/reader-sim
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.
$ npx -y skills add haowjy/creative-writing-skills --skill reader-sim --agent claude-codeHow it fires
How this skill gets triggered: by you, by Claude, or both.
- Fires itselfAuto-invocation. Claude auto-loads it when your prompt matches the work.Auto-invocation is when the right skill fires by itself at the right moment, driven by a FLOW.md router and a hook, instead of you invoking it by name. It is the difference between a skill being installed and a skill actually getting used.Read the full definition →
- You can call itInvoke it directly when you want it.
- Slash command
/reader-sim
Context preview
The summary Claude sees to decide when to auto-load this skill.
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.
SKILL.md
reader-sim.SKILL.mdname: 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.
Read more
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.
Write novels, short stories, and serial fiction with AI that maintains your voice, tracks your continuity, and gets better the more you use it.
Other skills on creative-writing-skills.
- /character-sim
Speak as a specified character from their current knowledge, voice, and emotional state. Use for skill-only workflows that need in-character conversation, voice discovery, or relationship pressure tests.
Open skill - /creative-research
Load when a story needs factual grounding the writer doesn't have: historical detail, cultural texture, domain accuracy, or how other authors handled similar material. Pass the question and story context; returns a sourced report the writer can draw from.
Open skill - /creative-writing-craft
Craft references for writing fiction well: prose, scenes, style, voice, and genre/page-level technique. Load when a writer, critic, or muse needs how-to-write guidance rather than a production mode.
Open skill - /creative-writing-modes
Creative-writing addendum to /llm-writing. Load when putting prose on the page: draft, revise, bridge, vary, or polish.
Open skill - /creative-writing-muse
Load when no subagents are available and one agent must plan, draft, critique, research, and capture memory by switching stances.
Open skill - /grill-with-docs
Use when challenging a plan — grills the author against documented decisions and sharpens terminology.
Open skill

