makepad-dsl

CRITICAL: Use for Makepad DSL syntax and inheritance. Triggers on: makepad dsl, live_design, makepad inheritance, makepad prototype, "<Widget>", "Foo = { }", makepad object, makepad property, makepad DSL 语法, makepad 继承, makepad 原型, 如何定义 makepad 组件

Quality

61%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./skills/makepad-dsl/SKILL.md

Quality

Content

63%Scale 1-5

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

This is a competent DSL reference skill with good concrete examples and clear syntax documentation. Its main weaknesses are moderate redundancy between inlined content and referenced files, some unnecessary explanations of basic concepts, and behavioral instructions that don't add much value. The progressive disclosure structure is undermined by the absence of bundle files to verify the referenced documents exist.

Suggestions

Remove or trim the Property Types table — Claude already knows what floats, strings, and hex colors are. Keep only Makepad-specific types like Size (Fit/Fill) and dep() syntax.

Trim the 'When Answering Questions' and 'When Writing Code' sections into a single brief 'Key points' list, as these are behavioral instructions Claude can infer from the examples.

Ensure the referenced files (`./references/dsl-syntax.md`, `./references/inheritance.md`) exist in the bundle, and move the detailed syntax/property tables there to avoid duplication between SKILL.md and the reference files.

Dimension	Reasoning	Score
Conciseness	The skill is mostly efficient but includes some unnecessary sections. The 'When Answering Questions' and 'When Writing Code' sections are somewhat redundant behavioral instructions that Claude doesn't need spelled out. The 'Documentation Completeness Check' section with Chinese text adds overhead. The property types table explains basic concepts (what a float or string is) that Claude already knows.	3 / 5
Actionability	The skill provides concrete, executable DSL code examples covering the main patterns (anonymous objects, named prototypes, inheritance, widget instantiation, Rust linking). The syntax reference table and property types are specific. However, the examples are somewhat isolated snippets rather than a complete working example, and the Rust struct linking example could be more complete.	4 / 5
Workflow Clarity	For a skill that is primarily about DSL syntax reference rather than a multi-step destructive process, the workflow is reasonably clear. The 'Documentation Completeness Check' provides a clear sequence (read files → check → fallback). The inheritance rules are well-sequenced with a concrete example. Minor gap: no explicit validation step for generated DSL code correctness.	4 / 5
Progressive Disclosure	The skill references two external files (`./references/dsl-syntax.md` and `./references/inheritance.md`) which is good structure, but no bundle files were provided, making it impossible to verify these references exist or are useful. The SKILL.md itself inlines a fair amount of reference material (syntax table, property types table, inheritance rules) that could arguably live in those reference files, creating redundancy with the referenced documents.	3 / 5
	Total	14 / 20 Passed

Description

58%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 excels at trigger term coverage and distinctiveness, with impressive multilingual keyword support and specific code patterns. However, it critically lacks any description of what the skill actually does — it reads more like a keyword index than a capability description. Adding concrete actions (e.g., 'Explains syntax rules, generates component definitions, resolves inheritance chains') would significantly improve it.

Suggestions

Add concrete action verbs describing what the skill does, e.g., 'Explains Makepad DSL syntax rules, generates component definitions, demonstrates inheritance and prototype patterns in live_design blocks.'

Restructure to separate the 'what it does' from the 'when to use it' — e.g., start with capability statements, then follow with 'Use when...' and the trigger list.

Dimension	Reasoning	Score
Specificity	The description names the domain (Makepad DSL syntax and inheritance) but provides no concrete actions. It doesn't say what the skill actually does — no verbs like 'generates', 'explains', 'converts', etc. It only lists trigger terms without describing capabilities.	2 / 5
Completeness	The 'when' is well-covered via the trigger list, but the 'what' is extremely vague — it only says 'Makepad DSL syntax and inheritance' without describing what actions the skill performs. There is no clear explanation of what the skill does beyond naming the topic area.	2 / 5
Trigger Term Quality	Excellent trigger term coverage including natural phrases ('makepad dsl', 'live_design', 'makepad inheritance'), code patterns ('"<Widget>"', '"Foo = { }"'), and even multilingual synonyms in Chinese ('makepad DSL 语法', 'makepad 继承', '如何定义 makepad 组件'). Very comprehensive for this niche domain.	5 / 5
Distinctiveness Conflict Risk	Highly distinctive with a very specific niche (Makepad DSL). The trigger terms are unique and unlikely to conflict with other skills. The inclusion of specific syntax patterns like '<Widget>' and 'Foo = { }' further reduces conflict risk.	5 / 5
	Total	14 / 20 Passed

Validation

90%

Warnings & errors only

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

Validation — 10 / 11 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	10 / 11 Passed

Repository: administrakt0r/AI-Agents-Safe-Coding-Skills
Path: skills/makepad-dsl/SKILL.md
Commit: fbdfd63

Reviewed: 3 days ago

Table of Contents

Discovery Implementation Validation

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.