fn-walk

Generates section-by-section code walkthroughs with annotated snippets and invariant explanations.

1|Updated Sep 3, 2017
One-click install
npx skills add https://github.com/mmgeorge/config --skill fn-walk-mmgeorge
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: fn-walk
Source: https://github.com/mmgeorge/config/tree/main/rulesync-global/.rulesync/skills/fn-walk
Command: npx skills add https://github.com/mmgeorge/config --skill fn-walk-mmgeorge

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve? Understanding a complex function's implementation requires tracing its phases, invariants, and error paths manually, which is slow and error-prone. This Skill produces a structured, phase-by-phase walkthrough of any target function with annotated code and consequence explanations. ## Core Features & Use Cases - Pre-Investigation Workflow: Locates the target entity with semantic tools, inspects callers via impact analysis, and maps execution into 3-5 discrete architectural phases. - Structured Response Format: Delivers a problem-first summary, numbered architectural sections with annotated code snippets, and a dedicated atomicity and error isolation analysis. - Use Case: When onboarding onto an unfamiliar codebase, ask for a walkthrough of a critical function like SessionStore::reconcile to receive a phase-by-phase breakdown covering preflight validation, atomic mutation, and rollback guarantees. ## Quick Start Ask the AI to walk through a specific function step by step, for example by saying "walk through this code" or invoking /fn-walk on the target function.

Frequently Asked Questions about fn-walk

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

FAQPage Schema
How do I get a detailed walkthrough of a function?▼

Invoke the walkthrough by asking to "walk through this code" or using /fn-walk on a target function. The Skill locates the entity, inspects its callers, and produces a phase-by-phase breakdown with annotated code snippets.

What does a code walkthrough include?▼

Each walkthrough contains a problem-first summary naming the target function, numbered architectural sections with context sentences and annotated code, and a final atomicity and error isolation analysis covering rollback guarantees.

How does the walkthrough handle error paths and invariants?▼

The Skill dedicates a section to atomicity and error isolation, detailing preflight validation safety, partial mutation reachability, and rollback guarantees. In-line comments explain non-obvious invariants rather than restating syntax.

When should I use a walkthrough instead of reading the code directly?▼

Use it when a function spans multiple architectural phases or has subtle invariants that are hard to trace manually. It is less useful for trivial single-purpose helpers where the source is self-explanatory.