← ClaudeAtlas

ck-teachlisted

Explain a body of code, a system, or an analysis workflow plainly by combining ck-how's implementation tracing with ck-why's investigation of rationale. Use when the user asks to learn or understand a change, subsystem, or workflow.
Wang-Cankun/cankun-skills · ★ 2 · AI & Automation · score 78
Install: claude install-skill Wang-Cankun/cankun-skills
# CK Teach Explain what a thing is, how it works, and why it took its current shape in one plain account. The goal is understanding. Match the user's language, background, and requested depth. ## Gather the explanation's evidence This skill composes `ck-how` and `ck-why`. Load their instructions from the available skill catalog or the sibling `ck-how/SKILL.md` and `ck-why/SKILL.md` directories. They own the investigation; use their findings rather than duplicating the work. If a companion is unavailable, say which investigation is limited and use the evidence you can inspect without claiming that skill ran. 1. Identify what the reader needs to understand from why they are asking: onboarding, reviewing, debugging, changing a workflow, or interpreting an output. Infer existing knowledge from the conversation instead of quizzing them. Put depth where their question is. 2. Orient briefly in the files or supplied material. Use `ck-how` for the mechanism and `ck-why` for the motivation. Scope each investigation to the actual question. A narrow mechanism question may need only `ck-how`; a rationale question may need only `ck-why` after the behavior is established. 3. Run independent investigations in parallel when the host supports it and the work benefits. Otherwise follow the needed companion workflows sequentially yourself. Inherit the current model and settings unless instructed otherwise. If earlier session decisions matter, an available history tool such as `obelisk` can s