Skip to content
Back to skills

Reviewing Design Docs

ASecurity

Reviews a technical design document or RFC adversarially in a fresh-context read-only subagent (coverage, decisions, edge cases, consistency, risks, citations, scope) and returns findings with a verdict. Use when asked to review a design doc, RFC, or technical design. Not for code diffs; use reviewing-code.

  • 2 stars
  • 0 votes
  • 0 copies
  • 0 views
  • Added October 21, 2026
ai-agents

Security analysis

A100/100

Pro scans all 7 files and shows the line behind each finding

Scanned October 21, 2026

npx -y skills add bostonaholic/skills --skill reviewing-design-docs --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Reviewing Design Docs?

Add the live security badge to your README. It updates with every re-scan.

Security grade badge for Reviewing Design Docs
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/bostonaholic-reviewing-design-docs/badge)](https://www.skillsdirectory.com/skills/bostonaholic-reviewing-design-docs)

More formats (shields.io, HTML) on the badges page. Keep it an A: scan every change in CI with Pro.

Download with Pro
SKILL.md
---
name: reviewing-design-docs
description: 'Reviews a technical design document or RFC adversarially in a fresh-context read-only subagent (coverage, decisions, edge cases, consistency, risks, citations, scope) and returns findings with a verdict. Use when asked to review a design doc, RFC, or technical design. Not for code diffs; use reviewing-code.'
effort: high
argument-hint: "[<design-doc-path-or-url>]"
---

# Engineering Design Doc Review

## Input

`$ARGUMENTS` is the path to one design document. When it is a URL or pasted
text, save it as Markdown in a scratch file outside the repository and
review that path; when a fetch fails, report the URL and the error. When the
argument is empty, names a directory, or names no readable file, ask for the
path and wait. Never guess.

## Reviewer

This session holds the author's conversation, so it cannot review the
document ([independent review rules](shared/independent-review.md)). Run the
[design reviewer brief](references/design-reviewer.md) in a fresh-context
subagent with read and search tools only, giving it the document's absolute
path and the paths of the files the brief links:
[design template](references/design-template.md),
[finding format](shared/findings.md), and
[decision-record rules](shared/decisions.md). Pass no author discussion. If
no such subagent can run, stop and say so. Never review inline.

## Verdict and relay

The report's first line must be exactly `**Verdict: APPROVE**`,
`**Verdict: REQUEST CHANGES**`, or `**Verdict: COMMENT**`. When it is
missing or wrong, run one new reviewer with the same inputs and name the
failed contract. When the second report also fails, print it, name the
failure, and stop. Never repair a verdict yourself.

Print the report verbatim. When the read-only restriction rested on the
reviewer's prompt rather than its tool grants, say so in one line after the
report. Do not revise the document; on REQUEST CHANGES the user decides how.
Write no file beyond the scratch copy.

Files in this skill

  • SKILL.md2 KB
  • agents/openai.yaml223 B
  • references/design-reviewer.md6.1 KB
  • references/design-template.md3.1 KB
  • shared/decisions.md1.3 KB
  • shared/findings.md1.3 KB
  • shared/independent-review.md1.1 KB

Attribution

Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.

Comments

Loading comments…

Newsletter

Get the weekly list of safe new skills, and the ones we pulled.