Goal
SkillDev toolsRead, criticize, and propose improvements for a table of content of a book
Available today. Use it from your connected AI after setup.
No other account needed.
Connect ahel once, and every AI you use reads what you have installed.
Then ask your AI: use the Goal skill
What this skill tells your AI
The instructions your AI receives, as published by causify-ai/helpers in .claude/skills/book.criticize_toc/SKILL.md and read by ahel’s review.
- Review and criticize the table of content for a chapter (or set of chapters) in a book
- Identify mistakes and improvement opportunities, focusing on factual errors, rather than style suggestions
- Propose concrete, ranked improvements to topics, ordering, scope, and audience fit
Workflow
Step 1: Read the Material
-
Read
.claude/templates/book_map.template.mdfor the expected structure of a table of content of a book -
Read the
book_map.mdthat stores the### Topicsmaking up the table of content for the book- Read
**Title**,**Target audience**at the top ofbook_map.md - Read the
# Partheading description the chapter belongs to - Read the target chapter's
### Topicsthat the user refers to - Ignore the rest of the sections besides
### Topics- I.e.,
### Lessons,### Tutorials,### Related packages,### Related books,### Related papers
- I.e.,
- Read the
### Topicsin the sibling chapters in that Part and the immediate neighbors, chapter N-1 and N+1, to judge continuity
- Read
Step 2: Criticize
-
Read
.claude/skills/text.criticize/SKILL.mdto understand general approaches to review and criticize text -
Evaluate along these axes, reporting only issues you are confident about:
- Internal flow:
- Order of the
### Topicsbullets - Prerequisite ordering
- Redundant or overlapping bullets
- A bullet that is really two topics
- Order of the
- Cross-chapter flow:
- Overlap with neighbors or others in the same Part
- A topic that belongs earlier or later
- Forward references to concepts not yet introduced
- Part fit:
- Does the chapter match the scope description of its
# Part(foundations vs. advanced theory vs. deployment) - Flag misplaced chapters
- Does the chapter match the scope description of its
- Structure conformance:
- Compare the structure to
.claude/templates/book_map.template.md - Report:
- Parts that don't follow the subsections
- Lessons without a FULL/PART/WEAK tag
- References not following
.claude/skills/references.rules.md
- Compare the structure to
- Audience fit:
- Matches the stated audience
- Level too high or low
- Assumed background
- Unexplained jargon
- Scope and balance:
- Too much or too little content for one chapter
- Candidates to split or merge
- Internal flow:
-
Rank each issue by severity:
- CRITICAL: breaks the chapter's logic or misplaces it
- HIGH: misleads or confuses the reader
- MEDIUM: hurts clarity or completeness
- LOW: minor polish
Step 3: Write Result
- Write results using the same format and file as in
## Step 4: Write the Resultsin.claude/skills/text.criticize/SKILL.md
Step 4: Wait for Approval
- Present the criticism to the user
- Wait for the user to select items to apply by index and give corrections
- Only then edit
map.md - Make sure to update all the sections (e.g., Topics, Lessons, Tutorials, Related packages, Related books, Related papers)
Signals
- GitHub stars
- 145
- Forks
- 159
- Last commit
- Sep 2026
Advanced
- Catalog kind
- skill
- Gateway key
book-criticize-toc- Source
- github.com/causify-ai/helpers