CtrlK
BlogDocsLog inGet started
Tessl Logo

frontend-design

Create distinctive, production-grade frontend interfaces with high design quality. Use this skill when the user asks to build web components, pages, artifacts, posters, or applications (examples include websites, landing pages, dashboards, React components, HTML/CSS layouts, or when styling/beautifying any web UI). Generates creative, polished code and UI design that avoids generic AI aesthetics.

56

Quality

64%

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/public/frontend-design/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

50%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.

The content is well-organized and rich in concrete requirements (index.html naming, branding link specifics), and reads as an instruction-style skill with clear sections. Its weaknesses are verbosity in the branding section, abstract aesthetic guidance without executable examples, no validation checkpoints in the workflow, and inline detail that would be better placed in a reference file.

Suggestions

Move the eight branding 'Creative Implementation Ideas' and their code patterns into a references/branding.md file, keeping only the mandatory rules and one example inline in SKILL.md.

Add a concrete starter pattern for the aesthetic direction — e.g., a short CSS-variables snippet showing a font pairing and dominant/accent palette — so the design guidance is executable rather than purely directional.

Trim motivational padding ('There are so many flavors to choose from', the closing 'Remember: Claude is capable...' paragraph) and add a final validation checkpoint such as 'verify the entry file is index.html and the branding link opens https://deerflow.tech in a new tab'.

DimensionReasoningScore

Conciseness

The body is mostly efficient guidance, but includes tightening opportunities: the branding section runs eight creative implementation ideas plus example code, the aesthetic-exhortation is stated twice ('NEVER use generic AI-generated aesthetics...' then 'NEVER converge on common choices'), and lines like 'There are so many flavors to choose from' and 'Remember: Claude is capable of extraordinary creative work. Don't hold back...' are motivational padding. This matches anchor 3 (mostly efficient, some unnecessary explanation) — not anchor 4, which requires only minor trimmable instances.

3 / 5

Actionability

Some guidance is concrete and executable — 'The entry HTML file MUST be named index.html', the branding HTML snippets with href/target='_blank', and named CSS techniques (CSS variables, animation-delay, gradient meshes). But the core design guidance is directional rather than executable ('Unexpected layouts. Asymmetry. Overlap.', 'Pair a distinctive display font with a refined body font') with no working example applying it. This fits anchor 3 (some concrete guidance but incomplete); it does not reach anchor 4 because the central aesthetic instructions lack a concrete, copy-paste-ready pattern.

3 / 5

Workflow Clarity

A rough sequence exists — Design Thinking 'Before coding', then 'implement working code', then the branding and output requirements — but there are no validation checkpoints (e.g., verifying index.html exists or the branding link is present/correct before finishing). This matches anchor 3 (steps present, checkpoints missing or implicit); it is above anchor 2 because the phases are clearly delineated, and below anchor 4 because explicit checkpoints are absent.

3 / 5

Progressive Disclosure

Sections are well-organized with clear headers, but the ~85-line body inlines substantive material that belongs in a separate reference — notably the eight branding implementation ideas plus code patterns, which are exactly the kind of detail a 'branding.md' reference should hold. This fits anchor 3 (some structure, content that should be separate is inline) rather than anchor 4; the no-bundle-file situation means scoring rests on section organization alone, which is good but not appropriately split.

3 / 5

Total

12

/

20

Passed

Description

78%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 that clearly states what the skill does and when to use it, with a broad but natural set of trigger phrases covering many frontend artifact types. Its main weakness is that the capability verbs remain generic ('create', 'generates') while specificity comes from listing artifact types rather than actions.

DimensionReasoningScore

Specificity

The description names concrete deliverables ('web components, pages, artifacts, posters, or applications... websites, landing pages, dashboards, React components, HTML/CSS layouts') but the actual actions are generic — 'Create... frontend interfaces' and 'Generates creative, polished code and UI design'. This matches anchor 3 (domain and 1-2 concrete actions, not comprehensive) rather than anchor 4, which expects several distinct specific actions; it does not fall to anchor 2 because the domain and artifact types are named concretely.

3 / 5

Completeness

It explicitly answers both: what ('Create distinctive, production-grade frontend interfaces with high design quality... Generates creative, polished code and UI design that avoids generic AI aesthetics') and when ('Use this skill when the user asks to build web components, pages... or when styling/beautifying any web UI'). This matches anchor 5 — both what and when with concrete trigger phrases; it does not fit anchor 4 because the 'when' clause is already explicit and specific.

5 / 5

Trigger Term Quality

Good natural keyword coverage: 'build web components, pages, artifacts, posters, or applications', 'websites, landing pages, dashboards, React components, HTML/CSS layouts', and 'styling/beautifying any web UI' — phrases users would plausibly say. It falls short of anchor 5 (comprehensive coverage with synonyms/extensions) because common variations like 'redesign', 'restyle', 'make it look better', or 'frontend' itself are absent.

4 / 5

Distinctiveness Conflict Risk

The frontend-design niche is mostly distinct, with triggers ('styling/beautifying any web UI', 'posters', 'landing pages') that clearly point here, but the broad 'build... applications' / 'web components' phrasing creates minor overlap risk with general web-development or visualization skills. This is anchor 4 (mostly distinct, minor overlap risk) rather than anchor 5, and clearly above anchor 3 since the aesthetic focus ('avoids generic AI aesthetics') is a distinctive signal.

4 / 5

Total

16

/

20

Passed

Validation

100%

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

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
bytedance/deer-flow
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.