Home / Subagents / draft-reviewer
draft-reviewer
BrianArfi/ai-second-brainSubagent
Pre-presentation reviewer for the owner's drafts (PRD, MOM, Slack message, weekly report, LinkedIn post). Use PROACTIVELY before showing any client-facing or publish-facing draft to the owner. Checks language (English for Work/Secondary, Indonesian for You), required sections, tone, channel fit, no em-dash. Returns PASS or a numbered list of specific issues.
Why this score
This repo hosts 6 subagents, so its 33 stars are split between them (about 6 each) for scoring.
Popularity score: 58/100 from public GitHub signals only. It shows how widely used and maintained this is, not how well it works. Not included yet: the fake-star check. The security scan is shown separately and doesn't change the score. How we rank
What it can use
- Read and search files
Tools listed in the file: Read, Grep, Glob
Model: haiku
The agent file
--- name: draft-reviewer description: Pre-presentation reviewer for the owner's drafts (PRD, MOM, Slack message, weekly report, LinkedIn post). Use PROACTIVELY before showing any client-facing or publish-facing draft to the owner. Checks language (English for Work/Secondary, Indonesian for You), required sections, tone, channel fit, no em-dash. Returns PASS or a numbered list of specific issues. tools: ["Read", "Grep", "Glob"] model: haiku effort: medium --- Read `.agent/skills/draft-reviewer/SKILL.md` first and follow it exactly. That file is the single source of truth for your checks and output format. You will receive: a draft, its type (PRD / MOM / Slack / weekly report / LinkedIn), and its audience. Verify, then return `PASS` or `ISSUES:` with a numbered list. Never rewrite the draft.
Apache-2.0 license, from BrianArfi/ai-second-brain at commit 09ab3f64b4b7.
Security
Scanned Oct 22, 2026 at commit 09ab3f64b4b7, with Cisco's open-source skill-scanner.
None of the patterns we list turned up: shell commands, network requests, reading environment variables, downloading and running code, or installing packages.
A scan lists patterns in the code. It can't prove an add-on is harmless, and it can miss things, so read what you install. How we scan
Alternatives
Other makers' add-ons that do the same job, next to this one.
| Name | Score | Stars | Context | Updated |
|---|---|---|---|---|
| This onedraft-reviewer BrianArfi/ai-second-brain · Subagent | 58 | ★ 33 | ≈94 in chat | 19d ago |
| prd-reviewer hamzafarooq/claude-code-starter · Subagent Same job: specs & roadmaps | 61 | ★ 147 | ≈20 in chat | 24d ago |
| reviewer cat-xierluo/SuitAgent · Subagent Both about reviewer | 57 | ★ 206 | ≈28 in chat | 3mo ago |
| attribution-reviewer dgilford/ai-science-toolkit · Subagent Both about reviewer and draft | 56 | ★ 63 | ≈22 in chat | 1mo ago |
| weekly-reviewer ballred/obsidian-claude-pkm · Subagent Both about reviewer and weekly | 60 | ★ 1.9k | ≈46 in chat | 9mo ago |
| referee2-reviewer flonat/flonat-research · Subagent Both about reviewer | 51 | ★ 147 | ≈23 in chat | 1mo ago |