agents-best-practices

Editor's pick

Use this skill when designing, generating an MVP blueprint for, auditing, refactoring, or explaining an agentic harness for any domain. Covers provider-neutral agent architecture for OpenAI, Anthropic, and OpenAI-compatible APIs: agent loops, tool design, permissions, system prompts, planning, goals, context compaction, memory, skills, MCP/external connectors, observability, evals, prompt caching, agent-legible environments, feedback loops, and safety.

Type
skill
GitHub stars
★ 2K
Repository
DenisSergeevitch/agents-best-practices
Category
devops

Install

  1. 1Quick install (skills CLI)

    npx skills add DenisSergeevitch/agents-best-practices --skill agents-best-practices --agent claude-code

    Installs agents-best-practices into the current project's .claude/skills/ directory. Requires Node.js and the skills CLI.

  2. 2Manual install

    Create ~/.claude/skills/<name>/ and copy the SKILL.md file from the repository into it. The directory name must match the skill name.

⚠️ Exact file layout and requirements vary by repository — always check the repo README first.

View on GitHub ↗

Prefer the full source? The repository README is the authoritative install reference.