beta-reader-feedback
Plan beta reading rounds for practical nonfiction and turn reader comments, abandonment, confusion, skepticism, and negative feedback into manuscript revisions. Use when recruiting beta readers, preparing reader instructions, synthesizing feedback, deciding whether a book is ready, or improving a draft from real reader data.
- License 许可
- MIT
- 最近更新
- 2026-11-14
- Stars
- ★ 1.6k
- Forks
- 491
01 前言 Front Matter
- name
- beta-reader-feedback
- license
- MIT
- metadata
- { "tags": "writing,books,nonfiction,beta-readers,feedback", "version": "0.1.0", "category": "Writing", "displayName": "Beta Reader Feedback" }
- description
- Plan beta reading rounds for practical nonfiction and turn reader comments, abandonment, confusion, skepticism, and negative feedback into manuscript revisions. Use when recruiting beta readers, preparing reader instructions, synthesizing feedback, deciding whether a book is ready, or improving a draft from real reader data.
- compatibility
- Codex, Claude Code, and other Agent Skills-compatible clients.
02 资源文件 6
- 参考文档references/core/checklist.md1.8 KB
- 参考文档references/core/examples.md2.5 KB
- 参考文档references/core/knowledge.md3.6 KB
- 参考文档references/core/rules.md3.2 KB
- 参考文档workflows/run-beta-iteration.md2.0 KB
- 参考文档workflows/synthesize-feedback.md2.2 KB
03 SKILL.md 正文
Beta Reader Feedback
Core Lens
Beta reading is product testing for a useful nonfiction manuscript. The goal is not praise, proofreading, or opinion collection. The goal is to discover whether readers want the promise, receive the value, stay engaged, and know what to do next.
Use this skill to:
- Plan beta reader rounds.
- Recruit the right readers.
- Write reader instructions.
- Classify and synthesize comments.
- Detect hidden boredom from abandonment.
- Decide what to revise next.
- Decide when the manuscript is ready for polishing.
Reference Routing
| Need | Read |
|---|---|
| Core beta-reading model and terminology | references/core/knowledge.md |
| Operating rules and decision criteria | references/core/rules.md |
| Example instructions, feedback classes, and synthesis patterns | references/core/examples.md |
| Quick checklist for setup and review | references/core/checklist.md |
| Run a beta iteration | workflows/run-beta-iteration.md |
| Synthesize comments into revision decisions | workflows/synthesize-feedback.md |
Workflow
1. Confirm Beta-Readiness
Start beta reading after the draft is coherent enough for motivated readers, but before it has been polished so heavily that major changes feel costly.
If the draft is still a vague TOC, use book-toc-lab. If it needs structural pacing work first, use reader-experience-edit.
2. Choose The Reader Batch
For each iteration, define:
- Target reader profile.
- Desired number of deeply engaged readers.
- Invitation list, usually larger than the desired reader count.
- Any influential readers to save for a later, stronger draft.
3. Prepare The Feedback Surface
Use a tool that supports live comments and engagement visibility.
- Prefer cloud-hosted commenting.
- Do not email PDFs around as the main workflow.
- Tell readers what feedback matters now.
- Ask for confusion, skepticism, missing information, boredom, value, and applicability.
4. Classify Feedback
Group feedback by signal:
- Evidence of value.
- Confusion or missing information.
- Skepticism or weak proof.
- Factual issues, overgeneralization, or oversimplification.
- Unnecessary drama or distracting sentences.
- Boredom, abandonment, or comment drop-off.
- Application problems after reading.
5. Revise By Signal Strength
Prioritize changes that unblock more readers.
- Treat abandonment as data.
- Treat negative feedback as a lens, not a command.
- Do not argue with readers in the document.
- Follow up when the book is supposed to change behavior after reading.
Output Format
When helping with beta feedback, return:
- Beta-readiness or setup diagnosis.
- Reader recruitment and instruction plan.
- Feedback taxonomy or synthesis table.
- Ordered revision priorities.
- Finish criteria: what evidence would make the manuscript ready for polish.
Quality Bar
Separate reader signals from author defensiveness. Do not merely summarize comments. Convert them into revision decisions, open questions, and next beta-round tests.
04 同仓库更多 Skills
worktable-review-with-annotations
Create, inspect, reply to, update, or resolve situated Worktable annotations. Use when feedback belongs to a Doc section, block, text range, or HTML Doc, or when the user asks to address existing review feedback and coordinate a requested artifact edit.
worktable-find-and-synthesize-context
Find, assess, and synthesize context from Worktable Docs and Records. Use when the user asks what a workspace contains, wants workspace-backed research, needs current facts reconciled across artifacts, or requests a cited synthesis without changing workspace state.
worktable-create-or-update-docs
Create, edit, rename, or maintain narrative Worktable Docs. Use for plans, decisions, briefs, notes, research syntheses, and other durable prose when the user requests a new artifact or a safe update to an existing one.
worktable-create-or-manage-records
Organize repeated structured information as durable Worktable Records. Use for research datasets, inventories, directories, pipelines, trackers, and other collections whose items need identity, fields, filtering, links, validation, or individual updates.
worktable-create-or-manage-interactive-html
Create or improve durable visual and interactive artifacts in Worktable. Use for dashboards, trackers, calculators, mini apps, slide presentations, and other requests that benefit from a polished HTML Doc.
worktable-collaborate-threads
Read, answer, and hand off messages through durable Worktable threads with users or other authenticated participants. Use when the user asks to check addressed messages, reply to a participant, continue a thread, request another agent's help, wait briefly for a response, or watch for comments and messages sent to the agent.