explain · sammcj — Claude Code skill: what it does, how to install
Explains code, systems, and algorithms using terminal ASCII diagrams or standalone interactive HTML step-through pages.
Apache-2.0 ★ 173 updated 2026-10-24
npx skills add sammcj/agentic-coding --skill explain -a claude-codeWhat explain does
This skill prioritizes visual structure over long text responses. In standard terminal mode, the agent draws a vertical ASCII diagram limited to 80 columns, followed by concise technical captions. When inspecting project files, it checks the source code first and supplies direct references formatted as path:line.
Prepending the argument with html prompts the skill to generate a self-contained page inside .explain/<kebab-slug>.html with bundled CSS and JavaScript. For sequential processes or protocols, it constructs an interactive viewer with scene controls tied to arrow keys and buttons. Generated files stay uncommitted because the skill silently adds .explain/ to Git's private info/exclude file instead of editing .gitignore.
Without an integrated browser tool, the agent cannot take screenshots to test contrast or layout bugs on the initial 1200x800 screen, and it explicitly reports that visual checks were skipped.
What it helps with
- render ASCII architecture diagrams directly inside terminal output
- build standalone interactive HTML pages with step-by-step playback
- inspect implementation details linked to exact
path:linelocations - keep visual documentation untracked without editing
.gitignore
Example prompts for the agent
- /explain queue processing architecture in worker.ts
- /explain html incoming request lifecycle through middleware
- /explain
How to install explain
1Skills CLI (Vercel)
npx skills add sammcj/agentic-coding --skill explain -a claude-code2Manually: put the files in place
~/.claude/skills/explain/SKILL.mdCopy the whole skill folder; for one project use .claude/skills/explain/
1Skills CLI (Vercel)
npx skills add sammcj/agentic-coding --skill explain -a codex2Manually: put the files in place
.agents/skills/explain/SKILL.mdFor all projects use ~/.agents/skills/
1Skills CLI (Vercel)
npx skills add sammcj/agentic-coding --skill explain -a cursor2Manually: put the files in place
.cursor/skills/explain/SKILL.mdCursor also reads .agents/skills/ and .claude/skills/
1GitHub CLI
gh skill install sammcj/agentic-coding Skills/explain/SKILL.md2Manually: put the files in place
.github/skills/explain/SKILL.md1Skills CLI (Vercel)
npx skills add sammcj/agentic-coding --skill explain -a gemini-cli2Platform CLI
gemini skills install https://github.com/sammcj/agentic-coding --path Skills/explainManually: put the files in place
.devin/skills/explain/SKILL.mdThe legacy .windsurf/skills/ path still works
Claude.ai
Zip the folder and upload it in Settings → Capabilities → Skills
Step by step, with commands for each platform: How to install skills in Claude Code: five ways
Questions about explain
How to install explain in Claude Code?
Run npx skills add sammcj/agentic-coding --skill explain -a claude-code. Alternatively, copy the skill definition directly into ~/.claude/skills/explain/SKILL.md.
What is the difference between terminal and HTML modes?
Terminal mode outputs an ASCII diagram up to 80 columns wide with numbered captions directly in the chat. The html mode writes an interactive page featuring inline SVG or Mermaid, step controls, and light/dark theme support.
Where does the skill save generated HTML pages?
Pages are saved to .explain/<kebab-slug>.html. The skill automatically appends .explain/ to $(git rev-parse --git-path info/exclude) so your Git status stays clean without touching .gitignore.
Source text
SKILL.md · Apache-2.0
--- name: explain description: Explain a concept, system or piece of code as a diagram-first terminal answer, or as an interactive HTML page. disable-model-invocation: true argument-hint: "[html] <topic>" compatibility: claude-code metadata: version: 2026-10-05 --- Arguments: `$ARGUMENTS`. If the first word is `html` use HTML mode, unless otherwise instructed use terminal mode. The rest is the topic. With no topic, explain what the conversation is currently about. ## Both modes - Show the real mechanism: the actual components, data flow and state changes, with real names, shapes and numbers. A labelled box saying "processing" explains nothing. - Picture first, prose second. Prose is short captions keyed to the picture. - Captions follow Simplified Technical English: max 20 words per step, 25 per description, active voice, one idea per sentence, plain words with one meaning. Keep code and identifiers verbatim. - For code in the current project, read it first and cite `path:line`. ## Terminal mode 1. Draw an ASCII diagram, at most 80 columns wide. Stack vertically rather than in one long row. 2. Follow it with numbered captions that use the diagram's labels. ## HTML mode 1. Create a task per step below, then work them to completion. 2. Load the `html-design-examples` skill for visual patterns, if available. 3. Write one self-contained page to `.explain/<kebab-slug>.html` in the working directory: inline CSS and JS, no build step. Reuse the slug when revising the same topic. In a git repo, append `.explain/` to `$(git rev-parse --git-path info/exclude)` if missing, so pages stay untracked without touching `.gitignore`. 4. Put the key picture in the first 1200x800 screen. Detail and depth go below it. Done when a reader gets the core idea without scrolling. 5. Draw diagrams as inline SVG so parts can highlight and animate. For a large flowchart or sequence, Mermaid from `https://cdn.jsdelivr.net/npm/mermaid@latest/dist/mermaid.esm.min.mjs` is fine. 6. For a process (pipeline, algorithm, protocol, request lifecycle), build a step-through: scenes driven by one step index, with prev/next buttons, arrow keys and play/pause. Each scene highlights what changed and shows a one-line caption. Load on the final, fully built scene so the first screen shows the whole picture. Done when buttons, arrow keys and play/pause all move the step index. 7. Add other controls (sliders, toggles, compare views) only where changing a value teaches something. 8. Support light and dark via `prefers-color-scheme`. Text meets WCAG AA contrast. 9. If a browser tool is available, screenshot the first 1200x800 screen in light and dark, and read the console. Fix clipped or overlapping text and any errors. With no browser tool, say the page was not visually checked. 10. Reply with the page path and a 2-3 line summary, leaving the HTML out of the reply.
© sammcj · Apache-2.0 · sammcj/agentic-coding
Similar skills
All skills for Writing and docs →explain by other authors comes first.