agentleFS
intelligems-iointelligems-io/intelligems-mcp-skills/skills/weekly-test-pulse/SKILL.md

weekly-test-pulse

Skill0 starsChanged 5 months agoMITView on GitHub

Use when a brand operator or agency asks for a quick weekly status report on running Intelligems tests and recommended next actions.

The file

We split this skill into the rules it gives an agent

7 rules. About 0 are common, 5 are distinctive, and 2 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈5

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 2

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Use this skill for a concise status report on tests that are currently running.

    line 9
  2. Very specific:

    Use get_experience_metrics_config when you need the correct analytics view type or primary metric.

    line 16
  3. Distinctive:

    Do not recommend ending a test solely from early conversion lift.

    line 21
  4. Distinctive:

    Check RPV, GPV, net revenue, AOV, and confidence when available.

    line 22
  5. Distinctive:

    Call out tests with low traffic, uneven traffic allocation, missing profit metrics, or suspicious segment concentration.

    line 23
  6. Very specific:

    If a lifecycle action is needed, recommend it but do not run experience_action without explicit approval.

    line 24
  7. Distinctive:

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

    line 28

≈ “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

Weekly Test Pulse

Use this skill for a concise status report on tests that are currently running.

Steps

  1. Resolve the organization. If ambiguous, use list_organizations and ask for the target.
  2. Find running tests with search_experiments or search_experiences using status: "started".
  3. For each running test, fetch details with get_experience and metrics with analyze_experience.
  4. Use get_experience_metrics_config when you need the correct analytics view type or primary metric.
  5. Group tests into: likely winner, likely loser, inconclusive, needs more data, and needs attention.

Watchouts

  • Do not recommend ending a test solely from early conversion lift.
  • Check RPV, GPV, net revenue, AOV, and confidence when available.
  • Call out tests with low traffic, uneven traffic allocation, missing profit metrics, or suspicious segment concentration.
  • If a lifecycle action is needed, recommend it but do not run experience_action without explicit approval.

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.

Output

Return:

  1. One-paragraph pulse summary.
  2. Table of running tests with status, leading variation, metric direction, confidence, and recommendation.
  3. Risks or anomalies.
  4. Exact next actions for the coming week.
  5. Source appendix with organization, date range, and tool calls.

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.