agentleFS
intelligems-iointelligems-io/intelligems-mcp-skills/skills/segment-intelligence/SKILL.md

segment-intelligence

Skill0 starsChanged 5 months agoMITView on GitHub

Use when a user asks how Intelligems test performance differs by device, visitor type, country, traffic source, source site, or landing page.

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:

    Use this skill to identify customer segments that consistently overperform or underperform.

    line 9
  2. Distinctive:

    Do not overstate tiny segments.

    line 42
  3. Distinctive:

    Use only the user's authenticated MCP or API context.

    line 46

≈ “Common” is an estimate: at least 1 in 5 of the 364,980 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

Segment Intelligence

Use this skill to identify customer segments that consistently overperform or underperform.

Segment Tools

Current public MCP docs include:

  • get_audience_by_country
  • get_audience_by_device
  • get_audience_by_visitor_type
  • get_audience_by_source_channel
  • get_audience_by_source_site
  • get_audience_by_landing_page

You can also use analyze_experience with view: "audience" and the appropriate audience field when the active client exposes that path.

Steps

  1. Resolve organization, experience scope, and date range.
  2. Identify relevant tests with search_experiences, search_experiments, or explicit experience IDs from the user.
  3. Pull overview metrics first so segment findings have context.
  4. Pull only the segment dimensions needed for the user question.
  5. Compare segment behavior across tests to separate one-off noise from repeated patterns.

Output

Return:

  1. Strongest segment insights.
  2. Segment table with metric direction, confidence, and sample caveats.
  3. Segment-specific recommendations.
  4. Tests to run next if the pattern is actionable.
  5. Appendix with dimensions queried, tool calls, and any missing metrics.

Do not overstate tiny segments. If sample size is thin, label the finding as directional.

Data Safety

Use only the user's authenticated MCP or API context. Do not save raw responses, exports, graph URLs, order data, customer data, or private store identifiers to the repository. Summarize findings and include experience IDs only when needed for the user's workflow.

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.