agentsclimarketplace

Testing strategy health check

Skill intelligems-io/intelligems-mcp-skills/skills/testing-strategy-health-check

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 testing-strategy-health-check

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 a user wants to evaluate the health of an Intelligems testing program, including velocity, win rate, test mix, learnings, and coverage gaps.

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, 319 tokens by cl100k_base, as published. Nobody here has run it

Testing Strategy Health Check

Use this skill to assess whether an Intelligems testing program is producing useful learning and profit.

Steps

  1. Resolve organization and analysis period.
  2. Pull completed, active, paused, and pending tests as needed with search_experiences or search_experiments.
  3. Categorize tests by type, theme, funnel area, metric, and status.
  4. Analyze outcomes for completed tests.
  5. Identify bottlenecks: too few launches, too many inconclusive tests, narrow test mix, missing profit metrics, or unimplemented winners.

Scorecard

Use a simple scorecard:

  • Velocity: tests launched and completed per period.
  • Quality: percent with clear hypothesis and metric fit.
  • Win rate: winners, losers, inconclusive.
  • Profit orientation: how often profit metrics are used.
  • Coverage: pages, audiences, offers, pricing, content, and personalization.
  • Follow-through: winners implemented and learnings reused.

Output

Return:

  1. Health grade with rationale.
  2. Scorecard.
  3. Biggest constraints.
  4. Recommended operating changes.
  5. Next tests or process improvements.
  6. Source appendix.

Be candid. A healthy program can have losses if it is learning quickly and avoiding profit traps.

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.

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.