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 divyanshu-iitian/agent-website-design-skills --skill conversion-accessibility-polishgit clone --depth 1 https://github.com/divyanshu-iitian/agent-website-design-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/divyanshu-iitian/agent-website-design-skills/conversion-accessibility-polish)<a href="https://agentmods.dev/skills/divyanshu-iitian/agent-website-design-skills/conversion-accessibility-polish"><img src="https://agentmods.dev/badge/skills/divyanshu-iitian/agent-website-design-skills/conversion-accessibility-polish/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/divyanshu-iitian/agent-website-design-skills/conversion-accessibility-polish"><img src="https://agentmods.dev/badge/skills/divyanshu-iitian/agent-website-design-skills/conversion-accessibility-polish.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00068 | $0.00605 |
| Opus 5.5 | $0.00027 | $0.00242 |
| Sonnet 5.5 | $0.00014 | $0.00121 |
| Haiku 4.5 | $0.00007 | $0.00060 |
Grade A, and why
conversion-accessibility-polish 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 — 50 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Conversion and Accessibility Polish
Improve business outcomes by making the interface clearer, more trustworthy, and easier to operate. Accessibility is a product requirement, not a final visual filter.
Workflow
- Identify the primary user task, success event, and doubts or access barriers that block it.
- Walk the path from entry to success. Include navigation, forms, validation, loading, errors, confirmation, and return visits.
- Audit decision clarity:
- what the user is choosing;
- cost and commitment;
- what happens next;
- evidence and risk;
- how to recover or leave.
- Audit semantics and interaction: landmarks, headings, names, labels, descriptions, keyboard order, focus management, announcements, and pointer alternatives.
- Audit visual access: contrast, text resize/reflow, focus visibility, target spacing, zoom, motion, and content hidden by sticky UI.
- Replace vague or inflated copy with specific outcomes, constraints, examples, and next-step language.
- Reduce form friction without removing necessary consent, security, or error prevention.
- Place trust information where commitment increases. Keep terms, privacy, cancellation, and destructive effects visible.
- Implement the highest-impact fixes first: blocked tasks, misleading decisions, keyboard failures, form failures, then visual polish.
- Re-test the complete path on mobile and with keyboard-only navigation. Use automated checks as support, not as proof of conformance.
Ethical Guardrails
- Do not add fake scarcity, hidden fees, confirmshaming, disguised ads, forced continuity, preselected consent, or obstructive cancellation.
- Do not fabricate testimonials, metrics, security claims, or guarantees.
- Do not trade away accessibility for a presumed conversion lift.
- Do not claim WCAG conformance from automated tooling alone.
- Preserve user input after recoverable errors and make destructive actions explicit.
Delivery Contract
Provide:
- Primary path - entry -> decision -> action -> success.
- Findings - severity, affected users, evidence, and relevant standard when known.
- Prioritized fixes - impact versus effort.
- Implementation - when changes are requested.
- Verification - keyboard path, mobile path, form states, and automated/manual checks.
- Honest limits - what still requires content, legal, analytics, or assistive-technology review.
What ships with it
2 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.
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 · 50 lines · 68 tokens per session scan A 42c103738dae
conversion-accessibility-polish is a skill published in the GitHub repository divyanshu-iitian/agent-website-design-skills (4 stars, last pushed 2mo ago), licensed MIT. It adds 68 tokens to every session and 605 once invoked, about $0.0003 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 2026-08-31.
Other skills, from other repositories
brand-visual-language
Shape language across type, radius and icons carries brand personality. Use when starting a design system, picking icons or radius tokens, or reviewing visual consistency.
loading-states-and-perceived-performance
Spinners, skeletons and staggered reveals that manage wait times. Use when designing loading states, async data or the feel of a slow interface.
micro-interactions
Small purposeful animations — toggles, animated icons, success moments. Use when designing interactive feedback, success states or loaders.
elevation-and-depth
Shadows and layering that lift elements above the surface. Use when designing cards, dropdowns, modals, tooltips or any floating element.
motion-and-storytelling
Disney's animation principles and cinematic technique applied to UI motion. Use when designing transitions, scroll animations or onboarding motion.
responsive-paradigms
Mobile, tablet and desktop are different paradigms, not one layout scaled. Use when designing responsive layouts or deciding what each breakpoint shows.