chapter-knowledge

Maintains cumulative knowledge files that carry lessons and primitives between textbook chapters.

Updated Sep 13, 2026
One-click install
npx skills add https://github.com/shammun/fluidpy --skill chapter-knowledge-shammun
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: chapter-knowledge
Source: https://github.com/shammun/fluidpy/tree/main/.claude/skills/chapter-knowledge
Command: npx skills add https://github.com/shammun/fluidpy --skill chapter-knowledge-shammun

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve? When building a multi-chapter educational project like fluidpy, each chapter's work risks losing context: notation drifts, pitfalls get rediscovered, and reusable helpers stay buried in old code. This Skill defines a structured knowledge-handoff protocol so every chapter starts smarter than the last. ## Core Features & Use Cases - Chapter-start reading protocol: Specifies the exact order to read knowledge/CUMULATIVE.md, notation.md, viz_patterns.md, concept_map.md, and the previous chapter's file before beginning new work. - Chapter-end writing templates: Provides a nine-section template for knowledge/chNN.md covering teaching spine, implemented items, reusable primitives, pitfalls, conventions, benchmarks, explainers, and feed-forward notes. - Promotion rules: Defines when duplicated JS helpers move into assets/viz_lib.js, when Python helpers move into fluidpy/core, and when lessons graduate into other skills, with required validation commands. - Use Case: After finishing Chapter 2 on Cartesian tensors, an agent writes knowledge/ch02.md, updates CUMULATIVE.md and concept_map.md, and promotes a shared plotting helper into fluidpy/core so Chapter 3 can reuse it. ## Quick Start Load this skill at the start of a new fluidpy chapter and read the knowledge files in the prescribed order before writing any code.

Frequently Asked Questions about chapter-knowledge

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I carry lessons learned between chapters of a coding project?

Write a structured chapter summary file at the end of each chapter covering what worked, new reusable primitives, pitfalls, and feed-forward notes. At the start of the next chapter, read the cumulative summary and previous chapter file before writing any code.

What files does the chapter-knowledge skill maintain?

It maintains knowledge/chNN.md per chapter plus shared files: CUMULATIVE.md, concept_map.md, notation.md, primers.md, viz_patterns.md, and progress.json. Each has a defined schema, such as the concept map's table of concept, book section, code target, and validation label.

When should a helper function be promoted to a shared core module?

Promote a Python helper when it is used by at least two chapters, moving it into fluidpy/core with re-exports from the old location and passing pytest. A JS helper duplicated in two or more explainers moves into assets/viz_lib.js after visual regression checks pass.

How do I keep notation consistent across a multi-chapter textbook project?

Keep a notation table mapping each symbol to its meaning, SI unit, sign convention, chapters, and code name. Add every symbol a chapter's code uses and explicitly flag symbols whose meaning changes between chapters, such as omega for angular frequency versus vorticity.

What are the limitations of a file-based knowledge handoff approach?

It depends on disciplined reading and writing by every agent at chapter boundaries, and files like CUMULATIVE.md must be rewritten and kept within size limits. It does not enforce correctness automatically, so stale or skipped updates can silently degrade later chapters.