agentsclimarketplace

Profit trap detection

Skill intelligems-io/intelligems-mcp-skills/skills/profit-trap-detection

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 profit-trap-detection

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 find Intelligems tests where conversion rate improved but revenue per visitor, gross profit, or another profit metric declined.

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

Profit Trap Detection

Use this skill to catch harmful winners before they are implemented.

Steps

  1. Resolve organization and date range.
  2. Search ended and active experiments relevant to the request.
  3. For each test, fetch overview metrics with analyze_experience.
  4. Compare conversion rate, RPV, GPV, AOV, net revenue, and confidence where available.
  5. Investigate audience breakdowns if the aggregate result hides a segment problem.

Profit Trap Definition

Flag a test when:

  • Conversion rate increases but RPV decreases.
  • Conversion rate increases but GPV or margin proxy decreases.
  • Order volume increases but AOV drops enough to reduce value.
  • A discount, offer, or shipping change wins on orders but loses on profit.
  • A strong segment winner masks broad underperformance.

Output

Return:

  1. Clear list of confirmed, likely, and possible profit traps.
  2. Metric evidence for each trap.
  3. Recommended action: do not implement, segment rollout, extend test, or investigate margin inputs.
  4. Missing data that would change confidence.
  5. Appendix with source tool calls and experience IDs.

Never call a result safe if profit metrics are missing. Mark it as "conversion-only evidence" instead.

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.