book-to-skill vs SkillForge
Turns any technical book PDF — or folder of sources — into a structured agent skill: mental models in SKILL.md, per-chapter files loaded on demand. Claims 24-51x fewer tokens than context-dumping. — versus — A methodology and toolkit for engineering AI skills instead of improvising them — plus a Context Skill Advisor that proactively recommends, improves or creates skills from what you're doing.
Both fight improvised skills: SkillForge is a methodology for engineering them by hand; book-to-skill automates the pipeline when the knowledge already exists as a book.
| book-to-skill | SkillForge | |
|---|---|---|
| Stars | 18k | 850 |
| Forks | 2.0k | 88 |
| Language | Python | Python |
| License | MIT | MIT |
| Last activity | 2 days ago | 11 days ago |
| Topics | skills | skills |
| Curated connections | 3 | 2 |
book-to-skill — the curator's take
Distillation over summarization is the insight: it extracts frameworks, decision rules and anti-patterns into a skill your agent loads per-question, so the book answers from real content instead of hallucinated recall — and it targets the open Agent Skills standard, not one vendor. When NOT: copyright is on you — a distilled skill of a purchased book is fine on your machine, not in your repo; and distillation quality tracks the source's structure — sprawling books distill poorly.
SkillForge — the curator's take
The 'skills are engineering, not art' manifesto, executed: structured creation process with validation built in, and v5.2's Context Skill Advisor watches your session/project context and suggests the skill you should have — with proactivity levels (off→active) so it advises rather than nags. If you author skills regularly, the rigor pays. NOT a registry or installer (that's the package managers' job) and the advisor's judgment tracks its context quality — garbage project context, garbage suggestions.