Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Upload files directly to Google Drive via a deployed Google Apps Script web app. Trigger on: upload to Drive, save to Drive, send to Drive, put this in Drive. Also Hebrew: "תעלה לדרייב", "שמור בדרייב", "העלה לגוגל דרייב". Use proactively when a workflow produces a file the user might want in Drive.
.claude/skills/davepoon-google-drive-upload/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-01 | ✗→✓ | ▲ Improved | 132% | 0% |
| case-05 | ✗→✓ | ▲ Improved | 63% | 0% |
| case-07 | ✗→✓ | ▲ Improved | -53% | 0% |
| case-08 | ✗→✓ | ▲ Improved | -13% | 0% |
| case-11 | ✗→✓ | ▲ Improved | -45% | 0% |
Upload files directly from Claude to Google Drive using a simple Google Apps Script.
~/.cowork-gdrive-config.json)~/.cowork-gdrive-config.json with your script URL and API keyAsk Claude naturally:
\\\bash
cat "$HOME/.cowork-gdrive-config.json"
FILE="/path/to/file" B64=$(base64 "$FILE" | tr -d '\n') MIME=$(file --mime-type -b "$FILE")
curl -s -L -H "Content-Type: application/json" \ -d '{"fileName":"name","content":"'$B64'","mimeType":"'$MIME'","apiKey":"KEY"}' \ "SCRIPT_URL" \\\
User: "Upload this report to Google Drive"
Output: Claude encodes the file, uploads it via the Apps Script, and returns: "Uploaded successfully! Here's your file: https://drive.google.com/file/d/abc123/view"
folderPath to organize files into folders (e.g., "Clients/Acme")"replaceExisting": true to overwrite instead of duplicatingFull plugin with setup guide and Apps Script code: https://github.com/msmobileapps/google-drive-upload-plugin
Built by MSApps — AI Automation & Application Development
| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-01 | fail→pass | 3,850 | 9,814 | +155% | 1 | 1 | 0% | 667 | 1,547 | +132% | 0 | 0 | — |
case-02 | fail→fail | 7,579 | 7,328 | -3% | 1 | 1 | 0% | 1,397 | 909 | -35% | 0 | 0 | — |
case-03 | fail→fail | 12,713 | 12,885 | +1% | 1 | 1 | 0% | 2,411 | 973 | -60% | 0 | 0 | — |
case-04 | fail→fail | 7,140 | 5,868 | -18% | 1 | 1 | 0% | 309 | 781 | +153% | 0 | 0 | — |
case-05 | fail→pass | 7,345 | 7,519 | +2% | 1 | 1 | 0% | 1,215 | 1,979 | +63% | 0 | 0 | — |
case-06 | fail→fail | 8,451 | 5,878 | -30% | 1 | 1 | 0% | 1,526 | 777 | -49% | 0 | 0 | — |
case-07 | fail→pass | 12,689 | 3,193 | -75% | 1 | 1 | 0% | 2,002 | 937 | -53% | 0 | 0 | — |
case-08 | fail→pass | 10,481 | 4,443 | -58% | 1 | 1 | 0% | 1,652 | 1,445 | -13% | 0 | 0 | — |
case-09 | pass→pass | 8,423 | 1,749 | -79% | 1 | 1 | 0% | 1,599 | 816 | -49% | 0 | 0 | — |
case-10 | fail→fail | 7,044 | 2,756 | -61% | 1 | 1 | 0% | 1,135 | 773 | -32% | 0 | 0 | — |
case-11 | fail→pass | 10,525 | 2,507 | -76% | 1 | 1 | 0% | 1,771 | 971 | -45% | 0 | 0 | — |
case-12 | fail→fail | 10,497 | 6,794 | -35% | 1 | 1 | 0% | 1,221 | 793 | -35% | 0 | 0 | — |
case-13 | fail→fail | 7,316 | 2,885 | -61% | 1 | 1 | 0% | 1,154 | 829 | -28% | 0 | 0 | — |
case-14 | pass→pass | 7,379 | 2,808 | -62% | 1 | 1 | 0% | 1,350 | 1,007 | -25% | 0 | 0 | — |
case-15 | fail→fail | 7,710 | 6,538 | -15% | 1 | 1 | 0% | 1,617 | 770 | -52% | 0 | 0 | — |
case-16 | fail→pass | 11,728 | 3,597 | -69% | 1 | 1 | 0% | 2,165 | 1,087 | -50% | 0 | 0 | — |
case-17 | pass→pass | 9,007 | 1,791 | -80% | 1 | 1 | 0% | 1,517 | 729 | -52% | 0 | 0 | — |
case-18 | pass→pass | 11,193 | 1,872 | -83% | 1 | 1 | 0% | 1,862 | 846 | -55% | 0 | 0 | — |
case-19 | fail→fail | 7,432 | 5,063 | -32% | 1 | 1 | 0% | 1,168 | 730 | -38% | 0 | 0 | — |
case-20 | pass→pass | 7,578 | 6,503 | -14% | 1 | 1 | 0% | 1,511 | 1,879 | +24% | 0 | 0 | — |
case-21 | pass→pass | 12,793 | 5,124 | -60% | 1 | 1 | 0% | 1,105 | 1,230 | +11% | 0 | 0 | — |
case-22 | pass→pass | 7,172 | 11,352 | +58% | 1 | 1 | 0% | 1,255 | 2,572 | +105% | 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 16 counted toward the lift figure. The other 6 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 +27 percentage points is the difference between those two pass rates over the 16 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.