Agent Design Review

Agent Design Review is an AI Engineering skill for Claude Code, published by mohitagw15856 in pm-claude-skills.

1.3K stars231 forkson mohitagw15856/pm-claude-skillsAdded 2026/08/20Repository updated 2026/08/19

agent-skillsagentsai-agentsai-toolsanthropicchatgptclaudeclaude-codeclaude-skillscursordeveloper-toolsgeminillmmcpmcp-serverproduct-managementproductivityprompt-engineeringpromptsskills

Install in seconds

Install Agent Design Review

Copy Agent Design Review 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/mohitagw15856/pm-claude-skills/tree/main/skills/agent-design-review ~/.claude/skills/agent-design-review

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/mohitagw15856/pm-claude-skills.git

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

In this catalog

Source file: skills/agent-design-review/SKILL.md in mohitagw15856/pm-claude-skills
Installs to: ~/.claude/skills/agent-design-review
Collection: One of 25 skills cataloged from this repository
Category: AI Engineering — 2451 skills

What Agent Design Review does

Agent Design Review evaluates an LLM agent architecture to find where it will be unreliable, expensive, or unsafe, and gives prioritized fixes. Use it when reviewing agent designs, debugging loops, or hardening an agent before launch.

Agent Design Review is cataloged under AI Engineering on DirSkills. Agent Design Review comes from a repository tagged agent-skills, agents, ai-agents, ai-tools and anthropic.

Documentation

README

Excerpt

Agent Design Review Skill

Most agents don't fail because the model is weak — they fail because the design lets them loop, call the wrong tool, lose the thread across steps, or burn tokens with no stopping rule. This skill reviews an agent's architecture against the decisions that actually determine reliability, and ranks the fixes — so "it works in the demo but not in prod" becomes a specific list of changes. (Writing a new agent spec? Use agent-spec.)

Working from a brief

Given a sketch ("a research agent that searches, reads, and writes a report"), deliver the full review anyway — infer the likely control flow and tools, label the inference, and flag what to confirm. Never withhold the review for missing detail.

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

Frequently asked about Agent Design Review

What else does mohitagw15856 publish alongside Agent Design Review?
Agent Design Review is one of 25 skills that DirSkills catalogs from mohitagw15856/pm-claude-skills, the repository it ships in. Its siblings there include 360 Feedback Template, 401k Plan Decoder and A/B Test Planner. Each one is a separate skill with its own page in this directory, installs the same way Agent Design Review does, and is maintained by mohitagw15856 in that same repository. The rest of the collection is listed on the mohitagw15856/pm-claude-skills page.
How does Agent Design Review compare to other AI Engineering skills?
Agent Design Review ranks #1111 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 Agent Design Review against them. Open each page to compare what they document and how they install.