Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Collect Framer debug evidence for support tickets and troubleshooting. Use when encountering persistent issues, preparing support tickets, or collecting diagnostic information for Framer problems. Trigger with phrases like "framer debug", "framer support bundle", "collect framer logs", "framer diagnostic".
.claude/skills/jeremylongshore-framer-debug-bundle/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-01 | ✗→✓ | ▲ Improved | -50% | 0% |
| case-02 | ✗→✓ | ▲ Improved | -1% | 0% |
| case-03 | ✗→✓ | ▲ Improved | -36% | 0% |
| case-10 | ✗→✓ | ▲ Improved | 39% | 0% |
| case-11 | ✗→✓ | ▲ Improved | -43% | 0% |
Collect diagnostic information for Framer plugin or Server API issues including package versions, API connectivity, and configuration.
bash#!/bin/bash BUNDLE="framer-debug-$(date +%Y%m%d-%H%M%S)" mkdir -p "$BUNDLE" echo "=== Framer Debug Bundle ===" | tee "$BUNDLE/summary.txt" echo "Date: $(date -u)" >> "$BUNDLE/summary.txt" # Runtime echo "--- Runtime ---" >> "$BUNDLE/summary.txt" node --version >> "$BUNDLE/summary.txt" 2>&1 npm --version >> "$BUNDLE/summary.txt" 2>&1 # Packages echo "--- Packages ---" >> "$BUNDLE/summary.txt" npm list framer-plugin framer-api framer 2>/dev/null >> "$BUNDLE/summary.txt" # Credentials (presence only) echo "--- Config ---" >> "$BUNDLE/summary.txt" echo "FRAMER_API_KEY: ${FRAMER_API_KEY:+[SET]}" >> "$BUNDLE/summary.txt" echo "FRAMER_SITE_ID: ${FRAMER_SITE_ID:+[SET]}" >> "$BUNDLE/summary.txt" # API connectivity echo "--- API Test ---" >> "$BUNDLE/summary.txt" curl -s -o /dev/null -w "Framer API: HTTP %{http_code}\n" https://api.framer.com/health >> "$BUNDLE/summary.txt" 2>&1 # Vite config cp vite.config.ts "$BUNDLE/" 2>/dev/null cp tsconfig.json "$BUNDLE/" 2>/dev/null cp package.json "$BUNDLE/" 2>/dev/null # Bundle tar -czf "$BUNDLE.tar.gz" "$BUNDLE" echo "Bundle: $BUNDLE.tar.gz"
summary.txt with runtime, packages, connectivityFor rate limit issues, see framer-rate-limits.
| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-01 | fail→pass | 20,132 | 12,475 | -38% | 1 | 1 | 0% | 4,218 | 2,099 | -50% | 0 | 0 | — |
case-02 | fail→pass | 22,267 | 18,069 | -19% | 1 | 1 | 0% | 3,496 | 3,474 | -1% | 0 | 0 | — |
case-03 | fail→pass | 18,822 | 14,857 | -21% | 1 | 1 | 0% | 4,011 | 2,585 | -36% | 0 | 0 | — |
case-04 | pass→pass | 22,368 | 18,334 | -18% | 1 | 1 | 0% | 3,644 | 3,450 | -5% | 0 | 0 | — |
case-05 | pass→pass | 15,276 | 15,818 | +4% | 1 | 1 | 0% | 1,921 | 2,524 | +31% | 0 | 0 | — |
case-06 | pass→pass | 16,954 | 7,060 | -58% | 1 | 1 | 0% | 2,254 | 1,769 | -22% | 0 | 0 | — |
case-07 | pass→pass | 18,042 | 17,507 | -3% | 1 | 1 | 0% | 2,375 | 2,927 | +23% | 0 | 0 | — |
case-08 | fail→fail | 9,162 | 13,884 | +52% | 1 | 1 | 0% | 1,644 | 2,128 | +29% | 0 | 0 | — |
case-09 | fail→fail | 12,963 | 15,097 | +16% | 1 | 1 | 0% | 2,310 | 2,226 | -4% | 0 | 0 | — |
case-10 | fail→pass | 9,826 | 15,217 | +55% | 1 | 1 | 0% | 1,690 | 2,352 | +39% | 0 | 0 | — |
case-11 | fail→pass | 16,430 | 2,371 | -86% | 1 | 1 | 0% | 1,775 | 1,008 | -43% | 0 | 0 | — |
case-12 | pass→pass | 6,075 | 8,154 | +34% | 1 | 1 | 0% | 1,171 | 1,126 | -4% | 0 | 0 | — |
case-13 | pass→pass | 7,759 | 11,529 | +49% | 1 | 1 | 0% | 1,380 | 1,729 | +25% | 0 | 0 | — |
case-14 | fail→pass | 31,587 | 6,461 | -80% | 1 | 1 | 0% | 1,098 | 1,717 | +56% | 0 | 0 | — |
case-15 | pass→pass | 12,326 | 5,334 | -57% | 1 | 1 | 0% | 1,463 | 1,343 | -8% | 0 | 0 | — |
case-16 | fail→pass | 14,287 | 6,749 | -53% | 1 | 1 | 0% | 1,542 | 797 | -48% | 0 | 0 | — |
case-17 | pass→pass | 10,780 | 8,752 | -19% | 1 | 1 | 0% | 1,118 | 1,332 | +19% | 0 | 0 | — |
case-18 | fail→pass | 14,460 | 4,551 | -69% | 1 | 1 | 0% | 1,913 | 1,444 | -25% | 0 | 0 | — |
case-19 | fail→pass | 14,372 | 12,876 | -10% | 1 | 1 | 0% | 3,367 | 3,474 | +3% | 0 | 0 | — |
case-20 | fail→pass | 13,184 | 7,983 | -39% | 1 | 1 | 0% | 1,690 | 1,163 | -31% | 0 | 0 | — |
case-21 | pass→pass | 9,963 | 10,312 | +4% | 1 | 1 | 0% | 1,967 | 1,626 | -17% | 0 | 0 | — |
case-22 | fail→pass | 7,141 | 7,346 | +3% | 1 | 1 | 0% | 399 | 1,020 | +156% | 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 +50 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.