CtrlK
BlogDocsLog inGet started
Tessl Logo

makepad-splash

CRITICAL: Use for Makepad Splash scripting language. Triggers on: splash language, makepad script, makepad scripting, script!, cx.eval, makepad dynamic, makepad AI, splash 语言, makepad 脚本

48

Quality

52%

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-splash/SKILL.md

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

SKILL.md
Quality
Evals
Security

Quality

Content

57%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 skill provides a reasonable overview of Splash scripting with concrete code examples covering core syntax, built-in objects, and widget interaction. Its main weaknesses are moderate verbosity (explanatory sections that don't add actionable value), lack of workflow structure for how to actually develop/debug scripts, and uncertainty about whether the referenced tutorial file exists. The content reads more like a language reference card than a focused skill guide.

Suggestions

Remove or significantly trim the 'Use Cases' and 'When Answering Questions' sections—Claude can infer these, and they consume tokens without adding actionable guidance.

Add a brief workflow section showing how to create, test, and debug a Splash script (e.g., write script → embed with script!{} or cx.eval() → check console output → iterate), with explicit validation steps.

Ensure the referenced `./references/splash-tutorial.md` actually exists in the bundle, or inline the essential content and remove the reference to avoid a broken progressive disclosure chain.

DimensionReasoningScore

Conciseness

The skill includes some unnecessary sections like 'Use Cases' (a list of obvious applications Claude can infer) and 'When Answering Questions' tips that are somewhat redundant. The code examples are reasonably concise but the overall document could be tightened—e.g., the 'What is Splash?' bullet list and use cases section add little actionable value.

3 / 5

Actionability

Provides concrete, executable-looking code examples for variables, functions, control flow, HTTP, timers, widget interaction, and async operations. However, it's unclear how verified these examples are—Splash is a niche/emerging language and some patterns (like `ui.widget()`, `button.on_click()`) may be speculative. The `script!{}` and `cx.eval()` Rust integration examples are concrete and useful.

4 / 5

Workflow Clarity

There is no multi-step workflow with validation checkpoints. The 'IMPORTANT: Documentation Completeness Check' section provides a 3-step process for Claude, which is good, but the actual scripting guidance lacks any workflow sequencing—no steps for creating, testing, or debugging scripts. For a scripting language skill this is acceptable but not strong.

3 / 5

Progressive Disclosure

References `./references/splash-tutorial.md` for detailed documentation, which is good progressive disclosure in principle. However, no bundle files were provided, so we can't verify the reference exists. The SKILL.md itself inlines a substantial amount of content (basic syntax, built-ins, async, widget interaction) that could potentially be split into the reference file, with the SKILL.md serving as a leaner overview.

3 / 5

Total

13

/

20

Passed

Description

47%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 providing trigger terms for skill selection but critically lacks any explanation of what the skill actually does. It reads more like a keyword list than a skill description. Adding concrete actions (e.g., 'Writes, debugs, and explains Makepad Splash scripts') would significantly improve its utility.

Suggestions

Add concrete capability descriptions: e.g., 'Writes, debugs, and explains Makepad Splash scripting language code for dynamic UI behavior and AI-driven interactions.'

Include a 'Use when...' clause that combines the trigger terms with actionable context: e.g., 'Use when the user needs to write, modify, or understand Splash scripts, or mentions splash language, makepad scripting, script!, or cx.eval.'

DimensionReasoningScore

Specificity

The description names the domain (Makepad Splash scripting language) but provides no concrete actions. It doesn't describe what the skill actually does—no verbs like 'write', 'generate', 'debug', 'interpret', etc.

2 / 5

Completeness

The 'when' is explicitly covered with trigger terms, but the 'what' is almost entirely missing—there's no description of what the skill actually does beyond identifying the domain. The description tells Claude when to use it but not what it does.

2 / 5

Trigger Term Quality

Good coverage of trigger terms including natural variations ('splash language', 'makepad script', 'makepad scripting', 'script!', 'cx.eval') and even Chinese equivalents. Missing some potential user phrases like 'write splash code' or '.splash files', but overall solid keyword coverage.

4 / 5

Distinctiveness Conflict Risk

The skill targets a very specific niche (Makepad Splash scripting language) with distinctive trigger terms like 'cx.eval' and 'script!'. Minor overlap risk with general scripting or Makepad UI skills, but the specific terms make it mostly distinct.

4 / 5

Total

12

/

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.