Explains how code works and why by combining the how and why skills into one plain account.
npx skills add https://github.com/adjohn/pstack --skill teach-adjohn
Please help me install this Agent Skill. Skill: teach Source: https://github.com/adjohn/pstack/tree/main/skills/teach Command: npx skills add https://github.com/adjohn/pstack --skill teach-adjohn
how and why skills in parallel and weaves their findings into one coherent explanation. - Audience-aware depth: Calibrates what to explain based on why the person is asking (about to change it, reviewing it, debugging it, new to it) and what they already know. - Progressive visual teaching: Builds understanding through a series of small diagrams that each add one part, using mermaid for flows and generated whiteboard-style images for spatial ideas. - Use Case: A developer joining a team asks "teach me how the virtualization in this chat UI works" and receives a plain, layered explanation of the rendering and disk-loading mechanisms, why they were built that way, and diagrams that assemble the flow step by step. ## Quick Start Ask the assistant to teach you how a specific subsystem or recent change works and why it was built that way.High-intent search queries and answers about installing and using this skill.
Ask to be taught how the subsystem works. The skill runs the how and why skills to investigate the mechanics and design rationale, then blends the findings into one plain explanation matched to what you already know.
The skill invokes the why skill, which investigates the reasoning behind design decisions using git history and sources. Its confidence hedges are preserved in the explanation since they are findings, not style.
No. The goal is understanding, not change. It reads code to get oriented and delegates investigation to the how and why skills, then delivers only an explanation.
Use it when you need both mechanics and rationale quickly, such as before changing, reviewing, or debugging unfamiliar code. For a tiny change, it may run only one of the underlying skills to match the question's size.
Explanations depend on what the how and why skills can uncover from code, git history, and available sources. Design rationale that was never written down may remain uncertain, which is why confidence hedges are kept intact.
sheer-reyCreate detailed implementation plans for multi-step software work.
JoNaYeonExplain complex code behavior across multiple programming languages.
agentsopeDistill or fuse Skills into execution-ready packages via staged pipelines.
videojsWrites compact Video.js architecture and decision records with non-inferable rationale.