills for SQL querying, analytics, ETL, and database workflows. Give AI agents access to structured data and pipelines.
This directory brings installable AI Agent skills into one place so you can filter by search, category, topic, and official source, then install them directly into Claude Code, Cursor, Windsurf, and other supported environments.
LIVE
1700
Available Skills
1700 available skills
design-tournament
Design-tournament is a two-phase wisdom of crowds pattern for design work, where multiple independent agents explore a problem in isolation, and independent rankers evaluate and merge findings into a ranked list.
★ 0
⑂ 0
authentication
Authentication is a skill that manages access control, authorization, and secure data exchange for AI agents, enabling protected route middleware and domain-restricted access.
★ 0
⑂ 0
scientific-schematics
Scientific-schematics is a skill that uses AI to generate publication-quality diagrams and schematics for scientific publications and research.
★ 0
⑂ 0
openrouter-research
openrouter-research is a skill that researches current OpenRouter API specifications and Grok model availability for SFUMATO.
★ 0
⑂ 0
sd-review
sd-review is a code analysis skill that combines defect review and refactoring analysis for comprehensive code evaluation
★ 0
⑂ 0
seo-manager
seo-manager is a skill that automates SEO audit orchestration, leveraging GSC data to provide actionable insights and recommendations
★ 0
⑂ 0
bats-testing-patterns
bats-testing-patterns is a skill that offers comprehensive guidance for writing unit tests for shell scripts using Bats, including test patterns, fixtures, and best practices.
★ 0
⑂ 0
bats-testing-patterns
bats-testing-patterns is a comprehensive testing framework for shell scripts, utilizing Bats for automated testing and validation
★ 0
⑂ 0
babysit-pr
babysit-pr is a GitHub PR monitoring tool that persistently tracks pull requests until terminal outcomes occur, such as merge, closure, or the need for user intervention.
★ 0
⑂ 0
figma-analyze
figma-analyze is a skill that analyzes existing Figma components against Nexus conventions, validating design-code parity, token usage, and AI readability.
★ 0
⑂ 0
bats-testing-patterns
bats-testing-patterns is a comprehensive testing framework for shell scripts, providing guidance on test patterns, fixtures, and best practices for production-grade testing.
★ 0
⑂ 0