Name: makepad-platform
Rating: 57.599999999999994 (1 reviews)
Author: administrakt0r

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

Quality

66%

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

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

Quality

Content

63%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 action-oriented with solid executable Rust examples and a reasonable documentation-check workflow, but it carries time-sensitive metadata in the main flow and inlines reference-grade detail while pointing to a reference file that is missing. Moving stable reference material into the referenced file and trimming redundancy would tighten it.

Suggestions

Move the OsType enum, platform-detection API, and #[cfg] reference tables into ./references/platform-support.md and keep SKILL.md as an overview, which also resolves the missing-file reference.

Relocate 'Last Updated: 2026-01-19' and the dev-branch version note into a clearly marked update/deprecation note rather than the top banner, per the time-sensitive guidance.

Remove or fold the 'When Answering Questions' list into the existing sections to eliminate repetition of os_type()/cfg guidance.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient tables and code, but time-sensitive info ("Last Updated: 2026-01-19", "makepad-widgets (dev branch)") sits outside a deprecated/old-patterns section and the 'When Answering Questions' list repeats os_type()/cfg facts already shown; not 4 due to these unnecessary or time-bound tokens.	3 / 5
Actionability	It provides concrete executable Rust (the OsType enum, cx.os_type() API, #[cfg(target_os = "...")] blocks, app_main! entry point); not 5 because match arms use placeholder comments (/* macOS-specific */) and some API signatures are illustrative rather than copy-paste complete.	4 / 5
Workflow Clarity	The 'Documentation Completeness Check' is a clear read-file -> handle-failure -> incorporate sequence with an explicit error branch (inform user, fall back to SKILL.md + built-in knowledge); not 5 because there is no validate/retry feedback loop, though this non-destructive skill does not trigger the 3-cap.	4 / 5
Progressive Disclosure	Sections are well-organized, but the only referenced file (./references/platform-support.md) does not exist in the bundle, and bulk reference material (OsType enum, platform-detection API, cfg examples) is inlined rather than split out; this fits 'some structure, content that should be separate is inline' better than 4.	3 / 5
	Total	14 / 20 Passed

Description

68%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 has strong, explicit trigger coverage and a clear niche, but its 'what' is a vague domain label rather than a list of concrete actions. Adding 1-2 specific capabilities would lift specificity and completeness.

Suggestions

Replace the bare domain statement with 1-2 concrete actions, e.g. 'Explain supported platforms/backends and write platform-specific conditional code for Makepad.'

Trim technical tokens like 'OsType' and 'CxOs' from the trigger list in favor of phrases a user would naturally say, or move them to a secondary line.

Lead with the capability sentence before the trigger list so the 'what' reads as an action, not just a domain.

Dimension	Reasoning	Score
Specificity	The description names the domain ("Use for Makepad cross-platform support") but enumerates no concrete actions, only trigger terms; this matches 'Names the domain but actions are minimal or generic' rather than 3, which requires 1-2 concrete actions.	2 / 5
Completeness	It states both what ("Makepad cross-platform support") and an explicit when ("Triggers on: …"); not 5 because the 'what' is a domain label without concrete capabilities, and not 3 because explicit trigger guidance is present so the 3-cap does not apply.	4 / 5
Trigger Term Quality	It lists many natural trigger terms across platforms and backends ("makepad macos, makepad windows, makepad linux", "makepad metal, makepad d3d11, makepad opengl, makepad webgl") plus Chinese variants, giving good coverage; a 5 would require fuller synonym/extension coverage and fewer technical tokens like 'OsType' and 'CxOs'.	4 / 5
Distinctiveness Conflict Risk	Makepad-specific terms ("makepad platform", "OsType", "CxOs") carve a clear niche with minimal overlap risk against other skills.	5 / 5
	Total	15 / 20 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
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-platform/SKILL.md
Commit: 57c135b

Reviewed: 4 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.