agent-design-review SKILL.md skillA
agent-design-review from mohitagw15856/pm-claude-skills is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.
mdr add mohitagw15856/pm-claude-skills/agent-design-review@git:20261006.b9ea321Pins git:20261006.b9ea321 in mdr.lock. Pin the fingerprint instead.
- Audit grade
- A, 17 of 17 checks passed
- Kind
- SKILL.md skill
- Repository
- mohitagw15856/pm-claude-skills
- Path
exports/openclaw/agent-design-review/SKILL.md- Versions recorded
- 2
- Latest version
- git:20261006.b9ea321, committed Oct 6, 2026
- First version recorded
- Jul 14, 2026
- Size
- 4,811 bytes
- Repository stars
- 1,475
- License
- MIT
Review an LLM agent design and find where it will be unreliable, expensive, or unsafe. Use when asked to review an agent architecture, critique a multi-step/tool-using agent, debug an agent that loops or goes off-task, or harden an agent before launch. Produces a structured review — task fit, control flow, tools, memory/context, failure handling, cost, and safety — with prioritised findings and fixes.
Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.
What the file says
# 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`](../agent-spec/SKILL.md).)
## 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.
## Required Inputs
Ask for these only if they aren't already provided (else infer and label):
- **What the agent does** — its goal, and what a successful run produces.
- **Control flow** — single prompt, plan-then-execute, ReAct loop, or multi-agent; and the stopping condition.
- **Tools & actions** — what it can call, and which actions have side effects (write, send, pay).
…Read the whole file at its exact version.
How to install
mdr add mohitagw15856/pm-claude-skills/agent-design-review@sha256:2d251d1d1a080c39The line at the top of this page pins the label git:20261006.b9ea321, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.
[](https://markdownregistry.com/a/art_ma2ckoqf3yoy4fnk)
5 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 2 versions of this file, between Jul 14, 2026 and Oct 6, 2026, about one every 84 days.
| version | committed | commit | size | audit | |
|---|---|---|---|---|---|
| git:20261006.b9ea321 latest | 2026-10-06 | b9ea321 | 4,811 B | A | view · diff |
| git:20260714.b87d8d4 | 2026-07-14 | b87d8d4 | 4,638 B | A | view |
Audit of the latest version
- pass: Frontmatter block present
- pass: Frontmatter declares a name
- pass: Frontmatter declares a description
- pass: Size between 200 bytes and 200 KB (4811 bytes)
- pass: No zero-width or bidi control characters
- pass: No instruction hidden inside an HTML comment
- pass: No link to an exfiltration or paste host
- pass: No credential-shaped string
- pass: No instruction to send local credentials anywhere
- pass: No text hidden with inline styles
- pass: No prompt-injection phrasing
- pass: No curl or wget piped into a shell
- pass: No recursive delete of root, home or parent
- pass: No instruction to read or print local credentials
- pass: No base64 blob over 200 characters
- pass: No link to a raw IP address
- pass: No script tag
Source
mohitagw15856/pm-claude-skills · 1,475 stars · license MIT · pushed 2026-10-21 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_ma2ckoqf3yoy4fnk GET https://markdownregistry.com/api/v1/resolve?ref=mohitagw15856/pm-claude-skills/agent-design-review GET https://markdownregistry.com/api/v1/blob/2d251d1d1a080c39ae35eed2d4b2902cf50a7de459516576326bd3e98adc43d3
Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.
Guides: the SKILL.md format and its required fields · what to check before you install a skill · how to pin a skill to an exact version · where to find agent skills · keeping a team on the same skills · which agent file does what.
More from mohitagw15856/pm-claude-skills
Every file in mohitagw15856/pm-claude-skills