agentleFS
Sign inStart free
milad-ahmdmilad-ahmd/agent-skills/skills/social-analytics-reporter/SKILL.md

social-analytics-reporter

Skill5 starsChanged 18 days agoMITView on GitHub

Turns raw social media analytics exports (Instagram Insights, TikTok Analytics, YouTube Studio, LinkedIn, X, Meta Ads CSV or screenshots) into a clear performance report with KPIs, trends, top and bottom content analysis, the reasons behind them, and prioritized recommendations. Includes a Python script to summarize CSV exports. Use when the user shares social media analytics, asks for a monthly social report, or asks "what's working on my socials".

The file

We split this skill into the rules it gives an agent

3 rules. About 0 are common, 3 are distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈3

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 0

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Ask for exports: CSV from YouTube Studio, TikTok, Meta Business Suite, LinkedIn or a scheduler, or screenshots.

    line 12
  2. Distinctive:

    Never invent or extrapolate numbers.

    line 45
  3. Distinctive:

    Keep it short enough that a busy founder reads it.

    line 47

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Social Analytics Reporter

From a pile of numbers to "here's what to do next week".

1. Collect data

Ask for exports: CSV from YouTube Studio, TikTok, Meta Business Suite, LinkedIn or a scheduler, or screenshots. For CSVs, run the helper to get a quick numerical summary:

python3 scripts/summarize.py export.csv                # auto-detects numeric columns
python3 scripts/summarize.py export.csv --sort views   # rank posts by a metric

2. KPIs by goal

GoalPrimary KPIs
AwarenessReach, impressions, non-follower reach %, views, follower growth
EngagementEngagement rate ((likes+comments+shares+saves)/reach), saves, shares, comments
VideoAvg watch time, % completion, retention, rewatches
Traffic / conversionProfile visits, link clicks, CTR, signups, sales, CPA/ROAS (ads)

Calculate rates, not just totals. Compare with the previous period and the account's own average, not with generic benchmarks.

3. Report (social-report-<period>.md)

# Social Report — <period>
## TL;DR (3 bullets: win, problem, next action)
## KPI scorecard (metric | this period | last period | Δ% | status 🟢🟡🔴)
## Platform breakdown
## Top 5 & bottom 5 posts — and WHY (hook, format, topic, timing, length)
## Patterns (what formats/topics/times over-perform)
## Recommendations — do more / stop / test (with hypothesis + success metric)

Rules

  • Never invent or extrapolate numbers. If data is missing, say so.
  • Mark correlations as correlations, and suggest a test to confirm the cause.
  • Keep it short enough that a busy founder reads it.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

Check your setup, free