Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Instagram analytics report — queries profile stats, recent posts, engagement rates, insights for all connected accounts. Generates HTML report. Use when user says 'instagram report', 'instagram metrics', or any reference to Instagram performance analysis.
.claude/skills/evolution-foundation-social-instagram-report/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-08 | ✗→✓ | ▲ Improved | -43% | 0% |
| case-09 | ✗→✓ | ▲ Improved | -56% | 0% |
| case-10 | ✗→✓ | ▲ Improved | -65% | 0% |
| case-11 | ✗→✓ | ▲ Improved | -45% | 0% |
| case-13 | ✗→✓ | ▲ Improved | 34% | 0% |
Routine that pulls data from Instagram via /int-instagram and generates an HTML performance report.
Always respond in English.
Para cada conta Instagram configurada:
bashpython3 {project-root}/.claude/skills/int-instagram/scripts/instagram_client.py summary python3 {project-root}/.claude/skills/int-instagram/scripts/instagram_client.py recent_posts [account] 20 python3 {project-root}/.claude/skills/int-instagram/scripts/instagram_client.py account_insights [account]
Read previous report from workspace/social/reports/instagram/ if it exists. Calculate deltas de seguidores, engagement, impressões.
Per account:
Use template .claude/templates/html/custom/social-analytics-report.html with {{REPORT_TYPE}} = "Instagram".
workspace/social/reports/instagram/[C] YYYY-MM-DD-instagram-report.htmlNotify: followers per account + average engagement + best post
| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-01 | fail→fail | 21,751 | 3,096 | -86% | 1 | 1 | 0% | 4,641 | 724 | -84% | 0 | 0 | — |
case-02 | fail→fail | 27,907 | 5,580 | -80% | 1 | 1 | 0% | 5,817 | 758 | -87% | 0 | 0 | — |
case-03 | fail→fail | 26,000 | 6,393 | -75% | 1 | 1 | 0% | 5,306 | 754 | -86% | 0 | 0 | — |
case-04 | pass→pass | 3,976 | 6,826 | +72% | 1 | 1 | 0% | 592 | 1,371 | +132% | 0 | 0 | — |
case-05 | pass→pass | 5,088 | 9,422 | +85% | 1 | 1 | 0% | 776 | 1,818 | +134% | 0 | 0 | — |
case-06 | fail→fail | 25,666 | 24,958 | -3% | 1 | 1 | 0% | 5,629 | 5,592 | -1% | 0 | 0 | — |
case-07 | fail→fail | 15,186 | 5,704 | -62% | 1 | 1 | 0% | 3,079 | 676 | -78% | 0 | 0 | — |
case-08 | fail→pass | 8,671 | 2,451 | -72% | 1 | 1 | 0% | 1,303 | 749 | -43% | 0 | 0 | — |
case-09 | fail→pass | 13,582 | 3,501 | -74% | 1 | 1 | 0% | 2,279 | 999 | -56% | 0 | 0 | — |
case-10 | fail→pass | 12,977 | 2,022 | -84% | 1 | 1 | 0% | 2,004 | 696 | -65% | 0 | 0 | — |
case-11 | fail→pass | 14,101 | 5,564 | -61% | 1 | 1 | 0% | 2,399 | 1,315 | -45% | 0 | 0 | — |
case-12 | fail→fail | 11,824 | 2,088 | -82% | 1 | 1 | 0% | 1,893 | 633 | -67% | 0 | 0 | — |
case-13 | fail→pass | 3,130 | 1,454 | -54% | 1 | 1 | 0% | 413 | 555 | +34% | 0 | 0 | — |
case-14 | fail→pass | 4,437 | 1,792 | -60% | 1 | 1 | 0% | 600 | 565 | -6% | 0 | 0 | — |
case-15 | fail→pass | 4,199 | 1,796 | -57% | 1 | 1 | 0% | 570 | 631 | +11% | 0 | 0 | — |
case-16 | fail→pass | 9,780 | 2,291 | -77% | 1 | 1 | 0% | 1,567 | 639 | -59% | 0 | 0 | — |
case-17 | fail→pass | 12,491 | 2,878 | -77% | 1 | 1 | 0% | 1,867 | 815 | -56% | 0 | 0 | — |
case-18 | pass→pass | 12,188 | 5,014 | -59% | 1 | 1 | 0% | 1,978 | 1,204 | -39% | 0 | 0 | — |
case-19 | fail→pass | 14,686 | 5,492 | -63% | 1 | 1 | 0% | 2,504 | 1,175 | -53% | 0 | 0 | — |
case-20 | fail→pass | 5,828 | 1,880 | -68% | 1 | 1 | 0% | 966 | 649 | -33% | 0 | 0 | — |
case-21 | pass→pass | 8,241 | 4,152 | -50% | 1 | 1 | 0% | 1,405 | 982 | -30% | 0 | 0 | — |
case-22 | pass→pass | 14,489 | 4,957 | -66% | 1 | 1 | 0% | 2,340 | 1,103 | -53% | 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 20 counted toward the lift figure. The other 2 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 20 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.