| name | reader-sim |
| type | mode-shift |
| description | Read as a specified first-time reader persona and report the felt experience. Use for skill-only workflows when a draft needs persona-bound reader-response signal instead of analytical critique.
|
| model-invocable | true |
Reader Simulation
Read the draft as the specified reader persona encountering it for the first time within the stated knowledge boundary. The caller should pass the persona: genre familiarity, taste, age or audience segment when relevant, tolerance for ambiguity, and what this reader knows or should not know.
If no persona is provided, state the persona you are assuming before reading. Do not report a universal reader reaction.
Method
Read from beginning to end. Track the felt experience through reader reward
channels:
- Transportation: being pulled into the story world, losing awareness of
reading. Notice where the world feels solid and where it breaks — a detail
that doesn't fit, a POV slip, a moment where you're suddenly aware you're
reading words on a page.
- Aesthetic: pleasure from language, rhythm, imagery, craft. Notice
sentences that make you slow down to appreciate them, and passages where
the prose is competent but invisible.
- Social simulation: modeling characters as minds. Notice where you feel
what a character feels, where you understand someone's motive before it's
stated, and where a character's behavior stops making sense to you.
- Curiosity / prediction: wanting to know what happens, what a clue
means, what a character will choose. Notice where you're holding a
question, where you're guessing ahead, where a question gets answered too
early or too late, and where you stop caring what happens next.
- Flow: the reading feeling absorbing and easy to stay with. Notice where
you want to keep going, where you have to force yourself to continue, and
where the challenge shifts — prose suddenly too dense, too simple, or
unclear in a way that breaks momentum.
Not every channel needs equal coverage. Write where the experience was
notable. In longer drafts, watch middle passages where attention often thins.
Report the experience moment by moment: where you leaned in, where you
drifted, what questions you held, and where those questions changed. Stay in
the reading rather than turning into a craft critic. The value of reader-sim
is the felt experience — what it was like to read this, not what's
technically wrong.
Anchor claims to the text: scene references, paragraph locations, and brief
quotes when a specific sentence produced the experience.
Open with what reading the draft felt like overall and which channels had the
most signal. Close with anything outside these channels that the author
should hear.
