CtrlK
BlogDocsLog inGet started
Tessl Logo

baoyu-design

Create polished design artifacts as self-contained HTML: UI mockups, interactive prototypes, wireframes, landing pages, dashboards, app screens, mobile apps, slide decks (a.k.a. PPT / PowerPoint presentations), documents and résumés, animations, 3D objects, research reports, HTML email, diagrams, fliers, and visual explorations. Use whenever the user asks to design, mock up, prototype, wireframe, visualize, explore, or make a PPT/deck for an interface, product screen, user flow, content layout, visual artifact, or pitch/deck concept, even if they do not say "design". Also use to export a deck built with this skill to PowerPoint (PPT/PPTX) — but only decks authored here (deck-stage / this skill's slide-structured HTML), NOT arbitrary HTML, so confirm the target is such a deck first. Also use for setting up, importing, or authoring reusable design systems, UI kits, brand tokens, or component libraries. Harness-agnostic for Claude Code, Cursor, Codex Agent, and similar file-capable agents.

66

Quality

83%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Failed to scan

The risk profile of this skill

SKILL.md
Quality
Evals
Security

Quality

Content

67%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 body is a well-structured orchestration flow with a clear numbered workflow, concrete file/script references, and good progressive-disclosure routing to specialized docs. It is slightly verbose in places (the intro and step 5), and several referenced bundle paths were not present to verify in the supplied files.

Suggestions

Trim the intro paragraph so it does not re-list trigger conditions already covered by the frontmatter description, saving context tokens.

Break step 5 ('Set up the output folder') into a short bullet list or sub-steps; the current single dense paragraph is hard to scan.

Ensure all referenced paths (system-prompt.md, built-in-skills/*, agents/*, project-types.json) exist in the bundle so progressive-disclosure links resolve.

DimensionReasoningScore

Conciseness

Mostly efficient as a routing doc, but the intro paragraph re-states trigger conditions already in the description and step 5 ('Set up the output folder') is a dense run-on paragraph that could be tightened, fitting 'mostly efficient but includes some unnecessary explanation or could be tightened'.

3 / 5

Actionability

Gives concrete, executable guidance — named files ('Read system-prompt.md'), a concrete command ('glob designs/*/_ds_manifest.json'), and named scripts (agents/compile-design-system.mjs, agents/import-design-system.mjs, agents/record-asset.mjs) — with only minor gaps, matching 'mostly executable guidance; concrete code or commands with minor gaps'.

4 / 5

Workflow Clarity

A clear numbered sequence (1: load methodology → 2: identify harness → 3: load built-in skill → 4: ask clarifying questions → 5: set up folder → 6: build, preview, verify) with a verification checkpoint in step 6 ('confirm it loads cleanly. Fix any errors before finishing'), fitting 'clear sequence with most checkpoints present; minor validation gaps'.

4 / 5

Progressive Disclosure

The body is an overview that routes to well-signaled one-level-deep references (system-prompt.md, references/<harness>.md, built-in-skills/*.md) with markdown links and content appropriately split; scored 4 rather than 5 because the provided bundle only contains references/ and several referenced paths (system-prompt.md, built-in-skills/*, agents/*, project-types.json) could not be verified against the actual bundle structure.

4 / 5

Total

15

/

20

Passed

Description

92%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.

The description is excellent on specificity, trigger terms, and completeness — it concretely lists actions, surfaces natural synonyms and file extensions, and explicitly states both what it does and when to use it. Its only weakness is breadth: covering so many artifact types raises overlap risk with more specialized skills.

Suggestions

Narrow or rank the artifact list so the most common triggers (UI mockups, prototypes, decks) lead, reducing surface overlap with dedicated dataviz/research/PPT skills.

Add a one-line boundary note clarifying when to defer to specialized skills (e.g., 'for pure data charts prefer the dataviz skill') to lower conflict risk.

Consider trimming the parenthetical export caveats into a shorter clause; the boundary detail is useful but slightly inflates the description.

DimensionReasoningScore

Specificity

Lists numerous concrete artifact types and actions — 'UI mockups, interactive prototypes, wireframes, landing pages, dashboards... slide decks... documents and résumés, animations, 3D objects, research reports, HTML email, diagrams, fliers' — plus 'export a deck... to PowerPoint (PPT/PPTX)' and 'setting up, importing, or authoring reusable design systems, UI kits, brand tokens, or component libraries', giving comprehensive coverage.

5 / 5

Completeness

Explicitly answers both 'what' ('Create polished design artifacts as self-contained HTML: ...') and 'when' ('Use whenever the user asks to design, mock up, prototype, wireframe, visualize, explore... even if they do not say "design"'), with concrete trigger phrases matching the score-5 anchor.

5 / 5

Trigger Term Quality

Comprehensive natural terms with synonyms and extensions: 'design, mock up, prototype, wireframe, visualize, explore, or make a PPT/deck', plus 'PPT / PowerPoint presentations' and 'PPT/PPTX' file formats, matching the score-5 anchor's coverage of synonyms and extensions.

5 / 5

Distinctiveness Conflict Risk

The unifying niche ('design artifacts as self-contained HTML') is specific and includes boundary guidance ('but only decks authored here... NOT arbitrary HTML'), but the ~20 covered artifact types (dashboards, diagrams, research reports, decks) overlap with specialized skills like dataviz or research skills, fitting 'somewhat specific but could still overlap'.

3 / 5

Total

18

/

20

Passed

Validation

93%

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

Validation — 15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

relative_links

Relative link issues: 25 missing

Warning

Total

15

/

16

Passed

Repository
JimLiu/baoyu-design
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.