Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Search GIFs from Tenor and Giphy via CLI or TUI, download GIFs, and extract stills or sprite sheets. Use when an agent needs to find a GIF by keyword, download it, or generate a still frame or contact sheet from a GIF.
.claude/skills/composio-community-gif-search-cli-gifgrep/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-02 | ✗→✓ | ▲ Improved | -47% | 0% |
| case-01 | ✗→✓ | ▲ Improved | -10% | 0% |
| case-03 | ✗→✓ | ▲ Improved | -5% | 0% |
| case-04 | ✗→✓ | ▲ Improved | -47% | 0% |
| case-05 | ✗→✓ | ▲ Improved | -61% | 0% |
Search GIF providers (Tenor, Giphy) with scriptable CLI output or interactive TUI with inline previews.
bashbrew install steipete/tap/gifgrep
Or via Go:
bashgo install github.com/steipete/gifgrep/cmd/gifgrep@latest
bashgifgrep cats --max 5 gifgrep cats --format url | head -n 5 gifgrep cats --json | jq '.[0].url' gifgrep "office handshake" --source giphy --max 3 --json
bashgifgrep cats --download --max 1 --format url gifgrep cats --download --reveal # download and reveal in Finder
bashgifgrep still ./clip.gif --at 1.5s -o still.png gifgrep sheet ./clip.gif --frames 9 --cols 3 -o sheet.png
bashgifgrep tui "office handshake"
Select via --source:
auto (default): prefers Giphy when GIPHY_API_KEY is set, else Tenortenor: uses public demo key if TENOR_API_KEY is unsetgiphy: requires GIPHY_API_KEY--json: array of objects with id, title, url, preview_url, tags, width, height--format url: one URL per line (pipeable)--thumbs: inline still-frame thumbnails (Kitty/iTerm2 terminals)TENOR_API_KEY (optional)GIPHY_API_KEY (required for --source giphy)| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-02 | fail→pass | 10,164 | 1,811 | -82% | 1 | 1 | 0% | 1,644 | 873 | -47% | 0 | 0 | — |
case-01 | fail→pass | 6,756 | 3,035 | -55% | 1 | 1 | 0% | 1,096 | 990 | -10% | 0 | 0 | — |
case-03 | fail→pass | 6,747 | 3,091 | -54% | 1 | 1 | 0% | 1,185 | 1,121 | -5% | 0 | 0 | — |
case-04 | fail→pass | 8,616 | 1,531 | -82% | 1 | 1 | 0% | 1,503 | 796 | -47% | 0 | 0 | — |
case-05 | fail→pass | 13,659 | 2,549 | -81% | 1 | 1 | 0% | 2,408 | 937 | -61% | 0 | 0 | — |
case-06 | fail→pass | 7,940 | 6,204 | -22% | 1 | 1 | 0% | 1,252 | 844 | -33% | 0 | 0 | — |
case-07 | fail→pass | 8,592 | 1,572 | -82% | 1 | 1 | 0% | 1,371 | 680 | -50% | 0 | 0 | — |
case-08 | fail→pass | 26,851 | 1,391 | -95% | 1 | 1 | 0% | 4,972 | 690 | -86% | 0 | 0 | — |
case-09 | fail→pass | 19,905 | 1,976 | -90% | 1 | 1 | 0% | 3,715 | 824 | -78% | 0 | 0 | — |
case-10 | pass→pass | 7,683 | 3,032 | -61% | 1 | 1 | 0% | 1,222 | 943 | -23% | 0 | 0 | — |
case-11 | fail→pass | 10,667 | 1,883 | -82% | 1 | 1 | 0% | 1,741 | 833 | -52% | 0 | 0 | — |
case-12 | pass→pass | 3,404 | 1,586 | -53% | 1 | 1 | 0% | 545 | 664 | +22% | 0 | 0 | — |
case-13 | fail→pass | 8,011 | 1,669 | -79% | 1 | 1 | 0% | 1,602 | 727 | -55% | 0 | 0 | — |
case-14 | fail→pass | 9,834 | 2,524 | -74% | 1 | 1 | 0% | 1,688 | 814 | -52% | 0 | 0 | — |
case-15 | pass→pass | 5,018 | 1,574 | -69% | 1 | 1 | 0% | 710 | 742 | +5% | 0 | 0 | — |
case-16 | pass→pass | 9,199 | 2,192 | -76% | 1 | 1 | 0% | 1,784 | 919 | -48% | 0 | 0 | — |
case-17 | pass→pass | 8,193 | 1,895 | -77% | 1 | 1 | 0% | 1,335 | 703 | -47% | 0 | 0 | — |
case-18 | fail→pass | 6,111 | 1,658 | -73% | 1 | 1 | 0% | 1,126 | 768 | -32% | 0 | 0 | — |
case-19 | pass→pass | 6,355 | 2,349 | -63% | 1 | 1 | 0% | 984 | 846 | -14% | 0 | 0 | — |
case-20 | pass→pass | 8,997 | 6,652 | -26% | 1 | 1 | 0% | 1,728 | 1,679 | -3% | 0 | 0 | — |
case-21 | pass→pass | 10,514 | 7,087 | -33% | 1 | 1 | 0% | 1,967 | 1,796 | -9% | 0 | 0 | — |
case-22 | pass→pass | 7,609 | 3,455 | -55% | 1 | 1 | 0% | 1,526 | 1,152 | -25% | 0 | 0 | — |
case-23 | fail→pass | 5,334 | 1,887 | -65% | 1 | 1 | 0% | 910 | 791 | -13% | 0 | 0 | — |
case-24 | fail→pass | 13,059 | 1,428 | -89% | 1 | 1 | 0% | 2,388 | 696 | -71% | 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. 24 cases were attempted. The headline lift of +63 percentage points is the difference between those two pass rates over the 24 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.