CtrlK
BlogDocsLog inGet started
Tessl Logo

claude-design

Design one-off HTML artifacts (landing, deck, prototype).

54

Quality

63%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./skills/creative/claude-design/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

77%

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

The content is a strong, actionable design-process skill with a clear sequenced workflow and validation/feedback loops, scoring top marks on actionability and workflow clarity. It loses points for length/repetition and for being entirely monolithic with no progressive disclosure into reference files, yielding a normalized score of 0.775.

Suggestions

Split the largest self-contained references (e.g. the Slop Diagnostic ten-tell audit and repair map, and the seven-surface archetype catalog) into files under references/ and link to them one level deep, shrinking the main SKILL.md toward an overview.

Tighten the redundancy between the "Anti-Slop Rules" list and the "Slop Diagnostic" ten tells, and de-duplicate the surface-first concept between its dedicated section and the Workflow step, to recover token budget.

Consider moving the format-specific rule blocks (Deck Rules, Prototype Rules, Variation Rules, React Guidance) into a single reference file reached via one-level links, keeping the core workflow and doctrine in SKILL.md.

DimensionReasoningScore

Conciseness

The body is mostly efficient, opinionated doctrine that does not explain concepts Claude already knows, but at ~640 lines / 25KB it is long and contains some repetition (anti-slop rules vs. the slop diagnostic, the surface-first concept restated in the workflow); it could be tightened without losing clarity.

2 / 3

Actionability

For an instruction-only skill the guidance is highly concrete and actionable: a seven-surface archetype taxonomy with examples, a ten-tell slop audit scored out of 10 with a tell-to-repair mapping, and specific numeric rules (44px hit targets, 1920×1080 decks, 24px+ slide text, pinned React versions); absence of executable code is not penalized because the guidance is specific and largely copy-paste-ready as a procedure.

3 / 3

Workflow Clarity

An explicit 8-step Workflow includes a Verify step with sub-checkpoints, a dedicated Verification section with minimum/better checklists, and the slop diagnostic provides a re-score feedback loop ("Re-score after repairing"), giving clear sequencing with validation checkpoints and error-recovery feedback.

3 / 3

Progressive Disclosure

The skill is a single ~640-line monolithic file with no bundle files (references/, scripts/, assets/ are absent) and no external references; internally it is well-organized with clear headers, but for a skill this large, material that could live in separate files (slop diagnostic, surface taxonomy, deck/prototype/variation rules) is all inline, matching the score-2 anchor of content that should be separate being inline.

2 / 3

Total

10

/

12

Passed

Description

50%

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

The description is concise and punchy but underspecified: it states the what without an explicit when, and does not differentiate the skill from closely related design skills. All four dimensions land at the middle anchor, yielding a normalized score of 0.5.

Suggestions

Add an explicit trigger clause, e.g. "Use when the user asks for a one-off designed HTML artifact (landing page, prototype, deck, component lab) with no specific brand or token system dictated."

Broaden trigger terms to include common natural variations users say (mockup, wireframe, presentation, dashboard, onboarding flow) to improve trigger coverage.

Add a one-line distinguisher so it does not collide with popular-web-designs (match a known brand) or design-md (author a token spec file).

DimensionReasoningScore

Specificity

Names the domain and concrete artifact types ("one-off HTML artifacts (landing, deck, prototype)") but relies on a single verb ("Design"); it lists object examples rather than multiple distinct actions, so it stops short of the score-3 anchor that lists several concrete actions.

2 / 3

Completeness

It clearly answers "what" (design one-off HTML artifacts) but provides no "Use when..." clause or equivalent explicit trigger guidance; the "when" is only implied by the parenthetical examples, which per the judging guidelines caps completeness at 2.

2 / 3

Trigger Term Quality

The terms "design", "HTML", "landing", "deck", and "prototype" are natural things a user might say, but common variations (mockup, wireframe, presentation, dashboard) are missing and there is no explicit trigger phrasing, so coverage is partial rather than comprehensive.

2 / 3

Distinctiveness Conflict Risk

"One-off HTML artifacts" is a reasonably specific niche, but the description does not distinguish it from sibling design skills (popular-web-designs, design-md) that occupy overlapping trigger space; the body's extensive disambiguation section confirms real overlap risk.

2 / 3

Total

8

/

12

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.

Validation12 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

skill_md_line_count

SKILL.md is long (651 lines); consider splitting into references/ and linking

Warning

metadata_version

'metadata.version' is missing

Warning

metadata_field

'metadata' should map string keys to string values

Warning

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

Total

12

/

16

Passed

Repository
NousResearch/hermes-agent
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.