show-me — Claude Code skill: what it does, how to install
Explains code and architecture through Mermaid diagrams, call trees, diffs, and HTML artifacts. Useful when you need a concise visual layout instead of walls of text.
npx skills add humanlayer/skills --skill show-me -a claude-codeWhat show-me does
This skill forces the model to explain concepts visually without introductory chatter. It picks the most compact format for the context, such as pseudocode for logic or a call tree for control flow. It relies on Mermaid sequence diagrams to map component interactions. Brevity is the priority here.
When existing code already defines the boundaries, the skill outputs a diff — for file layout or state updates. For layouts too dense for terminal text, it generates a standalone HTML document styled for desktop and mobile screens. The agent then launches it directly through the Bash open command.
The frontmatter sets disable-model-invocation: true. Because of that, the assistant will not trigger this workflow automatically; you have to invoke it intentionally during the session.
What it helps with
- trace runtime control flow with call trees
- map component hierarchies and module boundaries
- visualize architectural changes with targeted diffs
- generate standalone HTML artifacts for dense layouts
Example prompts for the agent
- Use the show-me skill to draw a call tree for submitForm
- Show me a Mermaid diagram of how UI communicates with the daemon
- Create an HTML mockup comparing session states for desktop and mobile
How to install show-me
1Skills CLI (Vercel)
npx skills add humanlayer/skills --skill show-me -a claude-code2Manually: put the files in place
~/.claude/skills/show-me/SKILL.mdCopy the whole skill folder; for one project use .claude/skills/show-me/
1Skills CLI (Vercel)
npx skills add humanlayer/skills --skill show-me -a codex2Manually: put the files in place
.agents/skills/show-me/SKILL.mdFor all projects use ~/.agents/skills/
1Skills CLI (Vercel)
npx skills add humanlayer/skills --skill show-me -a cursor2Manually: put the files in place
.cursor/skills/show-me/SKILL.mdCursor also reads .agents/skills/ and .claude/skills/
1GitHub CLI
gh skill install humanlayer/skills show-me2Manually: put the files in place
.github/skills/show-me/SKILL.md1Skills CLI (Vercel)
npx skills add humanlayer/skills --skill show-me -a gemini-cli2Platform CLI
gemini skills install https://github.com/humanlayer/skills --path plugins/show-me/skills/show-meManually: put the files in place
.devin/skills/show-me/SKILL.mdThe legacy .windsurf/skills/ path still works
Skills CLI (Vercel)
npx skills add humanlayer/skills --skill show-me -a opencodeClaude.ai
Zip the folder and upload it in Settings → Capabilities → Skills
Similar
Questions about show-me
How to install show-me in Claude Code?
Run npx skills add humanlayer/skills --skill show-me -a claude-code in your terminal.
What does the show-me skill do?
It instructs the agent to explain architecture and logic visually using pseudocode, Mermaid diagrams, component trees, or standalone HTML files.
Why does show-me not run automatically on every prompt?
Its frontmatter specifies disable-model-invocation: true. This prevents the model from invoking the skill on its own, so it only activates when requested.
Source text
SKILL.md · MIT
---
name: show-me
description: Help the user understand the current topic visually with concise diagrams, code-shape sketches, and focused HTML artifacts.
disable-model-invocation: true
---
Help the user understand the current topic of conversation visually. Skip the preamble and keep prose brief. Pick the smallest view that makes the key point clear.
- Show logic or an algorithm as pseudocode:
```text
on(save)
if content is unchanged
return cached result
write new content
return fresh result
```
- Show runtime control flow as a call tree:
```text
submitForm
createSession
persistPrompt
launchAgent
navigateToSession
```
- Show UI structure as a component tree, including state and module boundaries that matter:
```tsx
<SessionPage> (apps/example/src/routes/session.tsx)
useSessionEvents()
<SessionToolbar>
<RunSkillButton> (packages/ui)
```
- Show file responsibility or a broad refactor as a shallow file tree:
```text
src/
├── commands/ # parses user actions
├── sessions/ # owns session state
└── transport/ # sends API requests
```
- Show component interaction, control flow, or data flow with Mermaid:
```mermaid
sequenceDiagram
participant User
participant UI
participant Daemon
User->>UI: choose command
UI->>Daemon: send expanded prompt
Daemon-->>UI: stream result
```
- Use `diff` when the point is what changes and the surrounding shape already exists. Match the diff shape to the topic.
For a component change:
```diff
<SessionPage>
useSessionEvents()
<SessionToolbar>
+ <RunSkillButton />
<SessionTimeline>
+ <SkillResultCard />
```
For a file-layout change:
```diff
src/
├── commands/
+│ └── show-me.ts # expands the slash command
├── sessions/
-└── transport.ts
+└── transport/
+ ├── client.ts
+ └── stream.ts
```
For a call-tree or call-stack change:
```diff
submitForm
createSession
persistPrompt
+ expandSkillMention
launchAgent
- navigateToSession
+ navigateToSession
+ subscribeToEvents
```
For a state or control-flow change:
```diff
on(save)
- write content
+ if content is unchanged
+ return cached result
+ write new content
+ invalidate cache
```
- Show the whole block when most of it is new, when omitted context would hide ownership or order, or when the user needs a copyable target shape:
```ts
function expandSkill(command: string): string {
const skillName = command.slice(1)
return `use the ${skillName} skill`
}
```
- For a visual UI, layout, state comparison, or concept too dense for Mermaid, write one focused HTML file — a diagram, an infographic, or a short slide deck, whichever fits the point. Match the product's colors, type, spacing, and components; use real labels and data; support desktop and mobile. Then open it for the user:
```
Bash(open path/to/show-me-{description}.html)
```
### guidance
Place each visual next to the short text it supports. Keep only the calls, files, props, states, and boundaries needed to answer the user's current question or the options to resolve the current discussion point.
You may use one of these, you may use several, it is unlikely you will use all of them. Use your judgement and don't overwhelm the user.
© humanlayer · MIT · humanlayer/skills