CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

makepad-skills

Makepad UI development skills for Rust apps: setup, patterns, shaders, packaging, and troubleshooting.

Quality

48%

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 ./skills/makepad-skills/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

18%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 an empty shell: it repeats the frontmatter description three times, links to the source repository, and provides no instructions, code, or workflows despite claiming coverage of setup, patterns, shaders, packaging, and troubleshooting. A Claude loading this skill would learn nothing actionable about Makepad development.

Suggestions

Replace the placeholder Instructions section with concrete, executable guidance — e.g. project scaffolding commands (cargo makepad), a minimal Live DSL widget example, and a shader-snippet pattern.

Split the five claimed topic areas into one-level-deep reference files (e.g. references/setup.md, references/shaders.md, references/packaging.md) and link them from clearly-labeled sections, instead of repeating the topic list.

Remove the duplicated Overview/When-to-Use/Instructions repetition and the double trailing period, and add a real 'When to use' trigger list so the body stops re-stating the description.

DimensionReasoningScore

Conciseness

The body is short, but the same sentence is repeated three times ('makepad ui development skills for rust apps: setup, patterns, shaders, packaging, and troubleshooting' appears in Overview, When to Use, and Instructions verbatim, including a duplicated trailing period), so tokens are spent without adding information. It matches the score-3 anchor — mostly efficient but includes unnecessary content that could be cut — and is not 2 because there is no over-explanation of known concepts.

3 / 5

Actionability

The Instructions section says only 'This skill provides guidance and patterns for...' — it describes rather than instructs, with no code, commands, examples, or concrete steps anywhere. This exactly matches the score-1 anchor ('entirely vague or abstract; no concrete code or commands; only describes rather than instructs').

1 / 5

Workflow Clarity

No steps or sequence of any kind are present — the claimed scope (setup, patterns, shaders, packaging, troubleshooting) implies multi-step workflows, but the body provides none. This matches the score-1 anchor ('steps missing or incoherent; no sequence').

1 / 5

Progressive Disclosure

Section headers exist (Overview, When to Use, Instructions) and there is a single clearly-signaled external link (the source repository), but the skill claims five substantive topic areas while providing zero reference files and zero inline detail — no references/, scripts/, or assets/ exist in the bundle. This matches the score-2 anchor (minimal structure; the substance the sections promise is absent) rather than 3, because there is no content at all to organize or navigate to.

2 / 5

Total

7

/

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 correctly identifies its niche and uses appropriate third-person voice, but it reads as a topic inventory rather than an action description, and it entirely lacks 'when to use' trigger guidance. It is serviceable but generic within its niche.

Suggestions

Add an explicit trigger clause, e.g. 'Use when the user works with Makepad, mentions makepad widgets/Live DSL, or asks about Rust UI development with Makepad.'

Replace the bare topic list with concrete actions, e.g. 'Set up Makepad projects, build widgets with the Live DSL, write Metal/GLSL shaders, package apps for desktop/mobile, and debug common Makepad errors.'

Include natural synonyms and specifics users would actually type ('cargo makepad', 'Live language', 'Makepad widgets') to improve trigger-term coverage.

DimensionReasoningScore

Specificity

The description names its domain ("Makepad UI development skills for Rust apps") and lists topic areas ("setup, patterns, shaders, packaging, and troubleshooting"), but these are bare topic labels rather than concrete verb-object actions like 'extract text from PDF files'. It sits between the score-3 anchor (domain plus limited actions) and the score-4 anchor (several specific actions with minor gaps), and the generic labels ('patterns', 'setup') keep it at 3 rather than 4.

3 / 5

Completeness

The 'what' is reasonably clear (Makepad UI development guidance covering setup, patterns, shaders, packaging, troubleshooting), but there is no 'when' — no 'Use when...' clause or equivalent trigger guidance, which the judging guidelines cap at 3. It is not 2 because the 'what' half is genuinely present and domain-specific.

3 / 5

Trigger Term Quality

Relevant keywords exist — 'Makepad', 'Rust', 'UI', 'shaders', 'packaging' — and a user asking about Makepad would plausibly say them, matching the score-3 anchor. But it misses common variations and natural phrases users would say when needing this skill (e.g. 'makepad widgets', 'live DSL', 'cargo makepad', '.rs'), so it does not reach 'good keyword coverage' at 4.

3 / 5

Distinctiveness Conflict Risk

'Makepad' is a specific niche framework, making this mostly distinct from generic Rust or UI skills with only minor overlap risk with general Rust-development skills — matching the score-4 anchor. It falls short of 5 because the phrase 'UI development skills for Rust apps' is broad enough to compete with general Rust UI tooling when Makepad isn't explicitly named.

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.

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

skills/makepad-skills/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.