CtrlK
BlogDocsLog inGet started
Tessl Logo

design-md

Analyze Stitch projects and synthesize a semantic design system into DESIGN.md files

53

Quality

60%

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/AI-Agents-Safe-Coding-Skills/skills/design-md/SKILL.md

The canonical home for this skill is design-md in administrakt0r/AI-Agents-Safe-Coding-Skills

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, actionable guide with concrete MCP tool calls, field-level detail, and a clear output template. Its main weaknesses are moderate redundancy across the Overview/Goal/Usage-Example sections and the absence of explicit validation checkpoints in the workflow.

Suggestions

Collapse the redundant 'The Goal' and Usage Example sections, which restate the Overview and retrieval steps, to tighten conciseness.

Add an explicit validation checkpoint after synthesis (e.g., verify every palette entry has a hex code and functional role before writing DESIGN.md) to lift workflow clarity.

Move the Common Pitfalls and Best Practices lists into a short reference section or trim them to the highest-value items to reduce padding.

DimensionReasoningScore

Conciseness

Mostly efficient and actionable, but 'The Goal' restates the 'source of truth' line from Overview, the Usage Example rehashes earlier retrieval steps, and Tips/Pitfalls/Best Practices sections add padded length that could be trimmed.

3 / 5

Actionability

Provides concrete MCP tool names with specific parameters and response fields (e.g., get_screen, htmlCode.downloadUrl, designTheme) plus a full output template, but the tool calls are described in prose rather than as copy-paste-ready code blocks.

4 / 5

Workflow Clarity

A clear numbered retrieval sequence (namespace discovery through metadata extraction) and a 5-step analysis/synthesis process are present; file generation is non-destructive so the batch/destructive cap does not apply, but explicit validation checkpoints are missing, keeping it below 5.

4 / 5

Progressive Disclosure

No bundle files exist; the skill is self-contained with well-organized section headers and a single external URL reference with no nesting. It is well-structured but the inline Tips/Pitfalls/Usage-Example content adds length that a split reference could absorb.

4 / 5

Total

15

/

20

Passed

Description

53%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 clearly states what the skill does and is anchored to a distinct product niche, but it lacks an explicit 'when to use' trigger clause and relies on a narrow set of domain keywords without natural-language synonyms. It sits at a solid mid-range across most dimensions.

Suggestions

Add an explicit 'Use when...' clause naming concrete trigger phrases (e.g., 'Use when generating DESIGN.md files for Stitch projects or when the user asks for a Stitch design-system summary').

Broaden trigger terms with natural user phrasings and synonyms (e.g., 'Stitch design language', 'design tokens', 'design documentation').

Add one more concrete action verb to lift specificity toward comprehensive coverage (e.g., 'extract', 'translate', 'document').

DimensionReasoningScore

Specificity

Names the domain ('Stitch projects') and two concrete actions ('Analyze', 'synthesize a semantic design system into DESIGN.md files'), matching the anchor for 1-2 concrete actions without being comprehensive.

3 / 5

Completeness

The 'what' is clearly stated but there is no 'Use when...' clause or equivalent explicit trigger guidance, which per the judging guidelines caps completeness at 3.

3 / 5

Trigger Term Quality

Relevant domain keywords ('Stitch projects', 'semantic design system', 'DESIGN.md files') are present but common natural-language variations or synonyms a user would actually say are missing.

3 / 5

Distinctiveness Conflict Risk

Tied to a specific product (Stitch) and a specific output artifact (DESIGN.md), giving it a clear niche with only minor overlap risk; not a 5 because the triggers are not fully fleshed out.

4 / 5

Total

13

/

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.

Validation15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

frontmatter_unknown_keys

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

Warning

Total

15

/

16

Passed

Repository
administrakt0r/AI-Agents-Safe-Coding-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.