#4040th of 43 in Skills, plugins and rules
hallmark
Design skill that steers coding agents away from generic AI-looking UI
Live demo ↗
(opens in a new tab)Website ↗
(opens in a new tab)Repository on GitHub ↗
(opens in a new tab)
- Stars
- 30k
- License
- MIT
- Last commit
- Aug 2026
- Language
- CSS
Checked on GitHub.
Overview
Hallmark is a skill for Claude Code, Cursor and Codex that picks a page macrostructure for a brief, applies one of twenty-one themes, and runs fifty-seven slop-test gates plus a self-critique before returning output. It has four verbs: build (default), audit, redesign and study, which extracts design traits from a screenshot or URL. Output is self-contained HTML and CSS.
Who it is for: Developers using coding agents who want distinctive front-end design output
Strengths
- Works across Claude Code, Cursor and Codex from one SKILL.md plus references
- Audit verb scores existing code and returns a punch list without editing
- Twenty-one themes plus a Custom branch for briefs no theme fits
- Live demo site and example pages are linked for each theme
Weaknesses
- Example output is static HTML and CSS; framework support is not documented
- Cursor install needs manual copy into a .mdc rule without frontmatter
- No benchmarks showing the slop-test gates improve output
- No tagged releases
What it needs
- no GPU
- Needs Claude Code, Cursor or Codex, npx
Also in Skills, plugins and rules
See all 43| Rank | Project | Score |
|---|---|---|
| 1 | skillsAgent skills for planning, TDD, debugging and code review | 94 out of 100 |
| 2 | eccAgents, skills, hooks and rules bundle for Claude Code, Codex and other harnesses | 93 out of 100 |
| 3 | ponytailSkill prompt that makes coding agents write less code and add tests | 91 out of 100 |
| #4 | cavemanProxy and skill that cut token use in coding agents | 91 out of 100 |
| #5 | spec-kitCLI and agent skills for spec-driven development, bug fixing and idea assessment | 89 out of 100 |