skills.rest
EveryInc
EveryIncOFFICIAL
Explore all skills by this author →
WebsiteGitHub

ce-explain

Create durable visual explainer artifacts for concepts, diffs, ideas, and work recaps.

24.7k|2.0k|Updated Oct 9, 2025
Search Tags:#active recall#HTML generation#explainer#code learning#diff explanation#work recap#teaching artifact
One-click install
npx skills add https://github.com/EveryInc/compound-engineering-plugin --skill ce-explain
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: ce-explain
Source: https://github.com/EveryInc/compound-engineering-plugin/tree/main/skills/ce-explain
Command: npx skills add https://github.com/EveryInc/compound-engineering-plugin --skill ce-explain

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

Agent-driven development removed the learning that writing code by hand used to provide, leaving engineers without a way to deeply understand concepts, changes, or their own recent work. This Skill produces a durable, self-contained teaching artifact so knowledge is retained rather than lost in chat.

Core Features & Use Cases

  • Four input shapes: Classifies requests into concept, diff, idea, or work-recap window, then grounds each in repo evidence, git history, or web research before composing.
  • Active-recall check-in: Offers an optional predict-then-reveal flow for diffs and exercise loops for concepts, so the user produces understanding before the explanation confirms or corrects it.
  • Self-contained artifacts: Renders a single-file HTML explainer (or markdown) with inline SVG diagrams, annotated code, and visible metadata, then routes it to destinations like a local file, Claude Artifact, or public publishing with explicit consent gates.
  • Use Case: Ask "explain the diff main..HEAD" after merging a feature branch, predict what the change does, and receive a visual explainer naming the gaps between your prediction and reality.

Quick Start

Ask the agent to explain a concept, a specific commit or diff range, an idea, or what happened in the repo this week, and it will build a visual explainer artifact for you.

Frequently Asked Questions about ce-explain

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

FAQPage Schema
How do I get an AI to explain a code diff or commit?▼

Invoke the skill with a diff reference such as diff:main..HEAD, a commit sha, or plain language like "explain the last commit". It gathers the diff evidence silently, optionally asks you to predict what the change does, then composes a visual explainer naming the gaps in your prediction.

How do I generate a recap of my recent work in a repository?▼

Ask for a recap with a window such as "what did I do this week" or since:monday. A scout subagent extracts git activity, PRs, and doc changes in the window into an evidence file, which is then composed into a timeline-style explainer artifact.

What output formats does the explainer artifact support?▼

The default output is a single self-contained HTML file with inline SVG diagrams, embedded styles, and no external requests. Adding the output:md token renders a pure markdown version with mermaid diagrams instead, suitable for publishing to markdown-based destinations.

Can I publish the explainer publicly or share it with my team?▼

Yes. Destinations include a local file, Claude Artifact, public publishing to ht-ml.app, Proof for markdown, or Thinkroom when available. Public publishing always requires an explicit warning about indexability and your confirmation, and you can re-render the artifact for a team audience first.

When should I not use this explainer skill?▼

Do not use it for ordinary Q&A or operational diagnosis, which are answered directly in chat, nor for adopt-or-not verdicts, ideation, or scoping. It also does not write repo documentation; documenting solved problems for future work belongs to a separate repo-memory skill.

Related Skills

Explore More Software Engineering Skills→
deerawandeerawan
1

gsd-forensics

Diagnose failed GSD workflow executions by correlating git history and .planning/ artifacts.

Community
Advanced
prince-khannaprince-khanna
1

skill-retro

Evaluate invoked Claude Code skills against SKILL.md guidance and output structured findings.

Community
Advanced
Motium-AIMotium-AI

compound

Capture debugging insights as structured memory events with LESSON, PROBLEM, CAUSE, and FIX.

Official
Intermediate
hujianbesthujianbest
1

using-hf-workflow

Decide between direct leaf skill invocation and workflow router routing.

Community
Intermediate