CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

makepad-basics

CRITICAL: Use for Makepad getting started and app structure. Triggers on: makepad, makepad getting started, makepad tutorial, live_design!, app_main!, makepad project setup, makepad hello world, "how to create makepad app", makepad 入门, 创建 makepad 应用, makepad 教程, makepad 项目结构

Quality

78%

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/antigravity-bundle-makepad-builder/skills/makepad-basics/SKILL.md

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

SKILL.md
Quality
Evals
Security

Quality

Content

71%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 lean, highly actionable getting-started body whose code examples are complete and copy-paste ready, weakened by a broken reference layer (both referenced files are missing from the bundle) and the absence of an explicit ordered setup-and-run sequence. Fixing the dangling references and adding the final run step would lift the weakest dimensions.

Suggestions

Ship the referenced files or remove the references: './references/app-structure.md' and './references/event-handling.md' are cited but absent from the bundle, leaving the Documentation section and its completeness-check workflow pointing at nothing.

Add an explicit ordered quick-start sequence: 1. cargo new my_app, 2. add the makepad-widgets dependency, 3. paste the boilerplate into main.rs, 4. cargo run — the current sections are parallel patterns with no run step.

Trim the 'You are an expert...' role preamble and fold the Documentation Completeness Check into one line; the Chinese fallback message duplicates what a simple 'if the reference read fails, answer from the patterns below' already conveys.

DimensionReasoningScore

Conciseness

The body is mostly dense, earning content: complete Rust and TOML examples plus compact API and platform tables. Minor padding could be trimmed — the 'You are an expert at the Rust makepad-widgets crate' role preamble and the six-line 'IMPORTANT: Documentation Completeness Check' meta-section — keeping it below anchor 5 but above anchor 3, since nothing extensively re-teaches concepts Claude already knows.

4 / 5

Actionability

Concrete, copy-paste-ready guidance throughout: full live_design!/app_main! boilerplate, Cargo.toml dependency setup, button-click handling, and widget access patterns. Minor gaps keep it below anchor 5 — there is no project-creation or build/run command (e.g., 'cargo run') to complete the getting-started flow.

4 / 5

Workflow Clarity

As a simple single-purpose skill the main action (write a basic Makepad app) is largely unambiguous via the complete boilerplate and the 'When Writing Code' checklist, but the sections are parallel patterns rather than an ordered create → configure → run sequence, and the run step is missing. No destructive or batch operations exist, so no validation cap applies.

4 / 5

Progressive Disclosure

Section structure is good and the two references ('./references/app-structure.md', './references/event-handling.md') are clearly signaled in a Documentation section, but neither file exists in the bundle (no references/ directory is present), so the navigation is dangling. This breaks the structure expected of anchor 4, while the body itself is well-organized rather than a monolith, keeping it above anchor 2.

3 / 5

Total

15

/

20

Passed

Description

76%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.

A highly triggerable, distinctly-scoped description with excellent keyword coverage in both English and Chinese, but it spends nearly all its budget on when-to-use terms and almost none on stating concrete capabilities. Adding two or three action statements would raise both specificity and completeness.

Suggestions

Replace the 'CRITICAL:' urgency framing with one or two sentences of concrete capabilities, e.g., 'Generates Makepad app boilerplate (live_design!, app_main!), configures Cargo.toml with the makepad-widgets dependency, and implements event handling.'

State what the skill does with action verbs (generate, configure, explain) rather than naming topics only ('getting started and app structure').

Trim 'makepad' repeats across trigger phrases to free budget for capability statements while keeping the distinct variants.

DimensionReasoningScore

Specificity

"Use for Makepad getting started and app structure" names the domain but states no concrete actions — the remainder of the description is a trigger keyword list, not capabilities. It does not reach anchor 3 because even one or two action verbs (e.g., 'generate app boilerplate', 'set up projects') are absent, and it is above anchor 1 because the domain is named specifically.

2 / 5

Completeness

Explicit trigger guidance is present and strong ('Triggers on: ...' enumerating concrete phrases), and the 'what' ('Makepad getting started and app structure') is present. It falls short of anchor 5 because the 'what' names topics rather than stating what the skill does, making it thinner than the 'when'.

4 / 5

Trigger Term Quality

The trigger list is comprehensive and natural: base term ('makepad'), phrase variants ('makepad getting started', 'makepad hello world', 'how to create makepad app'), framework-specific macros ('live_design!', 'app_main!'), and Chinese synonyms ('makepad 入门', '创建 makepad 应用', 'makepad 教程', 'makepad 项目结构'). File extensions are not applicable to a framework skill, and no natural term a user would say is missing.

5 / 5

Distinctiveness Conflict Risk

Every trigger is Makepad-specific — 'live_design!' and 'app_main!' are macros that exist only in Makepad — so the skill occupies a clear niche with minimal overlap or wrong-trigger risk.

5 / 5

Total

16

/

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/antigravity-bundle-makepad-builder/skills/makepad-basics/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.