help-book-review
Skill61 starsChanged 6 months agoApache-2.0View on GitHub
Show help for the book review pipeline
In this repository15 other files it gives its agents.
- alex-reviewSkill
- book-fixmeSkill
- book-refineSkill
- book-reviewSkill
- clean-circuitsSkill
- code-refineSkill
- code-reviewSkill
- doc-auditSkill
- fv-docsSkill
- fv-preflightSkill
- fv-reviewSkill
- master-fvSkill
- sean-reviewSkill
- spec-fidelity-auditSkill
- tal-reviewSkill
The file
We split this skill into the rules it gives an agent
1 rule. About 0 are common, 1 is distinctive, and 0 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈1
Distinctive · estimate
This author's own choices. Worth a look.
0
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 39
After a review, give feedback in natural language, then:
≈ “Common” is an estimate: at least 1 in 5 of the 372,429 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Print the following help text exactly, then stop. Do not add commentary.
Book Review Pipeline
Three skills, one feedback loop:
/book-review — review any part of the book
/book-refine — improve the review system based on your feedback
/doc-audit — audit book vs. rustdoc surface placement
Reviewing
/book-review review uncommitted changes
/book-review book/src/guide/gadgets/ review a whole section
/book-review book/src/protocol/core/nark.md review a specific chapter
/book-review book/src/protocol/core/nark.md:40-80 focus on specific lines
/book-review book/src/protocol/prelim/bulletproofs.md book/src/protocol/core/nark.md
review multiple files + cross-file consistency
/book-review "accumulation schemes" find and review a topic wherever it appears
/book-review "the transition from preliminaries to core construction"
review a conceptual boundary across chaptersLaunches one parallel agent per policy file in .claude/book-review/. Currently:
grammar, prose, structure, math, formatting. Results are
synthesized and presented as must-fix issues first, then suggestions.
Refining
After a review, give feedback in natural language, then:
/book-refine use feedback from the conversation
/book-refine "stop flagging passive voice in definitions"
/book-refine "I'd write 'the prover' not 'a prover'"
/book-refine "add a reviewer for code example accuracy"This enters plan mode — it reads all policies, generalizes your feedback into
a principle, audits for duplication/contradictions, and shows you the proposed
changes before executing. New policy files are auto-discovered by /book-review.
Policy files
.claude/review-shared/writing.md shared writing rules (grammar + prose reviewers)
.claude/review-shared/math.md shared math notation rules (math reviewer)
.claude/review-shared/surface-placement.md book vs. rustdoc placement policy
.claude/book-review/standards.md master standards (all reviewers)
.claude/book-review/grammar.md book-specific grammar rules
.claude/book-review/prose.md transitions, terminology appendix
.claude/book-review/structure.md organization, flow, progressive disclosure
.claude/book-review/math.md notation, correctness, accessibility
.claude/book-review/formatting.md line width, headings, code blocks
.claude/book-review/formatting-examples.md concrete before/after examplesEdit these directly or let /book-refine manage them.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

