Agent Pack

design

MIT

hallmark

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

Nutlope

85/ 100

公开评测 · 综合采用结论

证据充分，整体质量与安全表现优秀

查看评测依据评测我的项目基于公开项目证据，非安全认证或安装推荐

GitHub

29.3kstars

1.5kforks

最近更新 1个月前

评测生成时间（北京时间）: 2026/08/21 10:04
本报告引擎: v3.0.0
当前引擎: v3.16.0

本报告与当前引擎使用不同规则；原分数不会自动更新，不同版本的分数不宜直接对比。

重新评测此项目

进入后确认来源与额度，提交才会创建任务。

Evaluation report

综合采用结论

满分 100

值得推荐低风险

决策摘要

证据充分，整体质量与安全表现优秀

68%

中置信度

文档

权重 22%

100

安全

权重 25%

质量

权重 30%

活跃

权重 13%

采用

权重 10%

历史报告未保存置信度明细；重新评测后可查看各项证据贡献。

How it works · 未生成图示

本次报告未完成图示提取

本次评测未完成 AI 证据提取；确定性评分与安全扫描仍然有效。重新评测后，证据充分时会自动选择合适图型。

补充参与方或组件说明谁参与、各自负责什么

说明关系与顺序提供输入输出、调用或依赖证据

重新评测自动选图按证据选择流程、时序或架构图

五维表现

确定性工程质量 90/100

采用建议

优势

问题与用途描述
有效 README
安装或接入步骤
可执行示例
未发现已知高风险模式

关注点

缺少输出或结果说明
缺少限制、权限或边界
缺少错误处理或排障

也有自己的公开项目？先看完证据，再用当前规则生成独立报告。

评测我的项目 →

文档证据

66/100

问题与用途描述10 分

有效 README12 分

安装或接入步骤14 分

可执行示例16 分

输入、参数或工具说明11 分

输出或结果说明9 分

限制、权限或边界12 分

错误处理或排障8 分

许可证信息5 分

结构化章节3 分

安全证据

低风险

未发现已知高风险模式

静态扫描不是安全保证，生产接入前仍应人工复核权限和数据边界。

优先改进清单

01补充输出或结果说明
02补充限制、权限或边界
03补充错误处理或排障

方法、证据与局限展开

数据来源

GitHub Repository API

扫描范围

3 个文件 · 73,594 字符

评测引擎

v3.0.0 · AI 复核未启用

局限

静态评测不会安装或执行项目代码
安全扫描基于高信号文件与已知模式，不能替代人工审计
流行度只反映采用程度，不代表安全或工程质量

30 天热度趋势

README

Hallmark

A design skill for Claude Code, Cursor, and Codex that refuses to look AI-generated.

Live demo → · twenty-one themes · four verbs · press T to cycle.

Made by Together AI.

Hallmark, a design skill that refuses to look AI-generated

Hallmark picks a macrostructure for the brief, dresses it in one of twenty-one themes, runs fifty-seven slop-test gates plus a pre-emit self-critique, and refuses the on-distribution defaults every LLM was trained into. Two pages by Hallmark for two different briefs feel like different sites, not colour-swaps of the same template.

Four verbs

Verb	What it does
(default)	Build new UI. Picks a macrostructure, applies the rule-set, runs the slop test before handing back.
`hallmark audit <target>`	Score existing code against the anti-patterns. Punch list, no edits.
`hallmark redesign <target>`	Throw out the structure, keep copy + IA + brand, rebuild with a different fingerprint.
`hallmark study <screenshot \| URL>`	Extract the DNA from a design you admire: macrostructure, type-pairing, colour anchor. Refuses pixel-clones and paid templates. Optionally emits a portable `design.md` for handoff to other AI tools.

Different briefs, different shapes

Each generated from a different brief. The skill picks the theme, structure, and craft to fit each one, not from a template.


Bubble _{Sourdough app · Hum}	Distil _{Extraction API · Cobalt}	Cold Snap _{Record label · Carnival}	Cinder _{AI tool · Lumen}

Ferns & Fathom _{Tea menu · Custom}	Hollowback Apiary _{Honey farm · Garden}	Off-Register _{Print fair · Riso}	Press Quaternary _{Type studio · Custom}

Tally _{SaaS · modern-minimal}	Wayfare _{Travel · atmospheric}	NAJM _{Fashion brand}	Hyperlane _{Dev infrastructure}

Each page is self-contained HTML + CSS, stamped with its macrostructure in the CSS comment. Browse the full set at usehallmark.com or under site/_tests/.

Custom ^NEW

When a brief carries creative intent that no catalog theme fits, Hallmark switches to Custom and designs the page from scratch: a made-to-measure palette, type, and layout. Same 57 slop-test gates, no template underneath.


The Cascadia Nightjar _{Sleeper-train ticket · Custom}	The Mend Assembly _{Repair-café broadsheet · Custom}

It stays a quiet branch; vanilla briefs never see it. The protocol lives in custom-theme.md.

Install

npx skills add nutlope/hallmark

Re-run any time to update. Or copy SKILL.md + references/ into:

Claude Code: ~/.claude/skills/hallmark/
Cursor: .cursor/rules/hallmark.mdc (body of SKILL.md, no frontmatter)
Codex: ~/.codex/skills/hallmark/ (personal) or .codex/skills/hallmark/ (project-scoped)

The rule-set lives in SKILL.md and references/. Worked examples in docs/recipes.md and docs/study-examples.md.

Licence

MIT. Use it, fork it, ship it.