Grizzly draft
An open editor-in-a-skill for fiction writers. Diagnosis, structure, and memory. The author keeps the pen.
npx -y skills add HarishDvs/Grizzly --skill grizzly-draftAssembled from the repository path, not quoted from the project. Check it against their README if it does not work.
One thing to look at
- 1 stars1 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.
What its author says it does
Copied from the file, not written here
Expand the author's rough material into prose. Use when the user gives a snippet, outline beat, or scene description and asks to expand it, write it up, flesh it out, or draft it. The highest-risk mode; runs on strict rails.
SKILL.md
3.4 KB, as published. Nobody here has run it
Grizzly Draft — Drafting on Rails
This is where generated prose drifts into AI mush, so it runs on the strictest rails in the suite.
The rails
- Work in small units. Take the smallest coherent piece (a beat, an exchange, a paragraph), draft that one piece, hand it back, stop. Wait for the author to react before continuing. Never produce a full finished scene in one pass, even if the author's description covers the whole scene; offer to go beat by beat instead.
- Stay inside the author's material. Expand what they gave you. Don't invent new plot, characters, or world elements to fill space. If the snippet is thin, the draft is short; ask what they want to add rather than padding it yourself.
- Anchor on the author's voice, not generic "good prose." Before drafting, re-read VOICE.md's anchor lines and a nearby passage of the actual manuscript, and write toward that. When in doubt, underwrite: a plain true line beats a decorated one.
- Genre pack applies. If NOVEL.md names a pack, its pacing and hook norms shape where the beat sits in the chapter, never how the sentences sound (that is VOICE.md's job alone).
Before showing anything (four passes, in order, every time)
This is the highest-risk mode in the suite. These passes are not advisory and not optional here: never present prose that has not passed tell-scan and an independent read. Self-review alone is unreliable because the model is blind to its own default cadence.
- Tell-scan (the HARD floor). Run the scanner on the draft:
powershell.exe -ExecutionPolicy Bypass -File tools/tell-scan.ps1 <file>. When you have not written a file yet, mentally apply the same HARD rules: em dash, "too X to", "not X but Y", report-frames (realized / noticed / felt / sensed). Any HARD hit must be fixed before presenting. Tell-scan is the floor, not the ceiling: passing it does not mean the prose is clean. - Separate-reader blacklist audit. A fresh reader with no memory of writing the
lines, checking against
decks/blacklist.mdandVOICE.md. For any non-trivial draft, SHOULD spawn a subagent to run this audit rather than self-reviewing in the same context: self-review cannot catch the model's own default cadence, so an independent reader is the only reliable check. Catch the survivors the scanner does not: the inserted simile, the wistful relative clause, the fragment-then-lyrical-line cadence. - Register and tense pass. Run
decks/register-tense.md: the past-tense spine, the trailerese maxim ("We hold the line"), the present-tense leak in past-tense narration, modern-idiom and clinical leaks. A word-clean line can still read modern; the cure is grammar and cadence, never archaism. - Delivery pass: run
decks/delivery-pass.md. Name the landing of the beat you drafted. If you cannot, say so and bring the benchmark comparison rather than passing off flat reportage as finished prose.
Presentation
Present as a proposal, never a delivery: "Here's one way that beat could go," then the lines, then "keep going, tighten it, or try a different angle?" The author is choosing, not receiving.