Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Use when creating animated demos (GIFs) for pull requests or documentation. Covers terminal recording with asciinema and conversion to GIF/SVG for GitHub embedding.
.claude/skills/mikeyobrien-pr-demo/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-01 | ✗→✓ | ▲ Improved | 48% | 0% |
| case-13 | ✗→✓ | ▲ Improved | 39% | 0% |
| case-14 | ✗→✓ | ▲ Improved | 57% | 0% |
| case-15 | ✗→✓ | ▲ Improved | 42% | 0% |
| case-16 | ✗→✓ | ▲ Improved | 34% | 0% |
Create polished terminal demos for PRs using asciinema recordings converted to GIF. The workflow: script → record → convert → embed.
| 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)
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
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.
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)
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:
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):
bashsvg-term --in demo.cast --out demo.svg --window
Claude can self-validate demos using three approaches:
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"'
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.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!"
After running the above, verify:
markdown## Demo  *Shows: [one-sentence description of what the demo shows]*
Store demos in docs/demos/ or assets/ directory.
| 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 |
| 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 |
docs/demos/
├── feature-name.gif # The demo
├── feature-name.cast # Source recording (optional, for re-rendering)
└── README.md # Recording instructions for future maintainers| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-03 | fail→fail | 11,940 | 9,252 | -23% | 1 | 1 | 0% | 2,221 | 3,239 | +46% | 0 | 0 | — |
case-01 | fail→pass | 11,730 | 8,119 | -31% | 1 | 1 | 0% | 2,170 | 3,213 | +48% | 0 | 0 | — |
case-02 | fail→fail | 12,360 | 8,930 | -28% | 1 | 1 | 0% | 2,527 | 3,342 | +32% | 0 | 0 | — |
case-04 | pass→pass | 8,766 | 8,558 | -2% | 1 | 1 | 0% | 1,962 | 3,120 | +59% | 0 | 0 | — |
case-05 | pass→pass | 11,353 | 10,769 | -5% | 1 | 1 | 0% | 2,274 | 3,638 | +60% | 0 | 0 | — |
case-06 | pass→pass | 12,368 | 10,760 | -13% | 1 | 1 | 0% | 2,225 | 3,292 | +48% | 0 | 0 | — |
case-07 | pass→pass | 8,946 | 3,904 | -56% | 1 | 1 | 0% | 1,559 | 2,171 | +39% | 0 | 0 | — |
case-08 | pass→pass | 11,050 | 1,942 | -82% | 1 | 1 | 0% | 2,007 | 1,833 | -9% | 0 | 0 | — |
case-09 | pass→pass | 5,563 | 1,925 | -65% | 1 | 1 | 0% | 902 | 1,803 | +100% | 0 | 0 | — |
case-10 | pass→pass | 4,220 | 1,520 | -64% | 1 | 1 | 0% | 793 | 1,676 | +111% | 0 | 0 | — |
case-11 | pass→pass | 3,225 | 1,906 | -41% | 1 | 1 | 0% | 549 | 1,751 | +219% | 0 | 0 | — |
case-12 | pass→pass | 2,894 | 1,774 | -39% | 1 | 1 | 0% | 489 | 1,758 | +260% | 0 | 0 | — |
case-13 | fail→pass | 7,238 | 1,370 | -81% | 1 | 1 | 0% | 1,209 | 1,680 | +39% | 0 | 0 | — |
case-14 | fail→pass | 22,431 | 2,510 | -89% | 1 | 1 | 0% | 1,206 | 1,891 | +57% | 0 | 0 | — |
case-15 | fail→pass | 8,900 | 4,881 | -45% | 1 | 1 | 0% | 1,596 | 2,273 | +42% | 0 | 0 | — |
case-16 | fail→pass | 8,867 | 4,213 | -52% | 1 | 1 | 0% | 1,678 | 2,251 | +34% | 0 | 0 | — |
case-17 | pass→pass | 4,674 | 1,976 | -58% | 1 | 1 | 0% | 833 | 1,840 | +121% | 0 | 0 | — |
case-18 | pass→pass | 10,905 | 4,940 | -55% | 1 | 1 | 0% | 1,973 | 2,372 | +20% | 0 | 0 | — |
case-19 | fail→pass | 8,795 | 2,023 | -77% | 1 | 1 | 0% | 1,621 | 1,856 | +14% | 0 | 0 | — |
case-20 | pass→pass | 11,307 | 2,183 | -81% | 1 | 1 | 0% | 2,228 | 1,835 | -18% | 0 | 0 | — |
case-21 | fail→pass | 9,837 | 2,711 | -72% | 1 | 1 | 0% | 1,848 | 1,871 | +1% | 0 | 0 | — |
case-22 | fail→fail | 10,904 | 7,485 | -31% | 1 | 1 | 0% | 2,045 | 2,984 | +46% | 0 | 0 | — |
DecimalAI ran this skill against gemini-3.6-flash twice over the same eval suite — once with the skill loaded and once without — and compared the two runs case by case. 22 cases were attempted, and 21 counted toward the lift figure. The other 1 produced results that are not comparable between the two arms, so they are excluded from the headline rather than averaged into it. The headline lift of +32 percentage points is the difference between those two pass rates over the 21 comparable cases.
Without the skill loaded, the model failed this case. With it loaded, the same prompt on the same model passed. This is one improved case from the latest verified run; every case, including any that regressed, is in the table above.
Other measured skills in the registry, with their headline benchmark lift.