agentsclimarketplace

Client performance review

Skill intelligems-io/intelligems-mcp-skills/skills/client-performance-review

Ready-to-install Agent Skills for analyzing Intelligems experiments, segments, pricing, and reporting through MCP and API.

Install
npx -y skills add intelligems-io/intelligems-mcp-skills --skill client-performance-review

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

One thing to look at

  • 0 stars0 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.

What its author says it does

Copied from the file, not written here

Use when preparing a monthly or quarterly Intelligems performance review for an agency client, customer, account, or stakeholder meeting.

The file declares its own license as MIT. That is the author’s claim about this one file, and it is not the same thing as the license GitHub reports for the repository, which is listed with the other numbers below.

SKILL.md

1.7 KB, 327 tokens by cl100k_base, as published. Nobody here has run it

Client Performance Review

Use this skill to turn completed and active Intelligems tests into a meeting-ready performance review.

Steps

  1. Resolve organization, review period, and audience for the review.
  2. Search for completed tests in the period with search_experiences or search_experiments using status: "ended".
  3. Include running tests only if the user asks or they materially affect the review.
  4. Analyze each completed test with get_experience, get_experience_metrics_config, and analyze_experience.
  5. Pull segment breakdowns only for tests where they change the story.
  6. Summarize revenue, profit, and learning impact separately.

Review Structure

Return:

  1. Executive summary.
  2. Completed tests: winners, losers, inconclusive tests.
  3. Estimated revenue or profit impact where supported by data.
  4. Strategic learnings by theme.
  5. Tests that should be implemented, repeated, extended, or retired.
  6. Recommended next tests.
  7. Appendix with organization, dates, experience IDs, and caveats.

Quality Bar

  • Explain what happened, why it matters, and what the client should do next.
  • Keep the narrative honest if the data is inconclusive.
  • Do not hide tests with negative results. Convert them into learnings when possible.

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.

Gives 0 of the 12 instructions most review quality skills give in 327 tokens

Counted across 1,048 of the 1,783 authors here whose files we hold, read 2026-08-06

  • ask questions one at a timein 82 of 1048, across 54 files
  • provide a recommended answer for each questionin 73 of 1048, across 45 files
  • explore the codebase instead of asking answerable questionsin 66 of 1048, across 37 files
  • resolve dependencies between decisions one-by-onein 42 of 1048, across 15 files
  • interview the user relentlessly about the planin 39 of 1048, across 12 files
  • order findings by severityin 29 of 1048
  • resolve each branch of the decision treein 28 of 1048, across 5 files
  • run a grilling sessionin 26 of 1048, across 5 files
  • update CONTEXT.md immediately when a term is resolvedin 26 of 1048, across 9 files
  • propose precise canonical terms for vague languagein 25 of 1048, across 6 files
  • create documentation files lazilyin 24 of 1048, across 5 files
  • use the domain-modeling skillin 22 of 1048, across 3 files

Said here and by no other author read

  • resolve the organization and review period first
  • summarize revenue, profit, and learning impact separately
  • explain what happened, why it matters, and next steps
  • categorize completed tests by outcome
  • include estimated revenue or profit impact where supported
  • group strategic learnings by theme

Grouped from the skills themselves: near-identical wordings counted once, and counted by distinct author, so one author publishing three of these counts once. Length counted with cl100k_base; the agent that loads this file may tokenize it differently.

Keep looking

Skills are one crate of 328,083. Ordering is by how many stacks a row turns up in, so the top of any crate is what has actually been picked rather than what has the most stars.