ui-showcase
Skill568 starsChanged 7 months agoMITView on GitHub
Display all agent pane UI elements simultaneously in the sidebar for visual verification. Trigger on "UI check", "showcase", "UI demo", "show all patterns", "verify panel display", "UIを確認したい", "showcaseして". Use after UI changes to visually confirm rendering.
In this repository5 other files it gives its agents.
- AGENTS.mdAGENTS.md
- docs-auditSkill
- regenerate-capturesSkill
- sync-upstream-featuresSkill
- version-releaseSkill
The file
We split this skill into the rules it gives an agent
4 rules. About 0 are common, 4 are distinctive, and 0 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈4
Distinctive · estimate
This author's own choices. Worth a look.
0
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 16
Start a background HTTP server via Bash tool.
- Distinctive: line 24
Create 3 tasks with TaskCreate, then set each to a different status to show all icon types (✔◼◻):
- Distinctive: line 46
After execution, confirm the following are all visible in the sidebar:
- Distinctive: line 70
Stop the HTTP server after verification:
≈ “Common” is an estimate: at least 1 in 5 of the 364,980 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
UI Showcase — Display All Agent Pane Elements Simultaneously
Trigger all UI elements within the current Claude Code session so the sidebar's agent pane displays everything at once for visual verification.
UI Elements and How to Trigger Them
Execute in this order. Once all steps complete, every element is visible in the sidebar simultaneously.
1. Port Display
Start a background HTTP server via Bash tool. The sidebar detects it through port scanning.
python3 -m http.server 9876 &2. Task Progress Display
Create 3 tasks with TaskCreate, then set each to a different status to show all icon types (✔◼◻):
- Task 1: create → TaskUpdate to completed (✔)
- Task 2: create → TaskUpdate to in_progress (◼)
- Task 3: create only → stays pending (◻)
3. Subagent Display
Launch 2 subagents in parallel via Agent tool with run_in_background: true.
The sidebar shows ├ / └ tree visualization while they run.
Give each subagent a time-consuming task. For example:
- subagent 1: Read all files in
src/ui/and list every public function/struct - subagent 2: Read all files in
tests/and list every test function name
4. Ask User to Verify
Once all elements are active, ask the user to check the sidebar. Subagents remain visible until they complete, providing enough time for inspection.
Verification Checklist
After execution, confirm the following are all visible in the sidebar:
- Status icon (● Running)
- Agent name (claude)
- Elapsed time (XmXs on the right)
- Branch name (auto-displayed when inside a git repo)
- Port number (:9876)
- Task progress (✔◼◻ X/Y)
- Subagent tree (├ / └)
- Prompt text
- Activity log (Bash, TaskCreate, Agent etc. in the Activity tab)
Elements That Cannot Be Shown Simultaneously
These are mutually exclusive states, so they are out of scope for this skill:
- Wait reason (permission required, etc.) — not shown while Running
- Response display (▶ arrow) — only shown in Idle state
- Error status (✕) — mutually exclusive with Running
- Permission mode badge — depends on Claude Code launch options (no badge in default mode)
- Worktree indicator (+ name: branch) — requires launching Claude Code inside a git worktree
Cleanup
Stop the HTTP server after verification:
kill $(lsof -ti:9876) 2>/dev/nullDoes it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

