hallmark: Anti-AI-slop design skill for Claude Code, Cursor, and Codex

by Nutlope · Claude Skill · ★ 53.2k

Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h

Featured in: Humanizer & Anti-Slop Skills · AI Design Tools

How to install hallmark

npx skills add nutlope/hallmark

Taken from the project's README on GitHub. Check the security audit before running it.

Security audit verdict: SAFE · quality 58/100

None of the 44 rules matched — no credential harvesting, no data exfiltration, no curl-pipe-shell installer. Scanned against 44 published rules built on the SlowMist agent-security taxonomy, refreshed every 8 hours. Full audit →

The quality score combines nine heuristic checks of the repo and its README: completeness, clarity, specificity, examples, structure, agent readiness, step-by-step content, instruction quality and security notes. It rates how well the project explains itself to an agent, not the code.

🧪 Tested by Agent Skills Hub

One of 10 tools we ran end to end on the same task for our AI Design Tools page (2026-10-10).

Our pick for a different result each time: All seven checks twice, little in common with the default, and its two builds differ from each other: one flat and technical, one editorial with a serif headline.

Result: shares 1.0 of 4 with the page built with no skill (fonts, accent, background) · its two builds share 2 of 4 · 7.0 of 7 page checks passed

See both builds → · See the whole test →

One of 27 tools we ran end to end on the same task for our Humanizer & Anti-Slop Skills page (2026-11-08).

Our pick for a soft, product-shot look: A soft grey gradient under a black top bar, a heavy black headline and the invoice card set like a product shot; the judge gave it 5 of 5 with 1 AI tell left, in 7.6 minutes.

Result: AI tells 65 → 1 · judge 5/5 · 7.6 min

What it made in our test

See before and after → · See the whole test →

Quick Facts

Stars53,181
Forks2,831
LanguageCSS
CategoryClaude Skill
LicenseMIT
Quality Score58/100
Open Issues45
Last Updated2026-11-11
Created2026-04-27
Platformsclaude-code, codex
Est. Tokens~16k

About hallmark

Hallmark A design skill for Claude Code, Cursor, and Codex that refuses to look AI-generated. Live demo →  ·  twenty-two themes  ·  four verbs  ·  press to cycle. Made by Together AI.

Compatible Skills

These tools work well together with hallmark for enhanced workflows:

  • swiftui-design-skill — semantic(0.49)+complementary+similar_pop+shared_platform (52%)
  • ui-craft — semantic(0.19)+complementary+similar_pop+shared_platform (47%)

hallmark alternative? Top 6 similar tools

Looking for a hallmark alternative? If you're comparing hallmark with other claude skill tools, these 6 projects are the closest alternatives on Agent Skills Hub — ranked by topic overlap, star count, and community traction.

  • marketingskills by coreyhaines31 · ⭐ 61.1k

    Marketing skills for Claude Code and AI agents. CRO, copywriting, SEO, analytics, and growth engineering.

  • claude-plugins-official by anthropics · ⭐ 47.7k

    Official, Anthropic-managed directory of high quality Claude Code Plugins.

  • awesome-agent-skills by VoltAgent · ⭐ 37.2k

    A curated collection of 1000+ agent skills from official dev teams and the community, compatible with Claude C

  • frontend-slides by zarazhangrui · ⭐ 32.6k

    Create beautiful slides on the web using a coding agent's frontend skills

  • planning-with-files by OthmanAdi · ⭐ 28.0k

    Persistent file-based planning for AI coding agents and long-running tasks. Crash-proof markdown plans, sessio

  • open-saas by wasp-lang · ⭐ 16.3k

    A 100% free modern JS SaaS boilerplate (React, NodeJS, Prisma). Full-featured: Auth (email, google, github, sl

More Claude Skill Tools

Explore other popular claude skill tools:

View all Claude Skill tools →

Popular CSS Agent Tools

How this security grade is produced

Grades come from a rule-based scan built on the SlowMist agent-security taxonomy: 44 published rules, covering credential harvesting, data exfiltration, curl | sh installers and more. It is a first-layer scan, not a manual audit — we say so rather than overstate it.

The scale of the problem is documented independently: Liu et al. (2026), in a study of 31,132 agent skills, report that 26.1% contain security vulnerabilities. Our own full-catalog census is published as a citable open dataset.

Sources & who's responsible:

View on GitHub → Browse Claude Skill tools