#156156th of 308 in Skills, plugins and prompts
hallmark
Design skill that builds and lints web pages to avoid AI-generated looks
- Stars
- 31.5k
- License
- MIT
- Last commit
- Oct 2026
- Language
- CSS
0 on 1 May 202631,451 on 23 Oct 2026
From GitHub's daily star counts.
Checked on GitHub.
Overview
Hallmark is a skill for Claude Code, Codex, Cursor and OpenCode that builds self-contained HTML and CSS pages from one of 48 themes, or from a custom direction. It lints the result in a real browser at eight widths against a list of AI-design tells, then has a fresh-context subagent review it. It also offers redesign and audit commands for existing pages.
Who it is for: Developers using AI coding agents to build polished landing pages and sites
Strengths
- Tiered gates (Floor, Reflex, Finish) cover contrast, focus, reduced motion and phone layout
- 48 themes, each one file of at most 8 KB with a reference screenshot
- Redesign checks that links, fields, handlers and headings survive via sloplint --before and --kept
- One npx command installs it for Claude Code, Codex, Cursor and OpenCode; also a Claude plugin
Weaknesses
- Browser lint needs puppeteer-core and Chrome; without them only static checks run
- Output is static HTML and CSS pages; no framework components are described
- Photo library links Wikimedia Commons images with mixed licenses that need on-page credit
- May not fire on its own; sometimes has to be invoked by name
What it needs
- no GPU
- Needs Node 18+, puppeteer-core, Chrome
- Models: Claude Code, Codex CLI, Cursor, OpenCode
Quick answers
Is hallmark open source?
Yes. Its code is on GitHub under the MIT license.
Safety checks
Checks passed: 7 of 8 (19 Oct 2026)
Checked commit 13ac0ec ↗ (opens in a new tab) · content sha256:deef0149dc8d…
- Pass
No hardcoded keys or tokens
No key matching a known secret format in 286 files
- Pass
No binaries or archives in agent or server folders
No binary or archive in 107 files
- Pass
- Pass
No hidden Unicode in agent-facing text
No hidden Unicode in 107 files
- Pass
No override, concealment or secret-file instructions
No override, concealment or sensitive-path instruction in 107 files
- Fail
A private way to report a vulnerability
No security policy and private vulnerability reporting is off
security page ↗ (opens in a new tab), reporting setting ↗ (opens in a new tab)
- Pass
- Pass
No fake prerequisite or installer steps
No installer or prerequisite step in 107 files
N/A: 10 checks do not apply here or had no data
- N/A
Package points back to this repo
Applies to MCP servers only
- N/A
Listed in the official MCP Registry under the owner's name
Applies to MCP servers only
- N/A
Latest release has build provenance
Applies to MCP servers only
- N/A
No advisories at CVSS 7 or higher
No lockfile at the repo root
- N/A
No install-time scripts
Applies to MCP servers only
- N/A
No dangerous CI workflow
No GitHub Actions workflows
- N/A
HTTPS endpoints, no credentials in shipped config
Not a plugin and not an MCP server
- N/A
No email recipients added since the last checked version, no hidden BCC
No server code or skill scripts
- N/A
No shell commands built from input, no unchecked URL opening
Applies to MCP servers only
- N/A
HTTP endpoints check auth or stay on localhost
Applies to MCP servers only
Facts, not pass or fail
- Bundles scripts
- No
- Hooks
- No
- A bin folder
- No
- MCP config file
- No
- Calls other MCP tools
- No
- Domains its agent files link to
- ai.google.dev, api.fontshare.com, api.svgl.app, blackforestlabs.ai, brandfetch.com, browserframe.com, cdn.jsdelivr.net, cdn.simpleicons.org and 22 more
Read on 19 Oct 2026 from the repo's files, npm, PyPI, deps.dev, OSV and the MCP Registry. We ran nothing from the project. N/A means the check does not apply or we could not read its data. Not part of the score: what each check looks at and what it cannot see. A result looks wrong? Tell us on GitHub (opens in a new tab).
Also in Skills, plugins and prompts
See all 308| Rank | Project | Score |
|---|---|---|
| 1 | impeccableDesign skill with 24 slash commands for AI coding agents' frontend output | 96 out of 100 |
| 2 | cavemanCuts token use in coding agents with terse replies and compressed inputs | 95 out of 100 |
| 3 | skillsAgent skills for planning, TDD, debugging and code review | 94 out of 100 |
| #4 | eccAgents, skills, hooks and rules bundle for Claude Code, Codex and other harnesses | 94 out of 100 |
| #5 | oh-my-claudecodeMulti-agent orchestration plugin and CLI for Claude Code | 94 out of 100 |