First Reader: An Open-Source Agent Skill That Simulates Reader Reactions to Your Draft
100% Open Source. Runs fully offline with zero dependencies.
There are 100+ anti-AI-slop skills out there. Every one of them checks your writing for the usual tells and flags the words you're not supposed to use. And none of them can tell you whether a real person would keep reading.
First Reader simulates two people going through your draft one passage at a time, and reports how they felt. What caught them, what didn't make sense, what they skipped, and the one thing they'd still remember the next day.
A third reader just skims it and tells you whether they'd have opened it at all.
You point your agent at a draft and say who it's for: "review this, the audience is backend engineers who've seen ten launches this month"
A few minutes later you get the read back in plain language, plus a page that lays your draft out with each reader's comments sitting next to the passage they reacted to. You see where each one leaned in or bailed, what stuck with them afterward, and a strip along the side that tracks how their attention climbed and dropped through the piece.
What makes it different from those 100+ skills:
• Readers get your draft one passage at a time, at human reading speed, so someone who bails at passage four genuinely never saw passage five
• When they tell you what they remember, it's from their own notes, not a second pass over your text
• They only report what happened to them and what would've kept them reading
After the run you keep asking. "Ask S what would have kept her past passage 4" and she answers from her own notes, in her own words. Revise the draft, say "again," and the same readers read it fresh, with the old attention strip sitting above the new one so you can see what moved.
The skill tries to tell you what your writing actually does to the person on the other end.
Link to the GitHub repo in the comments.
First Reader is a free, open-source agent skill that runs offline with no external dependencies. It prompts an AI agent to process a draft in sequential chunks, generating simulated reader-style feedback for each passage — noting what stood out, what was confusing, and what was skipped. A third simulated reader gives a quick skim-level reaction on whether they'd continue reading.
Users specify an intended audience (e.g., "backend engineers who've seen ten launches this month"), and the tool returns feedback in plain language alongside a layout showing comments next to the relevant passage, plus a visual indicator of attention across the piece.
The tool supports follow-up prompts referencing the earlier simulated feedback, and can re-run the same personas against a revised draft for comparison.
Source code is available via a linked GitHub repository (link posted in comments).