✨
AI EngineeringJavaScript

Best Practices

by MoizIbnYousaf

Best Practices is an AI Engineering skill for Claude Code, published by MoizIbnYousaf in Ai-Agent-Skills.

1.1K stars131 forkson MoizIbnYousaf/Ai-Agent-SkillsAdded 2026/08/20Repository updated 2026/08/17
agent-skillsai-agentsclaude-codeclicodexcursordeveloper-toolsmcpproductivity
Install in seconds
Install Best Practices
Copy Best Practices into your Claude Code skills folder. Run the command in your terminal, or review the source on GitHub before installing.
terminal
npx degit https://github.com/MoizIbnYousaf/Ai-Agent-Skills/tree/main/skills/best-practices ~/.claude/skills/best-practices

Requires Node.js. Downloads this skill only — not the rest of the repository — into your Claude Code skills folder.

Without Node.js

git clone https://github.com/MoizIbnYousaf/Ai-Agent-Skills.git

Clones the whole repository, then copy the skill’s own directory into your skills folder yourself.

In this catalog

Source file
skills/best-practices/SKILL.md in MoizIbnYousaf/Ai-Agent-Skills
Installs to
~/.claude/skills/best-practices
Collection
One of 18 skills cataloged from this repository
Category
AI Engineering — 3670 skills

What Best Practices does

Best Practices transforms vague prompts into optimized Claude Code prompts by adding verification, specific context, constraints, and proper phasing. Invoke with /best-practices when you need to improve a prompt.

Best Practices is cataloged under AI Engineering on DirSkills. Best Practices comes from a repository tagged agent-skills, ai-agents, claude-code, cli and codex.

Documentation

README

Best Practices — Prompt Transformer

Transform prompts by adding what Claude needs to succeed.

Start Here

Based on user's request:

User provides a prompt to transform: → Ask using AskUserQuestion:

  • Question: "How should I improve this prompt?"
  • Header: "Mode"
  • Options:
    1. Transform directly — "I'll apply best practices and output an improved version"
    2. Build context first — "I'll gather codebase context and intent analysis first"

User asks to learn/understand: → Show the 5 Transformation Principles section

User asks for examples: → Link to references/before-after-examples.md

User asks to evaluate a prompt: → Use the Success Criteria eval rubric at the end of this document


If "Transform directly"

This is the opening of the README. Read the full README on GitHub.

Frequently asked about Best Practices

  • What else does MoizIbnYousaf publish alongside Best Practices?

    Best Practices is one of 18 skills that DirSkills catalogs from MoizIbnYousaf/Ai-Agent-Skills, the repository it ships in. Its siblings there include Add Upstream Skill, Ask Questions If Underspecified and Audit Library Health. Each one is a separate skill with its own page in this directory, installs the same way Best Practices does, and is maintained by MoizIbnYousaf in that same repository. The rest of the collection is listed on the MoizIbnYousaf/Ai-Agent-Skills page.

  • How does Best Practices compare to other AI Engineering skills?

    Best Practices ranks #1255 by stars among the 3670 AI Engineering skills in this catalog. The most-starred ones next to it are Architecture Decision Records, AI-First Engineering and Agentic OS. DirSkills ranks by the star count of the repository each skill ships in, so that order reflects how popular those repositories are rather than any review of Best Practices against them. Open each page to compare what they document and how they install.

More from MoizIbnYousaf/Ai-Agent-Skills

Best Practices is one of 18 skills cataloged on DirSkills from MoizIbnYousaf/Ai-Agent-Skills.

See all 18 skills →
🔗
2026/08/20

Add Upstream Skill

Add Upstream Skill adds a remote skill entry to the active workspace without copying its source. Use it to keep your library shaped like your own while preserving upstream metadata and choosing shelf, branch, and reason.
AI Engineering
1.1K131
❓
2026/08/20

Ask Questions If Underspecified

Ask Questions If Underspecified prompts an AI agent to pause and ask 1-5 targeted clarifying questions when a request is ambiguous, then confirms assumptions before proceeding so it doesn't start wrong work.
AI Engineering
1.1K131
🩺
2026/08/20

Audit Library Health

Audit Library Health runs validation, doctor, and sync checks on a skills library so it is consistent and ready to share. Use before pushing a library to a shared repo.
Quality
1.1K131
⚙️
2026/08/20

Backend Development

Backend Development provides patterns for designing APIs, database schemas, and backend system architecture. Use it when planning REST endpoints, authentication, caching, rate limiting, and observability.
DevOps
1.1K131
🔍
2026/08/20

Browse And Evaluate

Browse And Evaluate uses the ai-agent-skills CLI to search and inspect skills before installing them. Use it to keep context usage low with --fields and --dry-run.
AI Engineering
1.1K131
📄
2026/08/20

Build Workspace Docs

Build Workspace Docs regenerates README.md and WORK_AREAS.md in a managed AI agent skills library workspace. Use it after adding, cataloging, or curating skills to keep workspace documentation in sync with the skills catalog.
Writing
1.1K131