CtrlK
BlogDocsLog inGet started
Tessl Logo

frontend-blueprint

AI frontend specialist and design consultant that guides users through a structured discovery process before generating any code. Collects visual references, design tokens, typography, icons, layout preferences, and brand guidelines to ensure the final output matches the user's vision with high fidelity. Use when the user asks to build, design, create, or improve any frontend interface — websites, landing pages, dashboards, components, apps, emails, forms, modals, or any UI element. Also triggers on "build me a UI", "design a page", "create a component", "improve this layout", "make this look better", "frontend", "interface", "redesign", or when the user provides mockups, screenshots, or design references. Do NOT use for backend logic, API design, database schemas, or non-visual code tasks.

82

Quality

77%

Does it follow best practices?

Impact

Pending

No eval scenarios have been run

SecuritybySnyk

Passed

No known issues

Optimize this skill with Tessl

npx tessl skill review --optimize ./packages/skills-catalog/skills/(architecture)/frontend-blueprint/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Discovery

100%

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

This is a strong, well-crafted skill description that excels across all dimensions. It provides specific capabilities, abundant natural trigger terms, explicit 'Use when' and 'Do NOT use' clauses, and clearly distinguishes itself from backend or non-visual coding skills. The description is comprehensive without being unnecessarily verbose.

DimensionReasoningScore

Specificity

Lists multiple specific concrete actions: guides through structured discovery process, collects visual references, design tokens, typography, icons, layout preferences, and brand guidelines, generates code with high fidelity to user's vision.

3 / 3

Completeness

Clearly answers both 'what' (AI frontend specialist that guides through discovery, collects design inputs, generates code) and 'when' (explicit 'Use when' clause with detailed trigger scenarios, plus a 'Do NOT use' exclusion clause for backend/non-visual tasks).

3 / 3

Trigger Term Quality

Excellent coverage of natural trigger terms users would say: 'build me a UI', 'design a page', 'create a component', 'improve this layout', 'make this look better', 'frontend', 'interface', 'redesign', plus mentions of mockups, screenshots, and design references. These are highly natural phrases.

3 / 3

Distinctiveness Conflict Risk

Clearly carves out a distinct niche as a frontend/design specialist with a structured discovery process. The explicit 'Do NOT use' clause for backend logic, API design, and database schemas further reduces conflict risk with other coding skills.

3 / 3

Total

12

/

12

Passed

Implementation

54%

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

The skill has excellent workflow structure with clear phase gates, validation checkpoints, and progressive disclosure through well-organized reference files. However, it is significantly over-verbose — explaining design philosophy, persona motivation, and concepts Claude already knows at length. The skill would benefit greatly from being cut to roughly half its current length while preserving the workflow structure and templates.

Suggestions

Cut the content by 40-50%: remove the persona framing paragraph, the 'What This Skill is NOT' section, philosophical justifications like 'A wrong first draft wastes more time than 2 minutes of discovery', and the 'Expert Behavior Guidelines' section (Claude already knows how to be a good consultant).

Add at least one concrete, executable code example in the Atomic Build phase showing what actual output looks like (e.g., a small component with CSS custom properties, semantic HTML, and responsive styles) to match the Technical Quality Standards.

Compress the examples section — Examples 1 and 2 could each be 3-4 lines instead of 8-12, and Example 3 (Stitch flow) repeats information already covered in Phase 4.

DimensionReasoningScore

Conciseness

The skill is extremely verbose at ~350+ lines. It extensively explains concepts Claude already understands (what a dashboard is, what discovery means, what 'modern and clean' means), includes lengthy philosophical justifications ('A wrong first draft wastes more time than 2 minutes of discovery'), and has an entire 'What This Skill is NOT' section that adds no actionable value. The persona framing ('You are a senior frontend design consultant') and motivational language ('every token spent on discovery saves 10x in rework') waste tokens.

1 / 3

Actionability

The skill provides a clear structured workflow with specific phases and concrete templates (Design Direction Summary, Execution Plan format), and includes Stitch MCP tool calls. However, it contains no executable frontend code examples despite being a frontend skill — the code quality standards section lists requirements but shows no implementation. The examples are conversational scenarios rather than concrete code artifacts.

2 / 3

Workflow Clarity

The 7-phase workflow is clearly sequenced with explicit gates between phases ('Do NOT skip phases', 'CRITICAL: Do not proceed to Phase 3 until...', 'Wait for explicit approval or adjustments before proceeding'). Each phase has a stated goal, clear exit criteria, and the conditional Phase 4 is well-explained. The atomic build phase includes a validation loop ('Does this match your vision? Any adjustments before I move to the next step?') and explicitly prevents accumulating technical debt.

3 / 3

Progressive Disclosure

Reference files are clearly listed with specific triggers for when to load them ('Load them ON DEMAND, not upfront'), each mapped to the relevant phase. The main skill provides the complete workflow overview while deferring deep-dive content (design principles, collection strategies, Stitch integration) to separate reference files with clear one-level-deep navigation.

3 / 3

Total

9

/

12

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.

Validation11 / 11 Passed

Validation for skill structure

No warnings or errors.

Repository
tech-leads-club/agent-skills
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.