pr-demo — Claude Code skill: terminal GIF demos for PRs
Records a terminal session with asciinema and turns it into a GIF or SVG you can drop into a pull request.
npx skills add mikeyobrien/ralph-orchestrator --skill pr-demo -a claude-codeWhat pr-demo does
The skill walks you through four steps: script, record, convert, embed. You write a short plan first — what gets typed, what runs, where the payoff moment sits. Then you clean up the shell: plain prompt, TERM=xterm-256color, a 100x24 window so the text survives scaling down.
Recording goes to a .cast file with asciinema rec demo.cast --cols 100 --rows 24, and agg demo.cast demo.gif produces the GIF. When the result is too heavy, svg-term-cli gives a lighter SVG instead. There is also a self-check pass: file size, duration pulled from the .cast metadata, and a scan for leaked API keys or paths containing a username.
The tools themselves have to be in place beforehand: brew install asciinema, cargo install --git https://github.com/asciinema/agg, and optionally npm install -g svg-term-cli. Skip agg and the conversion step simply fails, so install it before you hit record — nobody wants to redo a demo because the converter was missing.
What it helps with
- record a terminal demo for a pull request description
- turn an asciinema session into a GIF
- cut demo weight by switching to SVG output
- scan a recording for leaked keys and paths
- embed the finished demo in a README or PR
Example prompts for the agent
- Record a demo of the
initcommand and convert it to a GIF for the PR - Check
demo.castfor API keys and confirm the duration - Make an SVG version of the demo, the GIF is too large
How to install pr-demo
1Skills CLI (Vercel)
npx skills add mikeyobrien/ralph-orchestrator --skill pr-demo -a claude-code2Manually: put the files in place
~/.claude/skills/pr-demo/SKILL.mdCopy the whole skill folder; for one project use .claude/skills/pr-demo/
1Skills CLI (Vercel)
npx skills add mikeyobrien/ralph-orchestrator --skill pr-demo -a codex2Manually: put the files in place
.agents/skills/pr-demo/SKILL.mdFor all projects use ~/.agents/skills/
1Skills CLI (Vercel)
npx skills add mikeyobrien/ralph-orchestrator --skill pr-demo -a cursor2Manually: put the files in place
.cursor/skills/pr-demo/SKILL.mdCursor also reads .agents/skills/ and .claude/skills/
1GitHub CLI
gh skill install mikeyobrien/ralph-orchestrator pr-demo2Manually: put the files in place
.github/skills/pr-demo/SKILL.md1Skills CLI (Vercel)
npx skills add mikeyobrien/ralph-orchestrator --skill pr-demo -a gemini-cli2Platform CLI
gemini skills install https://github.com/mikeyobrien/ralph-orchestrator --path .claude/skills/pr-demoManually: put the files in place
.devin/skills/pr-demo/SKILL.mdThe legacy .windsurf/skills/ path still works
Skills CLI (Vercel)
npx skills add mikeyobrien/ralph-orchestrator --skill pr-demo -a opencodeClaude.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 pr-demo
How do I install pr-demo in Claude Code?
Run npx skills add mikeyobrien/ralph-orchestrator --skill pr-demo -a claude-code; the skill file lands at ~/.claude/skills/pr-demo/SKILL.md.
What does pr-demo do?
It guides you through recording a terminal session with asciinema and converting it to GIF or SVG, then checks size, duration and sensitive content in the recording.
What has to be installed before recording?
asciinema and agg — without them you can neither record nor convert. svg-term-cli matters only if you want the SVG route.
Source text
SKILL.md · MIT
--- name: pr-demo description: Use when creating animated demos (GIFs) for pull requests or documentation. Covers terminal recording with asciinema and conversion to GIF/SVG for GitHub embedding. metadata: internal: true --- # PR Demo Creation ## Overview Create polished terminal demos for PRs using asciinema recordings converted to GIF. The workflow: **script → record → convert → embed**. ## Tool Selection | Goal | Tool Chain | Output | |------|------------|--------| | CLI demo for GitHub PR | asciinema → agg | GIF (< 5MB) | | Smaller file needed | asciinema → svg-term-cli | SVG (< 500KB) | | TUI screenshot | tmux → freeze | SVG/PNG | **Default choice:** asciinema + agg (best compatibility, GitHub renders GIFs natively) ## Prerequisites ```bash # Install tools (macOS) brew install asciinema cargo install --git https://github.com/asciinema/agg npm install -g svg-term-cli # Optional: for SVG output ``` ## Workflow ### 1. Script Your Demo (REQUIRED) Before recording, write a brief script: ```markdown ## Demo: [feature name] Duration: ~20-30 seconds 1. [0-3s] Show command being typed 2. [3-10s] Command executes, show key output 3. [10-25s] Highlight the "aha moment" - what makes this valuable 4. [25-30s] Clean exit or final state ``` **Keep it short.** 20-30 seconds max. Show ONE thing well. ### 2. Prepare Environment ```bash # Clean terminal state clear export PS1='$ ' # Simple prompt export TERM=xterm-256color # Consistent colors # Hide sensitive info (API keys, paths with usernames) ``` Terminal size: **100x24** (readable when scaled down) ### 3. Record ```bash # Record to .cast file asciinema rec demo.cast --cols 100 --rows 24 # Execute your scripted demo # Press Ctrl+D or type 'exit' when done ``` **Tips:** - Type at readable speed (not too fast) - Pause briefly after key moments - If you make a mistake, start over (editing is harder than re-recording) ### 4. Convert to GIF ```bash # Basic conversion (recommended) agg demo.cast demo.gif # With speed adjustment (1.5x faster) agg --speed 1.5 demo.cast demo.gif # With custom font size for readability agg --font-size 14 demo.cast demo.gif ``` **Alternative - SVG (smaller files):** ```bash svg-term --in demo.cast --out demo.svg --window ``` ### 5. Validate (Self-Validation) Claude can self-validate demos using three approaches: #### A. Automated Checks (run these first) ```bash # Check file size (must be < 5MB for GitHub) ls -lh demo.gif # Check recording duration from .cast metadata head -1 demo.cast | jq '.duration // "check manually"' ``` #### B. Visual Validation (LLM-as-judge) Extract a static frame for Claude to analyze: ```bash # Option 1: Use svg-term to render a specific timestamp (e.g., 15 seconds in) svg-term --in demo.cast --out demo-preview.svg --at 15000 # Option 2: Use asciinema cat + freeze for a snapshot asciinema cat demo.cast | head -500 | freeze -o demo-preview.png # Option 3: Just convert to GIF and use the file directly # Claude can read GIF files with the Read tool ``` Then ask Claude to analyze using the Read tool on the image: **Validation prompt:** ``` Analyze this terminal demo screenshot. Check: 1. Is the text readable (not too small/blurry)? 2. Is the command being demonstrated visible? 3. Is there any sensitive info (API keys, /Users/username paths)? 4. Does the terminal look clean (simple prompt, no clutter)? 5. Is the "aha moment" visible - what value does this demo show? Rate: PASS or FAIL with specific issues. ``` #### C. Content Validation (parse .cast file) The `.cast` file is JSON lines - validate the content programmatically: ```bash # Check what commands were typed (input events) grep '"i"' demo.cast | head -20 # Check recording duration head -1 demo.cast | jq -r '.duration | floor' # Should be 20-30 seconds # Look for sensitive patterns grep -iE '(api.?key|password|secret|/Users/[a-z])' demo.cast && echo "WARNING: Sensitive data found!" ``` #### D. Full Validation Checklist After running the above, verify: - [ ] File size < 5MB (automated) - [ ] Duration 20-30 seconds (automated) - [ ] No sensitive info in .cast (automated) - [ ] Text readable in preview frame (visual/LLM) - [ ] Demo shows feature clearly (visual/LLM) - [ ] Clean terminal appearance (visual/LLM) ### 6. Embed in PR ```markdown ## Demo  *Shows: [one-sentence description of what the demo shows]* ``` Store demos in `docs/demos/` or `assets/` directory. ## Quick Reference | Setting | Recommended Value | |---------|------------------| | Duration | 20-30 seconds | | Terminal size | 100x24 | | Speed multiplier | 1.0-1.5x | | Target file size | < 2MB ideal, < 5MB max | | Font size (agg) | 14-16 | ## Common Mistakes | Mistake | Fix | |---------|-----| | Demo too long | Script it first, show ONE thing | | Text unreadable | Use --font-size 14+, terminal 100x24 | | File too large | Use svg-term-cli instead, or increase speed | | Cluttered terminal | Clean PS1, clear history, hide paths | | No context in PR | Add one-line description below GIF | ## File Organization ``` docs/demos/ ├── feature-name.gif # The demo ├── feature-name.cast # Source recording (optional, for re-rendering) └── README.md # Recording instructions for future maintainers ```
© mikeyobrien · MIT · mikeyobrien/ralph-orchestrator