agentleFS
Sign inStart free
Ootto-AIOotto-AI/claude-content-skills/skills/social-analytics-report/SKILL.md

social-analytics-report

Skill417 starsChanged 3 months agoMITView on GitHub

Use when you need to turn supplied social performance data into a decision about what to keep, test, change, or stop. Trigger phrases include "report on this campaign", "what worked on social?", "analyse these post results", "make a weekly social report", and "what should we do next from these metrics?". Do not use this to invent data access, claim causation from a dashboard, or replace a campaign brief; use campaign-brief to define success before launch and launch-retrospective for the broader after-action review.

2 other projects use a version of this.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

7 rules. About 0 are common, 7 are distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈7

    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 the date range, channels, posts or campaigns, metric definitions, collection method, target or baseline, and any known changes in …

    line 12
  2. Distinctive:

    Never claim causation from correlation or a single post.

    line 28
  3. Distinctive:

    Do not compare unlike metrics, date windows, paid and organic activity, or posts at different maturity without saying so.

    line 29
  4. Distinctive:

    Keep raw data, calculated rates, and interpretation distinguishable.

    line 30
  5. Distinctive:

    Do not hide low-performing or incomplete data to make a narrative look cleaner.

    line 31
  6. Distinctive:

    Never fabricate access to native analytics, ad accounts, or conversion systems.

    line 32
  7. Distinctive:

    Use campaign-brief and utm-campaign-plan before publishing so the report has a decision and attribution plan.

    line 45

≈ “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 Report

Make an honest operational report from the metrics the team actually has, with context, uncertainty, and a next decision.

1. Establish what the data can answer

Ask for the date range, channels, posts or campaigns, metric definitions, collection method, target or baseline, and any known changes in spend, audience, format, or distribution. If definitions differ across channels, do not silently compare the raw totals.

2. Check the data before interpreting it

Identify missing rows, partial reporting windows, duplicate posts, changed tracking, or metrics collected at different ages. Label the report's data boundary. Separate direct observations from hypotheses about why something happened.

3. Read outcomes against the intended job

Group results by the job each post or channel was assigned: awareness, education, discussion, qualified traffic, conversion assistance, or creator partnership learning. Compare like with like. Look for repeatable patterns in message, format, audience context, and distribution rather than choosing one winner by impressions.

4. Recommend the next smallest test

Return a decision table: observation, confidence, likely explanation, action, owner, and evidence needed next. State what not to conclude. Recommend a bounded test that preserves the campaign claim and measurement method so the next report can actually compare it.

Hard rules

  • Never claim causation from correlation or a single post.
  • Do not compare unlike metrics, date windows, paid and organic activity, or posts at different maturity without saying so.
  • Keep raw data, calculated rates, and interpretation distinguishable.
  • Do not hide low-performing or incomplete data to make a narrative look cleaner.
  • Never fabricate access to native analytics, ad accounts, or conversion systems.

Failure modes

FailureDo this instead
A high-impression post is declared successfulJudge it against the job and downstream evidence it was intended to influence.
A report lists metrics but makes no decisionEnd with one keep, one test, one change, and their owners.
Platform totals are compared as if identicalNormalize the question or report each channel separately.
The team changes five things at onceChoose the smallest observable test and hold other conditions steady where possible.

Where it sits

Use campaign-brief and utm-campaign-plan before publishing so the report has a decision and attribution plan. Use this skill during a campaign for operating reviews. Use launch-retrospective after the reporting window to combine results, qualitative evidence, and process lessons.

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