Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Knowledge and utilities for creating animated GIFs optimized for Slack. Provides constraints, validation tools, and animation concepts. Use when users request animated GIFs for Slack like "make me a GIF of X doing Y for Slack."
.claude/skills/dokhacgiakhoa-slack-gif-creator/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-01 | ✗→✓ | ▲ Improved | 26% | 0% |
| case-02 | ✗→✓ | ▲ Improved | -43% | 0% |
| case-06 | ✗→✓ | ▲ Improved | 12% | 0% |
| case-07 | ✗→✓ | ▲ Improved | -6% | 0% |
| case-11 | ✗→✓ | ▲ Improved | -2% | 0% |
A toolkit providing utilities and knowledge for creating animated GIFs optimized for Slack.
Dimensions:
Parameters:
pythonfrom core.gif_builder import GIFBuilder from PIL import Image, ImageDraw # 1. Create builder builder = GIFBuilder(width=128, height=128, fps=10) # 2. Generate frames for i in range(12): frame = Image.new('RGB', (128, 128), (240, 248, 255)) draw = ImageDraw.Draw(frame) # Draw your animation using PIL primitives # (circles, polygons, lines, etc.) builder.add_frame(frame) # 3. Save with optimization builder.save('output.gif', num_colors=48, optimize_for_emoji=True)
core.gif_builder)core.validators)core.easing)core.frame_composer)| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-01 | fail→pass | 26,934 | 28,917 | +7% | 1 | 1 | 0% | 4,417 | 5,553 | +26% | 0 | 0 | — |
case-02 | fail→pass | 44,634 | 24,178 | -46% | 1 | 1 | 0% | 8,233 | 4,663 | -43% | 0 | 0 | — |
case-03 | fail→fail | 46,639 | 45,528 | -2% | 1 | 1 | 0% | 8,230 | 8,885 | +8% | 0 | 0 | — |
case-04 | pass→pass | 19,950 | 18,069 | -9% | 1 | 1 | 0% | 2,826 | 3,363 | +19% | 0 | 0 | — |
case-05 | pass→pass | 18,510 | 12,546 | -32% | 1 | 1 | 0% | 2,678 | 3,118 | +16% | 0 | 0 | — |
case-06 | fail→pass | 15,924 | 13,887 | -13% | 1 | 1 | 0% | 1,853 | 2,071 | +12% | 0 | 0 | — |
case-07 | fail→pass | 9,828 | 8,560 | -13% | 1 | 1 | 0% | 1,392 | 1,315 | -6% | 0 | 0 | — |
case-08 | fail→fail | 13,749 | 2,858 | -79% | 1 | 1 | 0% | 1,489 | 1,142 | -23% | 0 | 0 | — |
case-09 | pass→pass | 9,825 | 8,732 | -11% | 1 | 1 | 0% | 1,595 | 1,216 | -24% | 0 | 0 | — |
case-10 | pass→pass | 17,766 | 10,585 | -40% | 1 | 1 | 0% | 2,053 | 1,639 | -20% | 0 | 0 | — |
case-11 | fail→pass | 13,026 | 3,558 | -73% | 1 | 1 | 0% | 1,303 | 1,282 | -2% | 0 | 0 | — |
case-12 | fail→pass | 19,504 | 12,751 | -35% | 1 | 1 | 0% | 2,743 | 2,246 | -18% | 0 | 0 | — |
case-13 | fail→pass | 8,194 | 6,517 | -20% | 1 | 1 | 0% | 1,639 | 957 | -42% | 0 | 0 | — |
case-14 | fail→pass | 26,310 | 1,843 | -93% | 1 | 1 | 0% | 3,680 | 934 | -75% | 0 | 0 | — |
case-15 | fail→pass | 17,861 | 7,533 | -58% | 1 | 1 | 0% | 2,330 | 1,029 | -56% | 0 | 0 | — |
case-16 | pass→fail | 16,570 | 6,878 | -58% | 1 | 1 | 0% | 1,898 | 968 | -49% | 0 | 0 | — |
case-17 | fail→pass | 6,599 | 7,199 | +9% | 1 | 1 | 0% | 1,079 | 901 | -16% | 0 | 0 | — |
case-18 | pass→pass | 4,060 | 8,861 | +118% | 1 | 1 | 0% | 754 | 1,344 | +78% | 0 | 0 | — |
case-19 | fail→pass | 29,190 | 7,481 | -74% | 1 | 1 | 0% | 1,271 | 1,044 | -18% | 0 | 0 | — |
case-20 | pass→pass | 16,851 | 2,088 | -88% | 1 | 1 | 0% | 1,712 | 1,046 | -39% | 0 | 0 | — |
case-21 | pass→pass | 15,169 | 7,849 | -48% | 1 | 1 | 0% | 1,554 | 1,158 | -25% | 0 | 0 | — |
case-22 | pass→pass | 18,926 | 7,003 | -63% | 1 | 1 | 0% | 2,286 | 977 | -57% | 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 +45 percentage points is the difference between those two pass rates over the 21 comparable cases. 1 case got worse with the skill loaded, and it is included in that figure.
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.