Claude Skill

DenisSergeevitch/agents-best-practices

A provider-neutral Claude Skill that encodes best practices for designing agentic workflows in Codex, Claude Code, and agentic harnesses. Reusable patterns for reliable AI agents.

Overview

Stars2,078
Forks186
LanguageUnknown
Last pushed2026-06-29
Last synced2026-07-03
View on GitHub

Repository

OwnerDenisSergeevitch
Repositoryagents-best-practices
Full nameDenisSergeevitch/agents-best-practices
Repo ID1,240,191,065

Install this Skill

npx skills add DenisSergeevitch/agents-best-practices -g

Registry

Typemcp_server
Quality score70/100
Verificationreadme_parsed
Last verified2026-06-02
Platforms
ClaudeMCPCodex
Capabilities
memorysearchimageworkflowagent-skillagent-skillsagentic-workflowsagentsai-agentsanthropic
Detected files
README.mdSKILL.md
Install methods
  • npx skills add DenisSergeevitch/agents-best-practices -g
  • git clone https://github.com/DenisSergeevitch/agents-best-practices.git \

Summary

A provider-neutral Claude Skill that encodes best practices for designing agentic workflows in Codex, Claude Code, and similar agentic harnesses. It offers reusable patterns and guidelines to build more reliable, maintainable AI agents.

Chinese description

面向 Codex、Claude Code 及代理化工具设计的供应商无关型 Agent 技能(Claude Skill)。

Key features

  • Provider-neutral design works with Codex, Claude Code, and other agentic harnesses
  • Encodes proven best practices for agentic workflow architecture
  • Reusable patterns for building reliable AI agents
  • Focuses on maintainability and robustness of agent behaviors

Use cases

  • Designing agentic workflows in Claude Code or Codex
  • Improving reliability of existing AI agent implementations
  • Learning best practices for agentic harness design
  • Standardizing agent behavior across different tools

README excerpt

<div align="center"> # agents-best-practices <img src="icon.jpeg" alt="agents-best-practices icon" width="300" /> > *"The model proposes actions; the harness validates, authorizes, executes, records, and returns observations."* [![License: MIT](https://img.shields.io/badge/License-MIT-yellow.svg)](LICENSE) [![Agent Skill](https://img.shields.io/badge/Agent-Skill-7c3aed)](SKILL.md) [![Codex](https://img.shields.io/badge/Codex-compatible-111827)](SKILL.md) [![Claude Code](https://img.shields.io/badge/Claude_Code-compatible-8b5cf6)](SKILL.md) <br> **A provider-neutral Agent Skill for designing, generating MVP blueprints for, auditing, refactoring, and explaining agentic harnesses.** It applies beyond coding agents: research, support, operations, sales, finance, data analysis, procurement, legal workflows, healthcare workflows, education, and workflow automation agents all need the same core runtime discipline. <br> **Install** - pick one: </div> **A. With [`skills`](https://github.com/vercel-labs/skills) (any compatible agent):** ```bash npx skills add DenisSergeevitch/agents-best-practices -g ``` The `-g` flag installs globally at user level so every project can discover it. **B. Or paste this prompt to your AI agent:** ```text Install the agents-best-practices skill for me: 1. Clone https://github.com/DenisSergeevitch/agents-best-practices into my user-level skills directory as `agents-best-practices/`. Use the skill directory my agent reads on this machine, for example: - Codex: ~/.codex/skills/ - Claude Code: ~/.claude/skills/ 2. Verify that SKILL.md, icon.jpeg, and the references/ directory are present. 3. Confirm the install path when done. ``` **C. Manual install paths:** ```bash # Codex mkdir -p "${CODEX_HOME:-$HOME/.codex}/skills" git

Topics

Explore more

Data from GitHub. Synced on 2026-07-03