Agents Best Practices
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.
Install on your platform
We auto-selected Claude Code based on this skill’s supported platforms.
Run in terminal (recommended)
claude mcp add agents-best-practices npx -- -y @trustedskills/agents-best-practices
Or manually add to ~/.claude/settings.json
{
"mcpServers": {
"agents-best-practices": {
"command": "npx",
"args": [
"-y",
"@trustedskills/agents-best-practices"
]
}
}
}Requires Claude Code (claude CLI). Run claude --version to verify your install.
About This Skill
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.
Tags
TrustedSkills Verification
Unlike other registries that point to live repositories, TrustedSkills pins every skill to a verified commit hash. This protects you from malicious updates — what you install today is exactly what was reviewed and verified.
Security Audits
| Gen Agent Trust Hub | Pass |
| Socket | Pass |
| Snyk | Pass |
Details
- Version
- v1.0.0
- License
- MIT
- Author
- DenisSergeevitch
- Installs
- 0
- Updated
- May 15, 2026
- Published
- May 15, 2026
🔓 Unverified
Not yet reviewed. Use with caution.