CtrlK
BlogDocsLog inGet started
Tessl Logo

craft-experiment-readout

Summarize experiment results, call a winner, and draft a stakeholder-ready recommendation. Use when an A/B test is complete and you need to communicate results.

74

Quality

Does it follow best practices?

Impact

No eval scenarios have been run

SecuritybySnyk

Passed

No known issues

SKILL.md
Quality
Evals
Security

Quality

Content

100%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The content is concise, actionable, and well-structured, providing a complete copy-paste prompt template with clear sequencing and an input checkpoint. It appropriately avoids over-explaining concepts Claude already knows.

DimensionReasoningScore

Conciseness

The body is lean: a single prompt template with a numbered structure and four short tips, with no padding explaining concepts Claude already knows. Every section earns its place.

3 / 3

Actionability

The prompt template is copy-paste ready with concrete numbered sections, explicit instructions ("Call out statistical significance", "Ship, iterate, or kill"), and clear input placeholders, giving executable guidance rather than abstract direction.

3 / 3

Workflow Clarity

A clear 10-step sequence covers the readout (1-7) then the stakeholder comms (8-10), and includes an input-validation checkpoint ("If the above is blank, ask the user"). This is not a destructive or batch operation, so missing retry feedback loops do not cap the score.

3 / 3

Progressive Disclosure

This is a simple single-purpose skill under 50 lines with no bundle files, and the body is organized into clear Prompt Template and Tips sections, which satisfies the rubric's allowance for well-organized simple skills to score 3 without external references.

3 / 3

Total

12

/

12

Passed

Description

85%

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

The description is specific, complete, and clearly scoped to A/B test readouts with an explicit trigger clause. Its main weakness is trigger term breadth, covering only a couple of natural phrases rather than the full range users might say.

Suggestions

Broaden the trigger terms to include natural phrases users actually say, e.g. "experiment readout", "analyze this test", "did it win", or "share results with stakeholders".

Mention the ship/kill/iterate decision framing in the description to align the trigger with the recommendation step users often need.

DimensionReasoningScore

Specificity

"Summarize experiment results, call a winner, and draft a stakeholder-ready recommendation" lists multiple concrete actions, matching the anchor for listing several specific actions rather than naming a domain alone.

3 / 3

Completeness

It states both what the skill does (summarize, call a winner, draft a recommendation) and an explicit "Use when an A/B test is complete and you need to communicate results" trigger, clearly answering what and when.

3 / 3

Trigger Term Quality

"A/B test" and "communicate results" are natural phrases, but the description omits common variations users would say like "experiment readout", "analyze this test", or "did it win", so coverage is partial rather than strong.

2 / 3

Distinctiveness Conflict Risk

"Experiment results" and "A/B test" scoped with stakeholder communication define a clear niche with distinct triggers that would not commonly conflict with other skills.

3 / 3

Total

11

/

12

Passed

Validation

93%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

Total

15

/

16

Passed

Repository
amplitude/builder-skills
Reviewed

Table of Contents

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.