🤖
AI Engineering

Agents Best Practices

by DenisSergeevitch

Agents Best Practices is an AI Engineering skill for Claude Code, published by DenisSergeevitch in agents-best-practices.

2.2K stars198 forkson DenisSergeevitch/agents-best-practicesAdded 2026/08/18Repository updated 2026/08/10
View source on GitHubDownload repo ZIP
agent-skillagent-skillsagentic-workflowsagentsai-agentsanthropicclaudeclaude-codecodexcodex-skillmcpprompt-engineering
Install in seconds
Install Agents Best Practices
Copy Agents 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/DenisSergeevitch/agents-best-practices ~/.claude/skills/agents-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/DenisSergeevitch/agents-best-practices.git

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

In this catalog

Source file
SKILL.md in DenisSergeevitch/agents-best-practices
Installs to
~/.claude/skills/agents-best-practices
Collection
The only skill cataloged from this repository
Category
AI Engineering — 2451 skills

What Agents Best Practices does

Agents Best Practices provides a provider-neutral framework for designing, building, auditing, and refining agentic harnesses across domains. Use it when creating MVP agent blueprints, tool permissions, context/memory, observability, evals, and safety controls for OpenAI, Anthropic, or compatible APIs.

Agents Best Practices is cataloged under AI Engineering on DirSkills. Agents Best Practices comes from a repository tagged agent-skill, agent-skills, agentic-workflows, agents and ai-agents.

Documentation

README

Agents Best Practices

Use this skill when the user asks how to build, improve, debug, or evaluate an agentic harness. This is a general-purpose agent architecture skill. Coding agents are one subdomain only; apply the same principles to research, finance, legal, support, operations, sales, healthcare, education, data analysis, procurement, and workflow automation agents.

Core stance

An agent harness is the control plane around a model. The model proposes actions; the harness validates, authorizes, executes, records, summarizes, and returns observations. Keep the loop simple and make the runtime rigorous.

Default architecture:

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

Frequently asked about Agents Best Practices

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

    Agents Best Practices ranks #840 by stars among the 2451 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 Agents Best Practices against them. Open each page to compare what they document and how they install.

More AI Engineering skills

Agents Best Practices is one of 2451 AI Engineering skills cataloged on DirSkills, ranked #840 by stars among them.

Browse all AI Engineering skills →
📐
3w ago

Architecture Decision Records

Architecture Decision Records captures architectural decisions made during Claude Code sessions as structured ADRs, recording context, alternatives, and rationale. Use it when significant technical choices are made so future developers understand why the codebase is shaped the way it is.
AI Engineering
239.8K36.4K
🤖
3w ago

AI-First Engineering

AI-First Engineering defines process, review, and architecture standards for teams where AI agents produce most implementation output. Use it to set ownership rules, quality gates, and evaluation criteria for agent-generated code.
AI Engineering
239.8K36.4K
🤖
3w ago

Agentic OS

Agentic OS codifies a persistent multi-agent operating system architecture for Claude Code. Use it when building a multi-agent workflow with file-based memory, slash commands, and scheduled automation that survives session restarts.
AI Engineering
239.8K36.4K