Agent Design

by nimadorostkar

Agent Design is an AI Engineering skill for Claude Code, published by nimadorostkar in Claude-Skills-collection.

18 stars2 forkson nimadorostkar/Claude-Skills-collectionAdded 2026/07/16+13% in starsRepository updated 2026/07/14

View source on GitHub Download repo ZIP

aiclaudeclaude-skillsskills

Install in seconds

Install Agent Design

Copy Agent Design 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/nimadorostkar/Claude-Skills-collection/tree/main/skills/ai/agent-design ~/.claude/skills/agent-design

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/nimadorostkar/Claude-Skills-collection.git

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

In this catalog

Source file: skills/ai/agent-design/SKILL.md in nimadorostkar/Claude-Skills-collection
Installs to: ~/.claude/skills/agent-design
Collection: One of 50 skills cataloged from this repository
Category: AI Engineering — 3670 skills

What Agent Design does

Provides patterns for designing reliable LLM agents with tool use, including loop termination, error handling, human checkpoints, and recognizing when an agent isn't needed.

Agent Design is cataloged under AI Engineering on DirSkills. Agent Design comes from a repository tagged ai, claude, claude-skills and skills.

Documentation

README

Excerpt

Build LLM agents that complete tasks reliably and fail safely. The two failure modes that define bad agents are looping forever without progress, and taking a destructive action confidently and wrongly.

When to Use

Building an agent that uses tools to accomplish multi-step tasks.
An agent that loops, stalls, or takes wrong actions.
Designing the tool surface an agent will use.
Deciding whether an agent is warranted at all.

Capabilities

Tool design: granularity, naming, descriptions, and error returns.
The agent loop: planning, acting, observing, and terminating.
Error recovery and retry.
Human-in-the-loop checkpoints for irreversible actions.
Guardrails: budgets, timeouts, and permission boundaries.

Inputs

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

Frequently asked about Agent Design

What else does nimadorostkar publish alongside Agent Design?
Agent Design is one of 50 skills that DirSkills catalogs from nimadorostkar/Claude-Skills-collection, the repository it ships in. Its siblings there include API Design, Agent Instructions and Agent Memory. Each one is a separate skill with its own page in this directory, installs the same way Agent Design does, and is maintained by nimadorostkar in that same repository. The rest of the collection is listed on the nimadorostkar/Claude-Skills-collection page.
How does Agent Design compare to other AI Engineering skills?
Agent Design ranks #3587 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 Agent Design against them. Open each page to compare what they document and how they install.