ab-test-generator

Name: ab-test-generator
Author: Affitor

4installs184forks

How to install ab-test-generator?

affitor/affiliate-skills/ab-test-generator

$npx -y skills add Affitor/affiliate-skills --skill ab-test-generator

Installs into the current project.

Summary

Generate A/B test variants for affiliate content. Triggers on: "create A/B test", "test my headline", "optimize my CTA", "generate variants", "split test ideas", "improve click-through rate", "test my landing page copy", "headline alternatives", "CTA variations", "which version i

Files · 1

View on GitHub

SKILL.md

1	# A/B Test Generator
2
3	Generate A/B test variants for affiliate content — headlines, CTAs, landing page sections, email subject lines, and social post hooks. Each variant includes a hypothesis explaining why it might outperform the original. Output is a Markdown document with the original, variants, hypotheses, and a test plan.
4
5	## Stage
6
7	S6: Analytics — Small changes in headlines and CTAs can swing conversion rates by 20-50%. A/B testing is how professional affiliates systematically find what converts best. This skill removes the guesswork by generating theory-driven variants using proven copywriting frameworks.
8
9	## When to Use
10
11	- User wants to improve conversion rates on existing content
12	- User has a headline, CTA, or email subject line and wants alternatives
13	- User says "test my headline", "optimize my CTA", "A/B test ideas"
14	- User has a landing page section that isn't converting
15	- User wants to compare different messaging approaches
16	- Chaining from S2-S5: take any content output and generate test variants
17
18	## Input Schema
19
20	```yaml
21	original: string # REQUIRED — the content to test (headline, CTA, paragraph,
22	# email subject line, or full social post)
23
24	content_type: string # REQUIRED — "headline" \| "cta" \| "landing_section"
25	# \| "email_subject" \| "social_hook"
26
27	goal: string # OPTIONAL — "clicks" \| "signups" \| "purchases"
28	# Default: "clicks"
29
30	num_variants: number # OPTIONAL — number of variants to generate (2-5)
31	# Default: 3
32
33	audience: string # OPTIONAL — who sees this content
34	# (e.g., "SaaS founders", "content creators")
35
36	product: string # OPTIONAL — product being promoted
37	```
38
39	Chaining context: If S2-S5 content exists in conversation, the user can reference it: "test the headline from my blog post" or "generate CTA variants for my landing page."
40
41	## Workflow
42
43	### Step 1: Analyze Original Content
44
45	Break down the original into components:
46	- Emotional angle: What emotion does it trigger? (curiosity, fear, desire, urgency)
47	- Specificity: How specific vs vague?
48	- Structure: Question, statement, command, statistic?
49	- Framework: Which copywriting framework does it follow? (PAS, AIDA, 4U, BAB)
50
51	### Step 2: Identify Testable Elements
52
53	Determine what to vary:
54	- Emotional angle (switch from curiosity to urgency)
55	- Specificity (add numbers, remove vagueness)
56	- Structure (question vs statement)
57	- Length (shorter vs longer)
58	- Power words (swap key words for stronger alternatives)
59	- Social proof (add or remove)
60
61	### Step 3: Generate Variants
62
63	Create `num_variants` alternatives, each using a different approach:
64	- Variant A: Different emotional angle
65	- Variant B: Different structure/format
66	- Variant C: Different specificity level
67	- Additional variants explore social proof, urgency, or contrarian angles
68
69	Each variant must:
70	- Preserve the core message and product reference
71	- Preserve any FTC disclosure from the original
72	- Be a realistic alternative (not just a word swap)
73
74	### Step 4: Write Hypotheses
75
76	For each variant, explain:
77	- What was changed and why
78	- Which copywriting principle supports the change
79	- What behavior change is expected (e.g., "Higher CTR because questions create open loops")
80
81	### Step 5: Suggest Test Plan
82
83	Recommend:
84	- Sample size needed (minimum 100 impressions per variant for social, 500 for landing pages)
85	- Test duration (7-14 days minimum)
86	- What metric to track (CTR, conversion rate, revenue per visitor)
87	- When to declare a winner (95% statistical significance or practical significance threshold)
88
89	### Step 6: Self-Validation
90
91	Before presenting output, verify:
92
93	- [ ] 3-5 distinct variants generated (not just word swaps)
94	- [ ] Each hypothesis grounded in a copywriting principle or framework
95	- [ ] Sample size calculation is present and realistic
96	- [ ] Test duration is ≥7 days minimum
97	- [ ] Winner criteria defined with statistical significance threshold
98
99	If any check fails, fix the output before delivering. Do not flag the checklist to the user — just ensure the output passes.
100
101	## Output Schema
102
103	```yaml
104	output_schema_version: "1.0.0" # Semver

People who liked this also viewed

6 picks

Type

ab-test-generator

4installs184forks

View on GitHub

How to install ab-test-generator?

affitor/affiliate-skills/ab-test-generator

$npx -y skills add Affitor/affiliate-skills --skill ab-test-generator

Installs into the current project.

Summary

Files · 1

View on GitHub

SKILL.md

1	# A/B Test Generator
2
3	Generate A/B test variants for affiliate content — headlines, CTAs, landing page sections, email subject lines, and social post hooks. Each variant includes a hypothesis explaining why it might outperform the original. Output is a Markdown document with the original, variants, hypotheses, and a test plan.
4
5	## Stage
6
7	S6: Analytics — Small changes in headlines and CTAs can swing conversion rates by 20-50%. A/B testing is how professional affiliates systematically find what converts best. This skill removes the guesswork by generating theory-driven variants using proven copywriting frameworks.
8
9	## When to Use
10
11	- User wants to improve conversion rates on existing content
12	- User has a headline, CTA, or email subject line and wants alternatives
13	- User says "test my headline", "optimize my CTA", "A/B test ideas"
14	- User has a landing page section that isn't converting
15	- User wants to compare different messaging approaches
16	- Chaining from S2-S5: take any content output and generate test variants
17
18	## Input Schema
19
20	```yaml
21	original: string # REQUIRED — the content to test (headline, CTA, paragraph,
22	# email subject line, or full social post)
23
24	content_type: string # REQUIRED — "headline" \| "cta" \| "landing_section"
25	# \| "email_subject" \| "social_hook"
26
27	goal: string # OPTIONAL — "clicks" \| "signups" \| "purchases"
28	# Default: "clicks"
29
30	num_variants: number # OPTIONAL — number of variants to generate (2-5)
31	# Default: 3
32
33	audience: string # OPTIONAL — who sees this content
34	# (e.g., "SaaS founders", "content creators")
35
36	product: string # OPTIONAL — product being promoted
37	```
38
39	Chaining context: If S2-S5 content exists in conversation, the user can reference it: "test the headline from my blog post" or "generate CTA variants for my landing page."
40
41	## Workflow
42
43	### Step 1: Analyze Original Content
44
45	Break down the original into components:
46	- Emotional angle: What emotion does it trigger? (curiosity, fear, desire, urgency)
47	- Specificity: How specific vs vague?
48	- Structure: Question, statement, command, statistic?
49	- Framework: Which copywriting framework does it follow? (PAS, AIDA, 4U, BAB)
50
51	### Step 2: Identify Testable Elements
52
53	Determine what to vary:
54	- Emotional angle (switch from curiosity to urgency)
55	- Specificity (add numbers, remove vagueness)
56	- Structure (question vs statement)
57	- Length (shorter vs longer)
58	- Power words (swap key words for stronger alternatives)
59	- Social proof (add or remove)
60
61	### Step 3: Generate Variants
62
63	Create `num_variants` alternatives, each using a different approach:
64	- Variant A: Different emotional angle
65	- Variant B: Different structure/format
66	- Variant C: Different specificity level
67	- Additional variants explore social proof, urgency, or contrarian angles
68
69	Each variant must:
70	- Preserve the core message and product reference
71	- Preserve any FTC disclosure from the original
72	- Be a realistic alternative (not just a word swap)
73
74	### Step 4: Write Hypotheses
75
76	For each variant, explain:
77	- What was changed and why
78	- Which copywriting principle supports the change
79	- What behavior change is expected (e.g., "Higher CTR because questions create open loops")
80
81	### Step 5: Suggest Test Plan
82
83	Recommend:
84	- Sample size needed (minimum 100 impressions per variant for social, 500 for landing pages)
85	- Test duration (7-14 days minimum)
86	- What metric to track (CTR, conversion rate, revenue per visitor)
87	- When to declare a winner (95% statistical significance or practical significance threshold)
88
89	### Step 6: Self-Validation
90
91	Before presenting output, verify:
92
93	- [ ] 3-5 distinct variants generated (not just word swaps)
94	- [ ] Each hypothesis grounded in a copywriting principle or framework
95	- [ ] Sample size calculation is present and realistic
96	- [ ] Test duration is ≥7 days minimum
97	- [ ] Winner criteria defined with statistical significance threshold
98
99	If any check fails, fix the output before delivering. Do not flag the checklist to the user — just ensure the output passes.
100
101	## Output Schema
102
103	```yaml
104	output_schema_version: "1.0.0" # Semver

People who liked this also viewed

6 picks

Type