hallmark

Anti-AI-slop design skill for greenfield pages, audits, redesigns, and design extraction from URLs or screenshots. Use when the user asks to build a new app or landing page, wants to redesign something, invokes Hallmark by name, or uses audit/redesign/study.

Quality

84%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Quality

Content

85%Weight 40%Scale 1-5

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

A highly actionable, well-sequenced skill body with strong progressive disclosure and explicit validation/feedback loops across a complex multi-verb workflow. Its one weak spot is conciseness: repeated motivational rationale and surplus sample blocks could be trimmed without losing operational clarity.

Suggestions

Cut the repeated 'picking on the page (not in your head)' / 'accountability line' rationale to a single statement; the rule itself is enough for Claude.

Trim the pre-flight section's two extra sample outputs and the 'three sample shapes' rotation block to one example each — the canonical format block already conveys the pattern.

Consolidate the load-condition commentary; the table structure already signals discipline, so the prose warnings about token waste can be shortened.

Dimension	Reasoning	Score
Conciseness	The body is dense with irreplaceable operational detail (tokens, stamps, gates, load tables) but carries notable repeated motivational rationale ('picking on the page not in your head' appears ~3x, 'accountability line') and surplus sample-output blocks (extra pre-flight samples, 'three sample shapes' for rotation), matching the 'mostly efficient but includes some unnecessary explanation or could be tightened' anchor rather than the 4.	3 / 5
Actionability	Fully executable guidance throughout — exact stamp comment strings, concrete CSS (`.btn:hover, .btn.is-hover { background: var(--color-paper-3); }`), a JSON log schema, named tokens (`var(--color-accent)`), exact file paths, and numbered steps covering the common cases.	5 / 5
Workflow Clarity	The Design flow is clearly sequenced Step 0 through 7 with explicit validation checkpoints (the 66-gate slop test where 'every answer must be no', the pre-emit self-critique where <3 triggers a revision pass) and feedback loops (fix then re-emit the preview block); the destructive/batch validation cap is satisfied by deletion-confirmation rules, not tripped.	5 / 5
Progressive Disclosure	The body is an overview that delegates ~30 reference files kept one level deep, all verified present on disk, organized into an explicit load-condition table (always-load, index-then-pick, load-per-build, load-conditionally, load-at-end, verb-specific, human-only) that explicitly warns against nested or whole-catalogue loading — a clear match for the 5 anchor.	5 / 5
	Total	18 / 20 Passed

Description

83%Weight 40%Scale 1-5

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

A clear, well-structured description that explicitly covers both what the skill does and when to invoke it, with concrete verb triggers and a distinct anti-AI-slop niche. Minor gaps in capability coverage and a few missing natural synonyms keep it just below the top anchor on specificity and trigger terms.

Dimension	Reasoning	Score
Specificity	Names several concrete capabilities — 'greenfield pages, audits, redesigns, and design extraction from URLs or screenshots' — matching the 'lists several specific actions; minor gaps' anchor; not a 5 because component-scope and design.md emission are absent.	4 / 5
Completeness	Explicitly answers both what ('Anti-AI-slop design skill for...') and when ('Use when the user asks to build a new app or landing page, wants to redesign something, invokes Hallmark by name, or uses audit/redesign/study') with concrete trigger phrases.	5 / 5
Trigger Term Quality	Natural phrases users would say ('build a new app', 'landing page', 'redesign', 'audit/redesign/study') give good keyword coverage, but it lacks synonyms like 'make it look less AI' and file extensions, so it falls short of the comprehensive 5 anchor.	4 / 5
Distinctiveness Conflict Risk	The anti-AI-slop niche plus 'invokes Hallmark by name' and the distinct audit/redesign/study verbs make it mostly distinct, but 'build a new app or landing page' overlaps with generic web-build skills, capping it at the 4 anchor.	4 / 5
	Total	17 / 20 Passed

Validation

75%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 12 / 16 Passed

Validation for skill structure

Criteria	Description	Result
skill_md_line_count	SKILL.md is long (551 lines); consider splitting into references/ and linking	Warning
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning
relative_links	Relative link issues: 13 deeper-than-1-level, 3 suspicious	Warning
referenced_paths_exist	Referenced path issues: 20 deeper-than-1-level	Warning

	Total	12 / 16 Passed

Repository: nexu-io/open-design
Path: plugins/community/hallmark/SKILL.md
Commit: 1a7a23d

Reviewed: about 7 hours ago

Table of Contents

Discovery Implementation Validation

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.