StackMap
Subscribe

book-to-skill vs skill-recorder

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 — Desktop app that records a real work session — clicks, apps, pages, narration — and uses Copilot CLI to reconstruct intent + steps, then generates a reusable SKILL.md or scheduled Automation.

The curated verdict

The third source in the skills-from-knowledge triangle: book-to-skill from what experts wrote, skill-recorder from what you actually did.

book-to-skillskill-recorder
Stars18k2.5k
Forks2.0k267
LanguagePythonTypeScript
LicenseMITMIT
Last activity2 days ago2 days ago
Topicsskillsskills
Curated connections32

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.

skill-recorder — the curator's take

Demonstration beats description: recording yourself doing a task once captures the tacit steps you'd never think to write down, and generalizing to native tools (gh, web_fetch) instead of replaying clicks is the right call. When NOT: it requires GitHub Copilot access and its Automation output targets Microsoft's agent surfaces (Scout, Cowork, Copilot Studio) — the SKILL.md is portable, the rest of the pipeline isn't; screen recording means trusting local capture with everything on screen.