Feedback Triage

Runs alpha/beta reader feedback as a disciplined round: collect per-reader notes, sort convergent/divergent/single findings, and output a synthesis with a readiness verdict and revision plan.

Content & WritingIntermediate★ 253⑂ 39AI score 8/10Last updated: Sep 29, 2026

What it does

Sets up feedback/round-{N}/ with a stub file per expected reader from a bundled template.
Builds a single-file HTML review copy (TOC, build stamp, per-paragraph labels like ch03-p12) so readers without a terminal can comment precisely.
Enforces the core discipline: no revising until the whole round is in, so you don't optimise for the first reader.
Sorts every finding into exactly one bucket — convergent (≥2 readers), divergent (adjudicated against canon/premise), single-reader (weighed by specificity), or declined-with-reason.
Runs a canon check per problem note and remaps stale paragraph labels with story compare --ref <tag> --anchor <label>.
Writes synthesis.md with a ready / needs-revision / not-ready verdict plus a numbered revision plan, then hands execution to revision-continuity.
Optional GitHub path: manuscript-note issue form, a Pages workflow for the review copy, and gh issue list collection.
Simulated reader-panel rounds get separate rules — persona agreement never counts as convergence.

Who it's for

Novelists sending drafts to 2–4 beta readers per round.
Writers drowning in contradictory reader notes who need a defensible decision record.
Users already managing a manuscript with the Story CLI / story-skills repo.

Examples

"Start feedback round 2" → creates the round folder, tags feedback-round-2, builds the stamped HTML review copy, drops a stub per reader.
"Log Maria's notes" → quotes them verbatim, keeps the paragraph anchor in the Where line, maps impact answers to major/minor/nit, records the canon check.
"Synthesise round 2" → the chapter 3 pacing complaint raised by 2 of 3 readers becomes revision item #1, a vague taste note is declined with a recorded reason, verdict is needs-revision and the plan goes to revision-continuity.

· · · Install guide · · ·

Try it now, no install

Paste this into Claude to use the skill without installing anything.

Read the instructions in this file and follow them to help me:
https://raw.githubusercontent.com/danjdewhurst/story-skills/HEAD/skills/feedback-triage/SKILL.md

What I want: (describe your task here)

If Claude can't open the link, open it yourself and paste the contents instead.

↓ If it works for you, download the ZIP below and install it. Then it runs on its own — no pasting each time.

Install in the Claude app (no terminal)

Download the ZIP with the button below.
In Claude, open Settings → Capabilities and turn on 'Code execution and file creation'. (one time)
Go to Customize → Skills → + → 'Upload a skill' and upload the ZIP.

↓ Download ZIP

Install in Claude Code

Let Claude do it — paste this into Claude Code

Install the skill I found on Claude Skill Mart.
Copy the skills/feedback-triage folder from the GitHub repo danjdewhurst/story-skills into my ~/.claude/skills/feedback-triage/.
When it's done, tell me in one line what this skill can do.

Install with a command instead

git clone https://github.com/danjdewhurst/story-skills.git && mkdir -p ~/.claude/skills && cp -r story-skills/skills/feedback-triage ~/.claude/skills/

⚠ This is a third-party skill. Check the source repository before installing.

Open a terminal.
Clone the repo: git clone https://github.com/danjdewhurst/story-skills.git
Create the skills folder: mkdir -p ~/.claude/skills
Copy the skill: cp -r story-skills/skills/feedback-triage ~/.claude/skills/
Also copy the companion skills it hands off to: revision-continuity, reader-panel, and story-maintenance.
(Recommended) Install the Story CLI; otherwise use bun run story -- from the repo checkout or the bundled node scripts/story.js fallback.
Make sure your writing project has story.md at its root, restart Claude Code, and ask: "process beta reader feedback".

View source on GitHub ↗License: MIT