CtrlK
BlogDocsLog inGet started
Tessl Logo

makepad-platform

CRITICAL: Use for Makepad cross-platform support. Triggers on: makepad platform, makepad os, makepad macos, makepad windows, makepad linux, makepad android, makepad ios, makepad web, makepad wasm, makepad metal, makepad d3d11, makepad opengl, makepad webgl, OsType, CxOs, makepad 跨平台, makepad 平台支持

52

Quality

59%

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/skills/makepad-platform/SKILL.md

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

SKILL.md
Quality
Evals
Security

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.

A solid platform reference skill with good executable code examples and a useful platform support table. Main weaknesses are moderate verbosity (meta-instructions, obvious feature lists) and incomplete progressive disclosure—the skill inlines content that could be in reference files while referencing a file that may not exist. Adding build/deploy commands per platform would significantly increase actionability.

Suggestions

Remove or significantly trim the 'Platform-Specific Features' section—listing 'Touch input' for mobile and 'File dialogs' for desktop tells Claude nothing it doesn't already know.

Add concrete build/run commands for each platform (e.g., `cargo makepad wasm run` or equivalent) to make the skill more actionable for cross-platform deployment.

Move the 'IMPORTANT: Documentation Completeness Check' meta-instructions to a less prominent position or trim them—they consume tokens on every load and are procedural boilerplate.

Ensure the referenced `./references/platform-support.md` bundle file actually exists and contains the detailed content promised, or inline the essential details if no bundle is available.

DimensionReasoningScore

Conciseness

The skill includes some unnecessary sections like the 'IMPORTANT: Documentation Completeness Check' meta-instructions and the platform-specific features section which lists obvious capabilities (e.g., 'Touch input' for mobile, 'File dialogs' for desktop) that Claude already knows. The 'When Answering Questions' section also partially restates what's already shown in the code examples. However, the code examples and tables are reasonably tight.

3 / 5

Actionability

Provides concrete, executable Rust code for OsType matching, conditional compilation, platform detection APIs, and the app entry point. The code examples are copy-paste ready. Minor gap: no build/run commands for different platforms (e.g., how to compile for web/wasm vs native), which would be highly actionable for cross-platform work.

4 / 5

Workflow Clarity

For a reference-style skill about platform support, the content is well-sequenced: platform table → OsType enum → detection APIs → conditional compilation → entry point. There's no destructive or batch operation requiring validation checkpoints. The 'When Answering Questions' section provides a clear decision framework (runtime vs compile-time detection). Minor gap: no workflow for adding platform-specific code to an existing app.

4 / 5

Progressive Disclosure

References `./references/platform-support.md` for detailed documentation, which is good, but no bundle files were provided to verify this exists. The SKILL.md itself inlines a fair amount of content (platform table, multiple code examples, feature lists) that could potentially be split. The reference is a single file rather than topic-organized references, and the platform-specific features section is a shallow list that either belongs in a reference file or should be removed.

3 / 5

Total

14

/

20

Passed

Description

54%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 with an extensive list of platform names, rendering backends, and multilingual keywords, making it highly discoverable. However, it critically lacks any description of what the skill actually does—there are no concrete actions or capabilities listed. The description reads more like a keyword index than a functional description.

Suggestions

Add concrete actions describing what the skill does, e.g., 'Guides platform-specific configuration, build setup, and rendering backend selection for Makepad applications across macOS, Windows, Linux, Android, iOS, and web targets.'

Include a 'Use when...' clause that connects the trigger terms to user intent, e.g., 'Use when the user needs help configuring Makepad for a specific OS, selecting a rendering backend, or troubleshooting platform-specific build issues.'

DimensionReasoningScore

Specificity

The description names the domain (Makepad cross-platform support) but provides no concrete actions. It doesn't explain what the skill actually does—no verbs like 'configures', 'builds', 'deploys', or 'detects'. It only lists trigger terms without describing capabilities.

2 / 5

Completeness

The 'when' is explicitly addressed with trigger terms, but the 'what' is almost entirely missing—'cross-platform support' is extremely vague and doesn't explain what actions or guidance the skill provides. Without a clear 'what', completeness is capped low.

2 / 5

Trigger Term Quality

Excellent coverage of trigger terms including platform names (macos, windows, linux, android, ios, web), rendering backends (metal, d3d11, opengl, webgl, wasm), internal API terms (OsType, CxOs), and even Chinese-language synonyms (跨平台, 平台支持). Very comprehensive for matching user queries.

5 / 5

Distinctiveness Conflict Risk

The Makepad-specific terminology and platform/backend combinations make this fairly distinct. Minor overlap risk exists with general cross-platform development skills, but the Makepad prefix on most triggers and the specific API terms (OsType, CxOs) reduce conflict significantly.

4 / 5

Total

13

/

20

Passed

Validation

90%

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

Validation10 / 11 Passed

Validation for skill structure

CriteriaDescriptionResult

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
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.