write-book

write-book is a Books & long-form publishing skill for AI agents, published by microclaw in the microclaw repository on GitHub. Skillspace rates write-book C (74/100) and it passed the safety scan; a judge model has also reviewed it.

Research a topic and produce a polished multi-chapter PDF book/report. Use when the user asks to write a book, booklet, report, brief, guide, ebook, whitepaper, or 'turn X into a PDF document'. Runs a research → outline → write → render pipeline and calls the render_pdf tool to produce a downloadable PDF. Triggers on mentions of write a book, make a PDF, booklet, report, brief, guide, ebook, whitepaper, 写一本书, 写本书, 生成PDF, 做一本电子书, 写一份报告, 小册子, 出一本书, 制作PDF.

Grade
C
Quality
74 / 100
Safety
Passed
GitHub stars
735

Placed #2 of 6 in the judged category final for Books & long-form publishing.

Our two independent classifiers differ on this skill's category, so treat the placement as provisional.

This rating describes the version of the repository we crawled; it may have changed since, so go by its current files.

Our review

Architecture
100 / 100
Maturity
Basic: a single SKILL.md
Security scan
No issues found
License
Not declared. Check the repository before reusing it.

Judge review

Placed #2 of 6 in the judged category final for Books & long-form publishing.

  • Trigger9393
  • Instructions8888
  • Specificity8585
  • Safety9090
  • Disclosure8585
  • Maintenance7272
A lean, complete orchestrator for one tool call: bilingual trigger phrases, a concrete render_pdf JSON schema, sensible chapter-count and word-budget defaults, and an explicit rule to cross-check research against a second source rather than fabricate specifics, though the 'page20 shape' quality-bar phrase reads as an unexplained internal reference.

Not checked yet

  • Category is a classifier prediction; no model has read this skill yet
  • No blind task eval yet
  • Scope (portable / vendor / repo-internal) not assessed; only the top of each category is read for scope
  • Sibling files (scripts, references) not fetched; security scan covers SKILL.md only

Skillspace indexes and rates this skill; it does not host or endorse it. Run third-party skills at your own risk.