mcpField
M
manuscript-engagement-analytics

manuscript-engagement-analytics

github.com/lvtd-llcDocuments161 installsUpdated 7w ago
Repository

About manuscript-engagement-analytics

Manuscript Engagement Analytics is a skill for locating where a manuscript may lose or confuse readers, using structure, word counts, and reader comments as signals. It combines a deterministic Markdown analysis script with editorial judgment to produce prioritized revision actions.

Key features

  1. 01Map heading-level word counts
  2. 02Flag slow starts and long sections
  3. 03Assess whether headings promise takeaways
  4. 04Interpret beta-reader comments and dropoff
  5. 05Prioritize structural revision actions
  6. 06Analyze Markdown with a script

Use cases

  1. 01Find long stretches before a manuscript's first payoff
  2. 02Identify sections with weak or unclear reader value
  3. 03Use comment patterns to target revisions
  4. 04Build a prioritized engagement audit

Install

Copy the command and run it in a terminal.

$npx skills add https://github.com/lvtd-llc/skills --skill manuscript-engagement-analytics

After installing, type/manuscript-engagement-analyticsin Claude Code to confirm it loaded.

Bundled files

References and scripts installed along with SKILL.md.

agents/
openai.yaml
references/core/
checklist.md
examples.md
knowledge.md
rules.md
scripts/
analyze_manuscript.py
workflows/
audit-engagement.md

Details

From the project README

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

NeedRead
Engagement analytics conceptsreferences/core/knowledge.md
Analysis rules and thresholdsreferences/core/rules.md
Example maps and findingsreferences/core/examples.md
Fast audit checklistreferences/core/checklist.md
Step-by-step engagement auditworkflows/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:

  1. Promise and first-payoff diagnosis.
  2. Value map or script output summary.
  3. Highest-risk sections.
  4. Revision recommendations ordered by expected engagement impact.
  5. Beta-reader comment/dropoff interpretation when data exists.
  6. 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.

Comments

Markdown supported