manuscript-engagement-analytics
Analyze nonfiction manuscripts for reader engagement signals, including heading-level word counts, slow starts, long slogs, weak takeaway titles, value pacing, beta-reader comment dropoff, and abandonment risks. Use when auditing a book, guide, manual, course-like draft, or technical manuscript for value density, reader experience, or beta-feedback engagement patterns.
- License 许可
- MIT
- 最近更新
- 2026-11-14
- Stars
- ★ 1.6k
- Forks
- 491
01 前言 Front Matter
- name
- manuscript-engagement-analytics
- license
- MIT
- metadata
- { "tags": "writing,books,nonfiction,analytics,reader-experience", "version": "0.1.0", "category": "Writing", "displayName": "Manuscript Engagement Analytics" }
- description
- Analyze nonfiction manuscripts for reader engagement signals, including heading-level word counts, slow starts, long slogs, weak takeaway titles, value pacing, beta-reader comment dropoff, and abandonment risks. Use when auditing a book, guide, manual, course-like draft, or technical manuscript for value density, reader experience, or beta-feedback engagement patterns.
- compatibility
- Codex, Claude Code, and other Agent Skills-compatible clients.
02 资源文件 7
- 参考文档agents/openai.yaml243 B
- 参考文档references/core/checklist.md2.1 KB
- 参考文档references/core/examples.md2.8 KB
- 参考文档references/core/knowledge.md3.6 KB
- 参考文档references/core/rules.md2.8 KB
- 脚本scripts/analyze_manuscript.py4.7 KB
- 参考文档workflows/audit-engagement.md2.2 KB
03 SKILL.md 正文
Manuscript Engagement Analytics
Core Lens
Reader engagement can be approximated by mapping value over reading time. A manuscript with long stretches between useful payoffs, vague topic headings, or reader-comment dropoff is signaling where readers may get bored, confused, or stuck.
Use this skill to:
- Generate heading-level word-count maps.
- Find slow starts and long slogs.
- Audit whether headings promise reader takeaways.
- Interpret beta-reader comment locations and abandonment.
- Produce a revision queue for value pacing.
Reference Routing
| Need | Read |
|---|---|
| Engagement analytics concepts | references/core/knowledge.md |
| Analysis rules and thresholds | references/core/rules.md |
| Example maps and findings | references/core/examples.md |
| Fast audit checklist | references/core/checklist.md |
| Step-by-step engagement audit | workflows/audit-engagement.md |
Script
Use scripts/analyze_manuscript.py for deterministic Markdown structure analysis:
python3 skills/manuscript-engagement-analytics/scripts/analyze_manuscript.py manuscript.md
It outputs a table of headings, line numbers, word counts, cumulative words, and heuristic flags. Use the script output as evidence, then apply judgment from the references.
Workflow
1. Establish The Reader Promise
Identify the target reader, book promise, and first meaningful payoff. If these are unclear, use book-toc-lab first.
2. Generate A Structure Map
Run the script or manually build a table:
Section | Line | Words | Cumulative words | Reader takeaway | Risk
3. Mark Value Events
Mark where the reader gets:
- A usable idea.
- A decision frame.
- A checklist.
- A worked example.
- A lab or exercise.
- A troubleshooting answer.
4. Diagnose Engagement Risks
Look for:
- Too many words before first payoff.
- Long sections with weak takeaways.
- Back-to-back setup sections.
- Vague headings that hide the reader value.
- Beta-reader comments stopping near the same section.
5. Recommend Revision Actions
Prefer structural fixes:
- Move value earlier.
- Cut or compress low-payoff setup.
- Rename headings around reader outcomes.
- Split long sections.
- Convert theory into examples, checklists, labs, or decisions.
Output Format
When auditing engagement, return:
- Promise and first-payoff diagnosis.
- Value map or script output summary.
- Highest-risk sections.
- Revision recommendations ordered by expected engagement impact.
- Beta-reader comment/dropoff interpretation when data exists.
- Follow-up checks after revision.
Quality Bar
Use metrics as signals, not verdicts. Word counts and comment dropoff show where to inspect; the final recommendation should explain what reader value is missing, delayed, or unclear.
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.