rampstackco/claude-skills / skills/evidence-based-reviews
evidence-based-reviews
VerifiedProduce honest product reviews and buying guides without fabricated first-hand experience, using disclosed evidence tiers: verified specs, owner-experience synthesis at scale, expert triangulation, and hands-on only when true. Use this skill whenever the user wants to write product reviews or buying guides without hands-on access, set up a review methodology, add evidence disclosure to review content, align reviews with Google's reviews system or FTC affiliate disclosure expectations, or decide when Review and Product schema are honest to use. Triggers on product review, buying guide, best-of list, review methodology, evidence basis, hands-on testing, we tested, affiliate review site, review disclosure, methodology block, original research, reviews system. Also triggers when review content claims testing that did not happen, or when an affiliate site needs a trust mechanism that survives scrutiny.
| File | Kind | Size |
|---|---|---|
| README.md | markdown | 363 B |
| SKILL.md | skill md | 12.1 KB |
| references/evidence-tiers.md | markdown | 4.1 KB |
| references/methodology-block-template.md | markdown | 2.7 KB |
references/methodology-block-template.md
View on GitHub# The methodology block: template, example, placement
The per-piece disclosure block. Short, placed with the criteria, written for readers. It names what the piece's verdicts rest on, and it never claims a tier the piece did not use.
## The template
> **How we reviewed this**
> **Criteria:** [the 3 to 5 criteria, in the order they were weighted, stated before the picks].
> **Evidence:** [the tiers actually used, specifically: verified manufacturer specs (noting where and when); owner-experience synthesis at scale (name the corpora and the rough sample size); expert-source triangulation (name the sources)].
> **Hands-on:** [what was physically done, quantified, or the words "none claimed for this piece"].
> **Updated:** [date]: [what changed and why].
## A worked example (generic category)
> **How we reviewed this**
> **Criteria:** noise under load, durability across a season, build quality, price against the field, in that order.
> **Evidence:** manufacturer specs verified against each maker's current product page (May 2026); owner-experience synthesis across roughly 1,400 retailer reviews and two seasons of forum threads from three owner communities; expert triangulation across two named publications, whose durability verdicts disagreed (the disagreement and the likely cause are discussed under pick 2).
> **Hands-on:** none claimed for this piece.
> **Updated:** June 2026: replaced the budget pick after recurring owner reports of a failed adjustment mechanism; previous pick moved to the skip-it section with the evidence.
## Placement rules
- The block sits with the criteria, before or immediately after the picks summary, never below the fold of a long piece and never in a footer.
- Body-size text. A disclosure styled to be skipped is a disclosure in name only.
- The hands-on line is mandatory even when the answer is "none claimed." The absence stated plainly is the trust mechanism; the absence omitted is the lie of implication.
- The affiliate disclosure is a sibling, not a substitute: it travels with the recommendation per FTC expectations and says in plain language that the site earns a commission and that the reader's price does not change. The methodology block discloses the evidence; the affiliate block discloses the money. A piece with affiliate links carries both.
## Anti-patterns
- A block that lists every tier the site has ever used instead of the tiers this piece used.
- "Extensive research" as the evidence line. Name the corpora or do not claim the scale.
- A block written in legal register. The reader should finish it trusting the piece more, not feeling warned.
- The block as template default with fields unfilled. An unfilled block is a claim generator; every line must be true per piece.
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| finishing-a-development-branchobra/superpowersUse when implementation is complete, all tests pass, and you need to decide how to integrate the work | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| systematic-debuggingobra/superpowersUse when encountering any bug, test failure, or unexpected behavior, before proposing fixes | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| test-driven-developmentobra/superpowersUse when implementing any feature or bugfix, before writing implementation code | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| skill-creatoranthropics/skillsCreate new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, edit, or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy. | Stars: 198k | Updated | Claude CodeCodex | Verified | Install |