Claude Skills is a library of reusable capability packages that give Claude task-specific instructions, terminology, and output formats for building, launching, operating, and growing websites and brands. People working on branding, design, content, SEO, development, operations, growth, or research can use the skills across different website stacks. The catalogue contains selected skills and plugins from the library.
Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add rampstackco/claude-skills --skill comparison-tool-designgit clone --depth 1 https://github.com/rampstackco/claude-skillsWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/rampstackco/claude-skills/comparison-tool-design)<a href="https://agentmods.dev/skills/rampstackco/claude-skills/comparison-tool-design"><img src="https://agentmods.dev/badge/skills/rampstackco/claude-skills/comparison-tool-design/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/rampstackco/claude-skills/comparison-tool-design"><img src="https://agentmods.dev/badge/skills/rampstackco/claude-skills/comparison-tool-design.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00146 | $0.03355 |
| Opus 5.5 | $0.00058 | $0.01342 |
| Sonnet 5.5 | $0.00029 | $0.00671 |
| Haiku 4.5 | $0.00015 | $0.00335 |
Grade A, and why
comparison-tool-design scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 1mo ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 268 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Comparison Tool Design
A senior product marketing director's playbook for designing side-by-side comparison tools that help users decide rather than just listing features. Plan-compare, product-compare, alternative-compare. Axis selection, default-comparison logic, recommendation discipline. The discipline of building a comparison tool that earns the user's trust.
Most comparison tools fail in one of two ways. They dump every feature into a giant grid (4 options × 40 features = 160 cells) and ask the user to weigh everything against everything. The user leaves without choosing. Or they pretend to be neutral comparisons but are actually sales pitches with biased defaults and weighted framing; the user catches the bias and trust collapses.
The comparison tools that work do something different. Genuine like-for-like comparison plus an explicit opinionated recommendation. "For X audience, choose Y." The recommendation is visible, defended, and not the only path; users can override. The tool helps the user decide rather than asking them to decide alone.
The voice is the senior product marketing director who has watched comparison tools double conversion when redesigned with honest recommendations and watched them collapse when feature grids grew without decision support. Practical, opinionated about which axes matter, willing to call out when the comparison is decoration.
When to use this skill: scoping a comparison tool for the first time, auditing a feature-grid comparison that produces no conversion lift, designing recommendation logic that is honest about the recommendation, or deciding which axes earn placement in a comparison tool.
What this skill covers
This skill spans side-by-side comparison tools. The growth-tooling distinctions:
calculator-designis calculators that give a number. This skill is comparing known options.quiz-and-assessment-designis quizzes that give a category. This skill is comparing options the user already knows about.comparison-tool-design(this skill) is axis selection, default-comparison logic, recommendation engine, filter-and-toggle UX.landing-page-copyis pricing-page copy; one specific application of comparison tools is the pricing page.content-strategyis upstream; what topics warrant comparison content.
What ships with it
10 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- README.md 363 B
- references/axis-selection-patterns.md 4.6 KB
- references/common-comparison-failures.md 5.6 KB
- references/comparison-anti-patterns.md 5.9 KB
- references/comparison-fatigue-patterns.md 5.8 KB
- references/comparison-tool-decision-criteria.md 4.5 KB
- references/default-comparison-logic.md 5.6 KB
- references/filter-and-toggle-patterns.md 6.1 KB
- references/honest-recommendation-discipline.md 6.7 KB
- references/recommendation-engine-design.md 5.0 KB
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 1mo ago First seen · 268 lines · 146 tokens per session scan A 3a8559eadf13
comparison-tool-design is a skill published in the GitHub repository rampstackco/claude-skills (1,000 stars, last pushed today), licensed MIT. It adds 146 tokens to every session and 3,355 once invoked, about $0.0006 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
popular-web-designs
54 real design systems (Stripe, Linear, Vercel) as HTML/CSS.
visual-qa
Runs rigorous visual QA across web, terminal, and paginated surfaces: an Apple HIG-based checklist, paired light/dark captures at phone and desktop widths, screenshot evidence, and a per-item PASS/FAIL verdict. Use for any UI build or change, or when asked whether a page, component, or TUI looks right or follows the…
frontend
Builds, styles, and polishes anything drawn with HTML, CSS, or SVG: web UI, pages, components, HTML reports rendered to PDF or print, figures, PNG/SVG diagrams, slides, and images for Notion or Slack. Use for any styling, layout, animation, or visual-quality task, or when asked to make something look or feel a certain…
ambience-skill
Layer A ambience-and-typographic-motion reference anchored to the react-bits catalog (reactbits.dev). Stacks on any style skill whenever work adds a hero atmosphere, an animated or shader background, a typographic reveal (split, blur, shimmer, typewriter, count-up, marquee), scroll storytelling, or card surface…
interaction-skill
Layer A interaction-mechanics reference anchored to the beui.dev catalog. Stacks on any style skill whenever work adds or changes motion or interaction — micro-interactions, animated components, transitions, gestures, hover/press/state feedback, loading/success/error morphs, 'make it feel alive'. Mandates reading the…
layout-skill
Layer A layout-mechanics reference. Stacks on any style skill when the screen is an app shell, dashboard, settings, list-detail, mail/inbox, or any layout with fixed regions plus a scrolling body — or when a layout breaks under long, empty, or unbroken content. Owns spatial structure and scroll ownership; owns zero…