Install
$ agentstack add skill-wilbeibi-wilbeibi-skills-show-me ✓ scanned · ✓ verified, works with Claude Code, Cursor, and more.
Security review
✓ PassedNo issues found. Passed automated security review. · v0.1.0 How review works →
- ✓ Prompt-injection patterns
- ✓ Secret / credential exfiltration
- ✓ Dangerous shell & filesystem operations
- ✓ Untrusted network calls
- ✓ Known-malicious package signatures
What it can access
- ✓ Network access No
- ✓ Filesystem access No
- ✓ Shell / process execution No
- ✓ Environment & secrets No
- ✓ Dynamic code execution No
From automated source analysis of v0.1.0. “Used” means the capability is present in the source — more access means more to trust, not that it’s unsafe.
Verified badge
Passed review? Show it. Paste this badge into your README, it links to the public security report.
Reliability & compatibility
Declared compatibility
Compatibility is declared by the source manifest. End-to-end runtime verification is coming, see below.
We're building live execution health for every listing: tool-call success rate, median latency, uptime, and last-checked timestamps, measured, not self-reported. It isn't live yet, so we don't show numbers we can't stand behind.
How agent discovery & health will work →About
show-me
Pick the smallest view that makes the point, set it beside one or two lines of text, stop. One view per question; two if a second genuinely adds an axis. Never all of them.
Pick the view
| The question is about | Show | |---|---| | an algorithm, branching, an invariant | pseudocode | | runtime order, who calls whom | call tree | | UI structure, state ownership | component tree — JSX plus the hooks and module paths that matter | | where code lives, refactor scope | shallow file tree, one-line responsibility per entry | | interaction across processes or time | Mermaid sequenceDiagram / stateDiagram | | the shape of an API before writing it | type signatures only, no bodies | | a change to any of the above | that same view, as a diff | | a layout, or a comparison too dense for the above | one self-contained HTML file |
Render target decides the format
Terminals do not draw Mermaid — a ```mermaid block in a chat reply is source code the user has to compile in their head. ASCII trees render everywhere.
- Reply in the terminal → indentation and box-drawing trees, pseudocode, diffs.
- Output lands in a file that renders — Obsidian note, GitHub PR or issue, markdown doc →
Mermaid is worth it. Say where it will render.
- HTML is the last resort, for layout, spatial comparison, or an interactive explainer.
Match the product's colors, type, and spacing; use real labels and real data. Write it outside the project tree ($TMPDIR) unless the user asks to keep it, then open it: open $TMPDIR/show-me-.html.
Examples
Call tree — runtime order:
submitForm
createSession
persistPrompt
launchAgent
navigateToSession
Component tree — structure, state, and the module a component comes from:
(apps/example/src/routes/session.tsx)
useSessionEvents()
(packages/ui)
File tree — responsibility, one line each:
src/
├── commands/ # parses user actions
├── sessions/ # owns session state
└── transport/ # sends API requests
Diff — when the surrounding shape already exists. Diff whichever view fits the topic; any of the above takes diff markers. Here, pseudocode:
on(save)
- write content
+ if content is unchanged
+ return cached result
+ write new content
+ invalidate cache
Rules
- Include only the calls, files, props, states, and boundaries this question needs. Elide the
rest with …. Do not pad a view toward completeness.
- Real paths, real names, real data. A tidy diagram with invented labels is worse than prose.
- Show the whole block instead of a diff when most of it is new, when the omitted context
hides ownership or order, or when the user needs something copyable.
- Skip the preamble. The visual is the answer; the prose is a caption.
Source & license
This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.
- Author: wilbeibi
- Source: wilbeibi/wilbeibi-skills
- License: MIT
Install and usage instructions live in the source repository linked above.
Reviews
No reviews yet, be the first.
Write a review
Versions
- v0.1.0 Imported from the upstream source.