book-reader-conversations
Plan and synthesize pre-draft reader conversations for useful nonfiction books, including listening interviews, teaching calls, reader-language capture, promise validation, scope refinement, and TOC testing. Use when validating a practical book idea, finding target readers, preparing interview prompts, testing a table of contents, or turning reader conversations into book decisions.
- License 许可
- MIT
- 最近更新
- 2026-11-14
- Stars
- ★ 1.6k
- Forks
- 491
01 前言 Front Matter
- name
- book-reader-conversations
- license
- MIT
- metadata
- { "tags": "writing,books,nonfiction,reader-research,interviews", "version": "0.1.0", "category": "Writing", "displayName": "Book Reader Conversations" }
- description
- Plan and synthesize pre-draft reader conversations for useful nonfiction books, including listening interviews, teaching calls, reader-language capture, promise validation, scope refinement, and TOC testing. Use when validating a practical book idea, finding target readers, preparing interview prompts, testing a table of contents, or turning reader conversations into book decisions.
- compatibility
- Codex, Claude Code, and other Agent Skills-compatible clients.
02 资源文件 6
- 参考文档agents/openai.yaml216 B
- 参考文档references/core/checklist.md1.9 KB
- 参考文档references/core/examples.md3.2 KB
- 参考文档references/core/knowledge.md3.8 KB
- 参考文档references/core/rules.md3.1 KB
- 参考文档workflows/run-reader-conversations.md2.4 KB
03 SKILL.md 正文
Book Reader Conversations
Core Lens
Reader conversations are product discovery for useful nonfiction. The goal is not to ask whether people like a book idea. The goal is to understand the reader's real situation, language, failed attempts, urgency, objections, and ability to receive the value the book intends to deliver.
Use this skill before or during drafting to:
- Validate a book promise before writing too much prose.
- Escape the author's curse of knowledge.
- Find the strongest reader profile and use case.
- Test a takeaway-first TOC by teaching from it.
- Turn conversations into scope, structure, examples, and beta-reader leads.
Reference Routing
| Need | Read |
|---|---|
| Core model and terminology | references/core/knowledge.md |
| Interview and synthesis rules | references/core/rules.md |
| Example prompts and synthesis patterns | references/core/examples.md |
| Fast setup and review checklist | references/core/checklist.md |
| Run a conversation round | workflows/run-reader-conversations.md |
Workflow
1. Define The Learning Goal
Choose one primary question for this round:
- Is the reader problem real and urgent?
- Which reader profile cares most?
- What does the reader already know or believe?
- Which promise is easiest to understand and recommend?
- Does the TOC sequence help the reader receive value?
Do not mix early listening with pitching unless the user is explicitly running a teaching conversation.
2. Recruit Readers Who Match The Hypothesis
Start with friendly first contacts, existing readers, community members, customers, students, or people already trying to solve the problem.
Avoid cold outreach unless no warm path exists. If nobody relevant will talk, treat that as a scope or access problem rather than a scheduling problem.
3. Run The Right Conversation Type
Use two modes:
- Listening conversation: explore lived experience, language, urgency, alternatives, and obstacles.
- Teaching conversation: help the reader through one slice of the TOC and watch where they get value, confusion, skepticism, or missing steps.
4. Synthesize Into Book Decisions
After each batch, update:
- Reader profile and exclusions.
- Promise wording and reader language.
- TOC order, section titles, and missing steps.
- Proof, examples, objections, and caveats.
- Potential beta readers, testimonials, or launch allies.
5. Decide The Next Test
Recommend one of:
- More listening with a sharper reader segment.
- Teaching a high-value chapter or section.
- Revising the TOC with
book-toc-lab. - Drafting enough for
reader-experience-editorbeta-reader-feedback.
Output Format
When helping with reader conversations, return:
- Learning goal and target reader hypothesis.
- Recruiting list or outreach plan.
- Conversation guide with prompts.
- Note-taking schema.
- Synthesis table: signal, evidence, implication, book decision.
- Next test or manuscript action.
Quality Bar
Keep the conversation about the reader's life before the author's idea. Prefer observed behavior, concrete stories, and exact reader language over opinions, compliments, or predictions.
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.