ai-agent-skills
Structured workflows for planning, testing, securing, and shipping code
All Skills in This Repository (31)
Pure Emerald Level Indicatorsmeeting-notes-to-tasks
Convert meeting notes into action items with owners and due dates.
idea-to-spec
Transform informal project ideas into structured, testable specifications.
debugging-methodology
Guide hypothesis-driven debugging to identify root causes with reproducible tests.
documentation
Generate architectural decision records, code-level documentation, and operational runbooks.
error-handling
Develop error handling strategies with retry logic and structured responses.
test-driven-development
Enforce Test-Driven Development by writing tests before implementation.
code-explanation
Generate structured explanations of code functionality, design patterns, and safety considerations.
think-before-coding
Plan coding tasks by articulating goals, assumptions, and constraints before implementation.
goal-driven-execution
Convert imperative instructions into verifiable goals with testable success criteria.
simplicity-first
Enforce minimum viable code to prevent overengineering in software development.
hallucination-prevention
Detect and mitigate factual inaccuracies in AI-generated outputs.
git-workflow
Enforce trunk-based development with atomic commits and conventional commit messages.
Frequently Asked Questions
FAQPage SchemaHow to install AI Agent Skills?โผ
Run `npx skills add DevelopersGlobal/ai-agent-skills --all -g -y` in your terminal to install all skills globally.
What problems do these skills solve?โผ
They stop agents from guessing, overengineering, skipping tests, and shipping insecure code by enforcing step-by-step workflows with verification checkpoints.
Do these skills work with Claude Code and Cursor?โผ
Yes. Every skill follows the standard SKILL.md format and works with Claude Code, Cursor, Gemini CLI, Copilot, and other compatible agents.
Can non-developers use these skills?โผ
Yes. Everyday skills like meeting-notes-to-tasks and research-and-summarize help anyone turn notes and research into clear, actionable output.
How do the skills prevent AI hallucinations?โผ
Dedicated skills like hallucination-prevention and ai-output-validation require grounding, schema checks, and verification before any generated output is trusted.
Related Repositories in Software Engineering
View All in Software Engineeringโopenclaw
Run a personal AI assistant across your devices and chat apps
superpowers
Gives coding agents a disciplined workflow from idea to merged code
react
AI agent skills for building, testing, and porting React core