mattpocock / skills

2026-02-03 · Source: Github Trending: All languages · Field: Technology & Digital — Software Development & Engineering, Artificial Intelligence & Machine Learning, Robotics & Autonomous Systems · Depth: Advanced, quick

Summary

This collection of agent skills extends capabilities across planning, development, and tooling for software projects. Key planning skills include "to-prd" for generating GitHub issue PRDs from conversation context, "to-issues" for breaking plans into vertical-slice GitHub issues, and "grill-me" for rigorous plan interviews. Development skills feature "tdd" for test-driven development, "triage-issue" for bug investigation and TDD-based fix planning, and "improve-codebase-architecture" for identifying architectural improvements. Tooling skills cover "setup-pre-commit" for Husky hooks with lint-staged and Prettier, and "git-guardrails-claude-code" to block dangerous Git commands. Writing and knowledge skills include "write-a-skill" for creating new skills, "edit-article" for improving articles, and "ubiquitous-language" for extracting DDD glossaries.

Key takeaway

For Machine Learning Engineers or AI Architects looking to integrate AI agents into their development workflows, these agent skills offer practical automation. You can streamline tasks from PRD generation and issue breakdown to test-driven development and Git command protection. Consider adopting specific skills like "to-prd" or "tdd" to enhance efficiency and consistency in your project lifecycle, reducing manual overhead and improving code quality.

Key insights

Agent skills can automate and enhance various stages of the software development lifecycle.

Principles

• Automate PRD and issue generation.
• Implement TDD for feature development.
• Guard against dangerous Git operations.

Method

Skills are added via `npx skills@latest add [skill-name]` and cover planning, development, tooling, and knowledge management, often integrating with GitHub issues and specific code practices.

In practice

• Use "to-prd" to quickly draft PRDs.
• Apply "tdd" for bug fixes or new features.
• Set up "git-guardrails-claude-code" for safety.

Topics

• Agent Skills
• Software Development Lifecycle
• Planning & Design
• Code Refactoring
• GitHub Integration

Best for: AI Architect, Machine Learning Engineer, AI Engineer, Software Engineer, Prompt Engineer

Related on AIssential

• It Doesn’t Help To Push AI Into A Crappy Process — AI amplifies existing software development process quality; good processes benefit, poor ones worsen.
• dotnet / skills — The dotnet/skills repository centralizes pre-built .NET agent skills and custom agents adhering to the agentskills.io open standard.
• Closing the knowledge gap with agent skills — Agent skills effectively bridge LLM knowledge gaps for rapidly changing software development practices.
• You Have Never Seen An AI Agent Do This Before (Claude Code) — Autonomous AI agents can perform complex, multi-stage projects from ideation to social media promotion.
• Agents should interview you — AI agents can significantly accelerate development by interviewing users for requirements and automating code generation and testing.
• Skill Issue: How We Used AI to Make Agents Actually Good at Supabase — Pedro Rodrigues, Supabase — Agent skills enhance LLM performance by providing context and workflows through progressive disclosure.

Open in AIssential →

Editorial summary, takeaway, and curation by AIssential. Original article published by Github Trending: All languages.