The AI Web
Test iteration logo

Skills

Test iteration

A test finished. Get ten specific things to try next, each with what changes, why it might work, and what success would look like, grounded in what the last one showed.

updated 02 Sept·Claude Code skill, reads your whole knowledge base first

When do you reach for Test iteration?

Reach for it at the decision point of every test, including the losers. A loss tells you the mechanism is real and pointed the wrong way, which is a better starting point than a blank page.

What makes an iteration idea usable?

Three things, and an idea missing any of them goes back. What specifically changes, why it might work, and what success looks like as a metric and a direction. The difference is the gap between try different copy and test an outcome-led CTA because the original tested a feature rather than a benefit. One of those can be built on Monday.

Where do ten ideas come from?

Eight angles, so the list is genuinely different rather than one idea wearing eight hats. A list of seven copy tweaks means the angles were skipped.

  • Intensity: dial the same change up or down. Was it too subtle, or too much?
  • Segment: the same change for a different audience, device or traffic source.
  • Timing: the same change at a different point in the visit.
  • A different route: same problem, another solution entirely.
  • Supporting elements: add or remove what sits around the change.
  • Message: a different value proposition or tone.
  • Visual weight: hierarchy, prominence, contrast.
  • The gaps: test what the last one failed to tell you.

What does grounding actually mean?

Reading everything first. Every past learning, every note on the audience, every documented failure mode, before a single idea gets written. Then each reason carries three parts: the connection to what the last test showed, the supporting evidence, and the mechanism, which is the sentence explaining why this particular change should produce a different result. Without that sentence it is a guess with a citation stapled to it.

What you copy

One block, ready to paste. Nothing else to install unless the block says so.

1---
2name: test-iteration
3description: Generate around ten specific iteration ideas for a concluded A/B
4 test, grounded in the hypothesis, the result and everything already known.
5 Use when a test has finished, whether it won, lost or went nowhere.
6argument-hint: [test name or result]
7---
8
9# Test iteration
10
11A finished test is an input, not a conclusion. This turns one result into the
12next ten things worth trying, with a reason attached to each.
13
14## Before generating anything
15
16Gather four things: the result (won, lost, inconclusive), the original
17hypothesis, what was learned and what was not, and which metrics moved.
18
19Then read the whole knowledge base, not a sample of it: every past learning,
20every note on the audience, every documented failure mode. Ideas that ignore
21what is already known are how a team runs the same test twice with a different
22button colour.
23
24## What separates a strong idea from a weak one
25
26| Weak | Strong |
27| --- | --- |
28| "Try different copy" | "Test an outcome-led CTA, because the original tested a feature rather than a benefit" |
29| "Make it bigger" | "Increase the CTA by 40% and add whitespace, since the original may have been lost in visual noise" |
30| "Test on mobile" | "Mobile-only test with the CTA in the thumb zone, since desktop won and mobile was flat" |
31
32Every idea answers three questions: what specifically changes, why it might
33work, and what success would look like.
34
35## Eight angles to generate across
36
371. **Intensity.** Dial the change up or down. Was it too subtle, or too much?
382. **Segment.** A different audience: device, new against returning, source.
393. **Timing.** The same change at a different moment in the visit.
404. **A different route.** Same problem, another solution entirely.
415. **Supporting elements.** Add or remove what sits around the change.
426. **Message.** A different value proposition or tone.
437. **Visual weight.** Hierarchy, prominence, contrast.
448. **The gaps.** Test what the last one failed to tell you.
45
46## Reasoning depth
47
48Each "why" carries three parts: the connection to what the last test showed,
49the supporting evidence (a past test, a documented behaviour, research), and
50the mechanism, which is the sentence explaining why this specific change should
51produce a different result.
52
53Without the mechanism it is a guess with a citation attached.
54
55## Output
56
57```
58[Test] - iteration ideas
59
60Original: [what ran]
61Result: [won / lost / inconclusive] - [headline metric]
62Learning: [one or two sentences]
63
64(1) [Title in sentence case]
65 Change: [what specifically changes]
66 Why: [connection, evidence, mechanism]
67 Success: [metric and direction]
68
69(2) ... through (10)
70
71Test first: (1), (2) - [why these]
72Worth exploring: (3), (4) - [why]
73If there is room: (5) to (10) - [why]
74```
75
76Number ideas as (1), (2), (3) rather than 1. 2. 3. - it survives being pasted
77into a tracker that mangles ordered lists.
78
79## Before you finish
80
81Check each idea: specific enough to build without another conversation, real
82reasoning rather than "let's try it", connected to what the last test showed,
83measurable, and not a repeat of something already run. That last one means
84running the learnings check over your own output.

Free to use in your own work, paid work included, no attribution required. Not for repackaging into a product you sell. Full terms.

Taggedclaude codea/b testingconversion

More in skills

Back to every skills entry.