book-sft-pipeline
book-sft-pipeline is a Books & long-form publishing skill for AI agents, published by muratcankoylan in the Agent-Skills-for-Context-Engineering repository on GitHub. Skillspace rates book-sft-pipeline C (76/100) and it passed the safety scan; a judge model has also reviewed it.
This skill should be used for book-to-SFT pipelines: ePub extraction, literary segmentation, author-voice dataset construction, style-transfer training, LoRA workflows, and model evaluation for voice replication.
- Grade
- C
- Quality
- 76 / 100
- Safety
- Passed
- GitHub stars
- 17,968
Placed #6 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
- 91 / 100
- Maturity
- Structured: ships references or scripts
- Security scan
- No issues found
- License
- Not declared. Check the repository before reusing it.
Judge review
Placed #6 of 6 in the judged category final for Books & long-form publishing.
- Trigger
75 75 - Instructions
68 68 - Specificity
68 68 - Safety
55 55 - Disclosure
55 55 - Maintenance
55 55
Real technical instincts, like sourcing ePub over PDF to avoid learning OCR errors, 150-400 word chunks at paragraph boundaries, and 15+ prompt templates to prevent overfitting, are undercut by an extraction snippet built on an 'epub2' API that doesn't match any well-known Python ePub library, and the skill never addresses the copyright question inherent in training a voice-clone model on literary works.
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.