CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

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

70%

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-platform/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

60%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 a solid, actionable quick-reference with real Makepad specifics (platform/backends table, OsType, Cx APIs, entry point), weakened by a missing referenced file and some boilerplate padding. Creating references/platform-support.md and trimming the generic #[cfg] gallery would move it into the top band.

Suggestions

Create the referenced ./references/platform-support.md (or remove the reference and the documentation-completeness workflow) — currently the sole detailed-reference pointer is dead, so the skill always answers from the overview alone.

Cut the 20-line #[cfg(target_os)] example gallery down to one or two lines plus a note that standard Rust cfg attributes apply; likewise drop the 'You are an expert...' role preamble.

Define or link the AndroidParams and WebParams structs used by OsType, and add one code snippet (e.g., matching WebParams or handling app lifecycle) under the Platform-Specific Features sections so they instruct rather than merely list.

DimensionReasoningScore

Conciseness

The Makepad-specific material (platform/backend table, OsType enum, Cx detection methods) earns its tokens, but it is padded with things Claude already knows: a ~20-line gallery of standard #[cfg(target_os)] boilerplate, an 'You are an expert at Makepad cross-platform development' role preamble, and generic bullet lists like 'Touch input / Virtual keyboard / Screen orientation'. Matches anchor 3 ('mostly efficient but some unnecessary explanation or could be tightened'): not 2 because the bulk is genuinely non-obvious framework info, not 4 because the cfg section and role preamble are clearly trimmable.

3 / 5

Actionability

Concrete, executable Rust is provided: the cx.os_type() match example, Cx method signatures (os_type, gpu_info, xr_capabilities, cpu_cores), the #[cfg] attributes, and a complete app_main! entry skeleton. Matches anchor 4 ('mostly executable guidance with minor gaps'): not 5 because AndroidParams/WebParams are used in the OsType enum but never defined, and the 'Platform-Specific Features' sections list capabilities without any accompanying code or API names; not 3 because the core examples are real, compilable-style code rather than pseudocode.

4 / 5

Workflow Clarity

The 'Documentation Completeness Check' is a clear conditional sequence with explicit branches: read the reference file, on failure inform the user ('本地文档不完整...') and fall back to SKILL.md patterns + built-in knowledge, on success incorporate its content. No destructive or batch operations exist, so no cap applies. Matches anchor 4 ('clear sequence with most checkpoints present'): not 5 because there is no verification beyond file existence (e.g., no check that the reference actually covers the asked platform), not 3 because the branch points are explicit rather than implicit.

4 / 5

Progressive Disclosure

The body's only external reference, './references/platform-support.md - Platform details and OsType', does not exist — there is no references/ directory in the bundle, so every documented path falls into the 'file read fails' branch. A clearly signaled but dangling reference is a broken disclosure structure: worse than anchor 3's 'references present but not clearly signaled', and at anchor 2's level of failure. Not 1 because the body itself has coherent section structure and the reference is only one level deep.

2 / 5

Total

13

/

20

Passed

Description

67%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 an excellent, distinctive trigger list but fails to state what the skill actually does. Adding 2-3 concrete capability statements (e.g., 'Explain supported platforms and graphics backends, write platform-conditional code, detect the runtime platform via OsType') would raise both specificity and completeness significantly.

Suggestions

Replace the bare 'Use for Makepad cross-platform support' with a capability sentence such as: 'Explains Makepad's supported platforms and graphics backends, helps write platform-conditional code (#[cfg]), and shows how to detect the runtime platform via cx.os_type()/OsType.'

Keep the trigger list but trim near-duplicates (e.g., 'makepad os' vs 'makepad platform') so the description stays scannable while the freed tokens describe capabilities.

State the scope boundary in one clause (e.g., 'covers platform detection, conditional compilation, and per-platform features') so the 'what' is explicit, not implied by the trigger terms.

DimensionReasoningScore

Specificity

'Use for Makepad cross-platform support' names the domain but states no concrete actions or capabilities — no verbs describing what the skill does (explain platforms, write conditional code, detect platform at runtime). It sits at anchor 2 ('names the domain but actions are minimal or generic'): above 1 because the domain and purpose are clearly identified, below 3 because not even 1-2 concrete actions are listed.

2 / 5

Completeness

The 'when' is explicit and strong ('Use for Makepad cross-platform support. Triggers on: ...'), but the 'what' is only a vague domain label with no stated capabilities — the mirror image of anchor 3's example (clear what, missing when). It is above 2 because the when-clause and trigger list are explicit and rich, and below 4 because 'Makepad cross-platform support' is not a clear statement of what the skill does.

3 / 5

Trigger Term Quality

The trigger list covers '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' — comprehensive natural terms including platform synonyms, graphics-backend names, API identifiers, and Chinese equivalents. This matches anchor 5 (comprehensive coverage including synonyms); it is not 4 because essentially every natural phrase a user would say for this topic is present.

5 / 5

Distinctiveness Conflict Risk

Every trigger is prefixed with the niche framework name 'makepad' or is a Makepad-specific API type (OsType, CxOs), giving a clear niche with minimal conflict risk against any other skill. This matches anchor 5; no neighboring anchor fits better since the vocabulary is unambiguously Makepad-scoped.

5 / 5

Total

15

/

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-platform/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.