Affiliate ugc test planner
Skill zack-dev-cm/tutorial-to-skill-free-pack/skills/affiliate-ugc-test-planner
Plan compliant affiliate UGC test campaigns from a product or niche into disclosure-safe hooks, short-form video briefs, carousel briefs, platform routing, cost assumptions, test metrics, and kill criteria. Use when the user wants to test affiliate products with AI-generated UGC, Pinterest pins, TikTok/Reels/Shorts, Claude/Higgsfield-style workflows, or similar content-generation systems without making unsupported income, health, or testimonial claims.From its SKILL.md
npx -y skills add zack-dev-cm/tutorial-to-skill-free-pack --skill affiliate-ugc-test-plannerAssembled 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.
SKILL.md
3.9 KB, 719 tokens by cl100k_base, as published. Nobody here has run it
Affiliate UGC Test Planner
Use this skill to turn an affiliate product idea into a small, compliant content test. It plans the campaign; it does not promise commissions, post content, or generate media directly.
Workflow
-
Validate the product.
- Identify product, audience, affiliate network, commission range, allowed traffic sources, and disclosure requirements.
- Reject or flag products that require medical, financial, legal, or unverifiable personal-result claims.
- Ask for real product evidence if claims are weak: landing page, product page, user reviews, usage notes, or creator-owned footage.
-
Choose the test path.
- Pick one primary platform: Pinterest, TikTok, Instagram Reels, YouTube Shorts, Lemon8, or owned landing page.
- State whether direct affiliate links are allowed, uncertain, or should route through an owned bridge page.
- Separate organic tests from paid tests.
-
Build the hook matrix.
- 5 hooks: problem, routine, comparison, objection, curiosity.
- Each hook must avoid fake personal experience unless the user actually used the product.
- For AI-generated people, do not present them as real customers.
-
Build content briefs.
- 2 short video briefs.
- 1 carousel brief.
- Each brief includes scene idea, product evidence, caption angle, disclosure line, CTA, and failure risk.
-
Plan generation and cost control.
- Define the minimum viable creative set before scaling.
- Estimate generation count, not revenue.
- Include a stop rule for tools that burn credits or require paid plans.
-
Define measurement.
- Track posts, impressions, saves, clicks, outbound CTR, affiliate network clicks, conversion events if available, and policy/account issues.
- Give day-3 and day-7 kill criteria.
Output Format
Start directly with the deliverable. Do not add a persona, greeting, or process preamble.
Return:
offer fit: product, audience, traffic source, and risk level.compliance flags: disclosures, claim risks, platform risks, and evidence gaps.hook matrix: 5 hooks in a table.video briefs: 2 concise UGC-style briefs.carousel brief: 4-slide structure.platform plan: posting path and link/disclosure handling.cost risk: low, medium, or high with reason.test metrics: day-3 and day-7 metrics.kill criteria: when to stop or rework.
Guardrails
- Do not copy prompts, private workflows, landing-page claims, or creator-provided files from a source video.
- Do not claim guaranteed views, income, commissions, sales, ranking, or virality.
- Do not promise income, commissions, virality, ranking, or sales.
- Do not fabricate testimonials, personal product experience, before/after results, medical outcomes, or financial outcomes.
- Do not advise hiding affiliate disclosures.
- Do not tell users to bypass platform policies, moderation, account limits, or affiliate-network rules.
- For health, wellness, finance, legal, or regulated products, use cautious copy and require evidence review.
- For AI-generated actors, disclose or phrase as demonstration/content, not a real customer review.
Reference
If source validation is needed, read references/source-evidence.md. It summarizes the public video/comment evidence behind this skill and the limits of the conversion.
What ships with it: 1 file
2.0 KB alongside SKILL.md
references/
- source-evidence.md2.0 KB
Gives 0 of the 12 instructions most plan spec skills give in 719 tokens
Counted across 1,099 of the 1,860 authors here whose files we hold, read 2026-08-07
- Ask one question at a timein 51 of 1099
- Break plans into vertical slicesin 29 of 1099, across 11 files
- Publish issues in dependency orderin 27 of 1099, across 9 files
- Iterate until user approves the breakdownin 25 of 1099, across 7 files
- Explore the repository to understand the codebase statein 24 of 1099, across 7 files
- Use domain glossary vocabularyin 23 of 1099, across 5 files
- Apply correct triage labels to published issuesin 23 of 1099, across 5 files
- Prefer AFK slices over HITLin 22 of 1099, across 7 files
- Write a specification before writing any codein 22 of 1099, across 14 files
- Write failing tests before implementation codein 22 of 1099, across 20 files
- Ask clarifying questions until requirements are concretein 21 of 1099, across 13 files
- Respect existing architecture decision recordsin 20 of 1099, across 5 files
Said here and by no other author read
- validate the product and identify disclosure requirements
- reject products requiring unverifiable claims
- request product evidence when claims are weak
- state direct linking rules clearly
- separate organic tests from paid tests
- build five distinct hooks
Grouped from the skills themselves: near-identical wordings counted once, and counted by distinct author, so one author publishing three of these counts once. Length counted with cl100k_base; the agent that loads this file may tokenize it differently.