CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

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

76%

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 ./plugins/AI-Agents-Safe-Coding-Skills-claude/skills/makepad-dsl/SKILL.md

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

SKILL.md
Quality
Evals
Security

Quality

Content

78%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.

A strong, dense DSL reference: executable examples, lookup tables, and an explicit fallback workflow for missing documentation. Its weaknesses are trimmable meta-padding (persona, restated rules, inline version/date) and references that point to files absent from the bundle.

Suggestions

Ship the referenced files (references/dsl-syntax.md, references/inheritance.md) or remove the references section; pointing at nonexistent files undermines the skill's progressive-disclosure structure.

Trim the persona preamble, the 'When Answering Questions' section (which restates the Inheritance Rules), and move the version/last-updated note out of the main body or into a clearly labeled versioning note.

Merge the duplicated notation coverage between the Key Patterns examples and the DSL Syntax Reference table so each construct appears once.

DimensionReasoningScore

Conciseness

The bulk is lean, Makepad-specific material Claude does not know (syntax tables, inheritance rules, compact code examples), but there is trimmable padding: the persona preamble ('You are an expert...'), the 'When Answering Questions' section restating the Inheritance Rules, and inline time-sensitive info ('Version: makepad-widgets (dev branch) | Last Updated: 2026-01-19') that is not in a deprecated/old-patterns section. It is above anchor 3 because the over-explanation is minor relative to the dense reference content, but not anchor 5.

4 / 5

Actionability

Five copy-paste-ready DSL examples (anonymous object, named prototype, inheritance with override, widget instantiation, Rust struct linking via {{MyWidget}}) plus the syntax and property-type tables cover the common cases fully. The examples are complete and executable within live_design!, matching the top anchor.

5 / 5

Workflow Clarity

The Documentation Completeness Check is a clear sequence with an explicit feedback loop (read reference files; if read fails or file is empty, inform the user and still answer from SKILL.md; otherwise incorporate the content). However, the code-writing path is a rules list ('When Writing Code') with no sequence or checkpoints, leaving minor gaps — clear but not fully checkpointed across both tasks.

4 / 5

Progressive Disclosure

The body is well-sectioned and the two references ('./references/dsl-syntax.md', './references/inheritance.md') are clearly signaled and only one level deep, but neither file exists in the bundle — the references/ directory is absent entirely, so navigation dead-ends. The inline content is self-sufficient and the completeness check anticipates missing files, which keeps this at the midpoint rather than 2, but the offload-to-references design does not function in this bundle.

3 / 5

Total

16

/

20

Passed

Description

63%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 excels at trigger coverage — rich natural keywords in both English and Chinese with concrete syntax tokens users would paste — but it never states what the skill actually does. It reads as a pure trigger declaration: strong *when*, missing *what*.

Suggestions

Add one or two concrete capability statements, e.g. 'Write Makepad live_design! DSL code and explain DSL inheritance and property overriding.'

State the *what* explicitly alongside the existing 'Use for' clause so the description answers both 'what does this do' and 'when to use it' without relying on the body.

Consider dropping or qualifying the generic quoted tokens ('<Widget>', 'Foo = { }') that can appear in non-Makepad widget DSLs, to reduce false triggers.

DimensionReasoningScore

Specificity

The description names the domain ("Makepad DSL syntax and inheritance") but states no concrete actions — there is no equivalent of 'writes DSL code' or 'explains inheritance'. It matches the anchor 'Names the domain but actions are minimal or generic' rather than anchor 3, which requires 1-2 concrete actions to be listed.

2 / 5

Completeness

'CRITICAL: Use for ... Triggers on:' provides an explicit and concrete *when*, but the *what* is only a topic phrase with no capability statement. This falls between anchor 2 (when present without what) and anchor 4 (both present); the when is strong but the what is never articulated, so it sits at the midpoint rather than above it.

3 / 5

Trigger Term Quality

The trigger list ('makepad dsl, live_design, makepad inheritance, makepad prototype, "<Widget>", "Foo = { }", makepad object, makepad property') covers the natural terms users would say or paste, and adds Chinese synonyms ('makepad DSL 语法, makepad 继承, makepad 原型'). Coverage is comprehensive for this domain; no common variation is missing.

5 / 5

Distinctiveness Conflict Risk

The makepad-specific terms form a clear niche with minimal conflict risk, but the generic quoted tokens "<Widget>" and "Foo = { }" are widget-creation syntax also found outside Makepad (e.g., Flutter-style DSLs), creating minor overlap risk. Not 5 because of these generic tokens; not 3 because every other trigger is unambiguously Makepad-scoped.

4 / 5

Total

14

/

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

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

Path

plugins/AI-Agents-Safe-Coding-Skills-claude/skills/makepad-dsl/SKILL.md

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.