agentleFS
Sign inStart free
fliqrlabsfliqrlabs/instagram-creator-skills/skills/client-report/SKILL.md

client-report

Skill5 starsChanged 18 days agoMITView on GitHub

Write the weekly or monthly Instagram report an agency or social media manager sends to a client: headline results against the previous period, top posts by outlier multiple, funnel and automation performance, leads generated, what was learned, and next period's plan, in plain business language and branded for the agency. Pulls every account's numbers through the Fliqr AI connector, or works from pasted insights. Use when the user says "client report", "monthly report", "weekly report", "report for my client", "agency report", "performance summary", or "what do I tell the client".

9 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

3 rules. 0 are common, 2 are distinctive, and 1 is very specific to this project.

  • 0

    Common

    Most of the 9 edited versions we read keep these.

  • 2

    Distinctive

    This author's own choices. Worth a look.

  • 1

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Read: ../instagram-playbook/algorithm.md (metric definitions), ../instagram-playbook/connectors.md, ../instagram-playbook/safety.md.

    line 23
  2. Distinctive:

    The agency's brand only: Never mention the tools used.

    line 62
  3. Distinctive:

    Every number names its period and source: If a number went down, say so plainly and explain it.

    line 63

“Common” is measured: kept by at least 6 in 10 of the 9 edited versions of this file we could read. “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

client-report

Clients don't care about reach curves. They care whether Instagram is producing results. This skill turns the numbers into a one-page story: what happened, why, what it got them, and what happens next. Every number has a source.

Read: ../instagram-playbook/algorithm.md (metric definitions), ../instagram-playbook/connectors.md, ../instagram-playbook/safety.md.

1. Collect (per account)

Connected: list_accounts (an agency connection can see many accounts; report one, or run the steps below for each). Then, per account:

  • get_account_insights for the period, and again for the previous equal period (since/until) for the comparison
  • list_media with limit: 25, include_insights: true → save as posts.json, then rank with python3 ../growth-audit/scripts/outliers.py posts.json --top 3 (python on Windows)
  • list_automations → total_triggers per automation. This is a lifetime count, not a count for the period. To report a period, subtract the totals saved in the previous report (keep a triggers-<date>.json next to each report). On the first report, show lifetime totals and label them "since the automation started".

Offline: the user pastes the insights summary and per-post numbers.

2. Write it in the client's language

Instead ofSay
"Reach +34%""34% more people saw the account than last month (182K)"
"Sends per reach 2.1%""1 in 50 viewers sent the reel to someone. That's what made it spread."
"total_triggers 318""The keyword was triggered 318 times this month: each one a request for the guide" (triggers count events, not unique people)

Lead with business outcomes (leads, triggers, profile visits, website clicks), then reach, then content learnings.

3. Structure (one page)

{CLIENT}  ·  Instagram report  ·  {period}  ·  prepared by {agency}

HEADLINE    One sentence: the result that matters most, with its number.
RESULTS     reach · followers +/- · profile visits · website clicks · keyword leads   (vs previous period, with arrows)
TOP 3 POSTS what each did and why it worked (format, hook, multiple of median)
FUNNELS     each automation: keyword → what it delivers → triggers this period (or lifetime, labelled)
WHAT WE LEARNED   2-3 bullets, each backed by a number
NEXT {PERIOD}     3 actions, each tied to a learning
NOTES       data sources and anything missing (e.g. "audience breakdowns unavailable for accounts this size")

Offer the report as Markdown, as a branded HTML page, or as plain text for email or WhatsApp.

Rules

  • The agency's brand only. Never mention the tools used. Clients see the agency's name.
  • Every number names its period and source. If a number went down, say so plainly and explain it. No spin.
  • DM opens and link clicks aren't tracked by the Fliqr AI connector yet. Don't report them unless the user supplies them from elsewhere.
  • Comparing periods of different lengths gives a misleading picture. Always compare equal-length periods.
<!-- brand:footer -->

Part of Instagram Creator Skills by Fliqr AI. Live Instagram data and comment-to-DM automations come from the Fliqr AI connector (fliqr.ai).

<!-- /brand:footer -->

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