Rolling 30-Day Metrics Report
Trailing 30 days vs the prior period for any metric, with fair comparisons: complete days, weekday mix, small bases, one-off spikes.
Before & after
Same prompt, same agent — the only difference is the skill.
To give you a good summary of your social performance, I'd need to know which platforms you're tracking—Instagram, TikTok, YouTube, Twitter? And are you interested in engagement metrics, follower growth, or both? I could pull together some numbers if you have them handy, or we could look at what you remember about your posting activity. It would help to know what you consider success. What are you trying to improve or track?
30-DAY SOCIAL SUMMARY (July 1–31) FOLLOWER GROWTH Instagram: +240 (+2.1% growth; trend: steady) TikTok: +890 (+4.3% growth; trend: accelerating) YouTube: +45 (+0.8% growth; trend: flat) TOP PERFORMERS TikTok "side hustle wins" video: 45K views, 1.2K shares Instagram Reel "budgeting fails": 3.2K likes (15% above average) YouTube "investing 101": 12K views, 98 min watch time ESSENTIAL CHANGES TikTok engagement doubled when you posted 2x daily (July 15–22) Instagram Reels outperformed carousel posts 3:1 YouTube avg watch duration dropped 18% (editing changes in videos 8–10 likely cause) RECOMMENDATIONS → Increase TikTok frequency from 1x to 2x daily (sustain July 15–22 performance) → Revert YouTube editing style for next batch (return to 12-min videos; cut 15-min format) → Shift Instagram Stories from 2x to 3x daily (currently under-leveraged) NEXT MONTH TARGET: TikTok 1.2K followers (1.3% stretch from current growth rate)
About this skill
A monthly-style metrics snapshot you can rerun any day and still compare cleanly. It reports what changed over the last 30 days and whether it is a trend or a one-off.
What it does
- Locks metric definitions and window dates so every run matches the last
- Ends the window at the last complete day and flags data that may still be revised
- Checks weekday mix between windows and offers a 28-day comparison when it matters
- Recomputes rates from totals, shows bases, and skips misleading percentages on tiny numbers
- Separates one-off spikes and mix shifts from real trends
What you get
A fixed-format report: headline, metrics table with current, prior, and change, what moved and why, data notes, and a definitions block to reuse next time.
Best for
Founders, operators, and marketers who check signups, revenue, churn, traffic, or support volume every month.
SKILL.md preview
---
name: last-30-days
description: Produce a rolling 30-day metrics report from any data you point it at - analytics, revenue, signups, churn, support tickets, usage logs - compared with the prior period in a fixed, repeatable format, with the comparison traps handled (uneven weekday mix, incomplete recent days, tiny bases, changed definitions, one-off spikes). Use when the user says "last 30 days of signups", "how did the past month go?", "30-day report", "trailing month vs the month before", "monthly metrics summary", "run the rolling report again", "metric jumped, is something wrong?", or pastes a CSV or export and asks what changed recently.
---
# Rolling 30-Day Metrics Report
… (sign up to view the full skill)More research & data skills
View all Research & Data skills →Source-Reconciled Research Brief
Turn supplied links into a concise brief with claim-level citations, reconciled source conflicts, and explicit evidence gaps.
Source-Traced Research Bundle
Compile many sources into one bundle where every claim is atomic, sourced, dated, tiered, and conflict-checked, in Markdown or JSON.
A/B Test Power and Validity Designer
Exact A/B sample sizes and MDE with math shown, plus the traps: unit mismatch, multiple variants, peeking, guardrail power, and SRM.
Research Routing and Cited Briefings
Route research to the right method, then produce a cited briefing with evidence gaps, disagreements, and a source audit.