CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

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.

64

Quality

80%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./plugins/community/hallmark/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

73%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 well-engineered, highly actionable skill body with excellent sequencing, validation feedback loops, and unusually disciplined progressive disclosure across its reference bundle. Its main weaknesses are verbosity from duplicated dispatch logic and a few dangling references that break navigation.

Suggestions

Collapse the duplicated catalog/custom theme-route dispatch (Step 1 and Step 2.6) into a single location and cross-reference it, cutting significant repetition.

Fix or remove the non-resolving paths (../../site/css/tokens.css, ../../docs/recipes.md) and add an explicit pointer to the 'active form protocol' definition so every reference resolves.

Trim the study-verb section in SKILL.md to the pipeline skeleton and push the detailed rules already living in references/study.md, reducing SKILL.md's token footprint.

DimensionReasoningScore

Conciseness

At ~550 lines the body is dense with genuinely novel, opinionated rules (gates, stamps, diversification axes), but there is real redundancy: the theme-route catalog/custom dispatch is explained at length twice (Step 1's "Theme route — only surface when the brief signals it" and Step 2.6), the study verb section repeats material delegated to references/study.md, and the component-scope section carries long illustrative blocks that could be tightened. This matches 'mostly efficient but includes some unnecessary explanation or could be tightened' rather than the noticeably-padded profile of a 2.

3 / 5

Actionability

The guidance is highly concrete — exact stamp formats, the .hallmark/log.json schema, copy-paste CSS for 8-state demos, pre-flight output templates, exact fallback phrasings, and enumerated signal lists. It falls short of fully-executable 5 because of minor gaps: two referenced paths (../../site/css/tokens.css, ../../docs/recipes.md) don't resolve from the bundle, and Step 1 says to 'Follow the active form protocol' without pointing to where that protocol lives.

4 / 5

Workflow Clarity

The Design flow is explicitly sequenced (Steps 0–7) with validation checkpoints throughout: pre-flight scan with file:line citations, a preview block before any code is emitted, the 69-gate slop test after Build with an explicit fix-and-re-test feedback loop, and re-emit-the-preview on gate failure. Destructive risk in existing projects is addressed by the implementation safety rail (deletions require explicit confirmation; file-level plans before editing). This matches the top anchor: clear sequence, explicit validation, feedback loops, checklists.

5 / 5

Progressive Disclosure

Structure is strong: a categorized load-discipline section (always-load, index-then-pick, load-per-build, load-conditionally, load-at-the-end, verb-specific, human-only) with one-level-deep references, and nearly every cited references/ path exists on disk. It falls just short of 5 because two human-only/data references (../../docs/recipes.md, ../../site/css/tokens.css) are broken in this bundle layout and the 'active form protocol' reference has no resolvable location, slightly hurting navigation.

4 / 5

Total

16

/

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 strong description: it states concrete capabilities and explicit 'Use when...' triggers in third person without padding. The only improvements are broader trigger synonyms and sharper separation from generic frontend-design skills.

Suggestions

Add common natural triggers such as 'design', 'website', 'UI', or 'make it look good' to the Use-when clause to broaden keyword coverage.

Clarify the niche vs. generic design/build skills (e.g., lead with 'opinionated anti-AI-slop design rules for...') to reduce overlap risk with general frontend build skills.

Consider mentioning component-scope work ('design a button/card/modal') since that is a documented first-class use of the skill.

DimensionReasoningScore

Specificity

The description names the domain ("Anti-AI-slop design skill") and lists four concrete capabilities — "greenfield pages, audits, redesigns, and design extraction from URLs or screenshots" — matching the anchor for several specific actions with minor gaps (e.g., component-scope design and the design.md portability flow are not mentioned). Not a 5 because coverage is not fully comprehensive of the skill's verbs; not a 3 because it clearly exceeds 1–2 actions.

4 / 5

Completeness

It explicitly answers both what ("Anti-AI-slop design skill for greenfield pages, audits, redesigns, and design extraction from URLs or screenshots") 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 — a direct match for the top anchor.

5 / 5

Trigger Term Quality

Natural user phrases are present — "build a new app or landing page", "wants to redesign something", "invokes Hallmark by name", "uses audit/redesign/study" — which map well to what users would actually say. A few natural terms are missing ("design", "website", "UI", "screenshot" as a standalone trigger), so it falls just short of the comprehensive synonym coverage of a 5.

4 / 5

Distinctiveness Conflict Risk

The "Anti-AI-slop" framing plus named verbs (audit/redesign/study) and a distinctive skill name give it a clear niche, but the broad trigger "build a new app or landing page" overlaps with generic frontend/design skills, presenting minor conflict risk rather than the minimal risk of a 5.

4 / 5

Total

17

/

20

Passed

Validation

75%

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

CriteriaDescriptionResult

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

Reviewed

Table of Contents

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.