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

57

Quality

66%

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-claude/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

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 code-rich and actionable with a sensible doc-check workflow, but it carries generic programming exposition and time-sensitive metadata that bloat the token budget, and it inlines tutorial material that should live in the (currently missing) referenced file.

Suggestions

Move the detailed syntax/built-in/async tutorial into ./references/splash-tutorial.md (create the file) and keep SKILL.md as a concise overview pointing to it, so the reference actually resolves.

Trim generic programming constructs (let/if-else/for/while basics) and the non-evergreen version/last-updated header, or relocate the latter to a clearly marked version/deprecation note.

Replace the partial `while condition { // ... }` and bare `cx.eval_with_context(code, context)` snippets with complete, runnable examples.

DimensionReasoningScore

Conciseness

Mostly efficient code-forward content, but the basic-syntax sections (let/fn/if-else/for/while) restate programming constructs Claude already knows, and the time-sensitive "Version: makepad-widgets (dev branch) | Last Updated: 2026-01-19" header adds non-evergreen tokens outside a deprecated section.

3 / 5

Actionability

Concrete, copy-paste-style examples for the script! macro, cx.eval, http.get/post, timer.set/interval/clear, and widget interaction cover the common cases; minor gaps like `while condition { // ... }` and bare `cx.eval_with_context(code, context)` signatures keep it just short of fully executable everywhere.

4 / 5

Workflow Clarity

The Documentation Completeness Check gives a clear sequenced procedure with a conditional fallback (read -> if empty/fails, inform user and answer from built-in knowledge -> otherwise incorporate content), and "When Answering Questions" adds ordered guidance; no destructive/batch cap applies.

4 / 5

Progressive Disclosure

Section headers give structure and there is a one-level-deep reference pointer ("./references/splash-tutorial.md"), but that referenced file does not exist in the bundle, and a large tutorial block (syntax, built-ins, async) that belongs in the reference is inlined directly in SKILL.md.

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 guidance and occupies a clearly distinct niche, but it underspecifies the concrete capabilities of the skill. Adding one or two concrete actions would lift specificity and the what-side of completeness.

Suggestions

Add concrete actions to the description, e.g. "Write and embed Splash scripts via script!, evaluate them at runtime with cx.eval, and drive Makepad widgets dynamically."

Expand the "what" beyond naming the language so the capability is explicit, not just the trigger terms.

DimensionReasoningScore

Specificity

It names the domain ("Makepad Splash scripting language") but the only action framing is "Use for", with no concrete capabilities like writing scripts, embedding via script!, or evaluating with cx.eval listed in the description.

2 / 5

Completeness

Both halves are present: a (thin) "what" ("Makepad Splash scripting language") and an explicit "when" ("Triggers on:" with a concrete list); the what could be more descriptive but the trigger guidance is explicit so it is not capped at 3.

4 / 5

Trigger Term Quality

A good spread of natural triggers ("makepad script", "makepad scripting", "splash language") plus technical markers ("script!", "cx.eval") and bilingual synonyms ("splash 语言", "makepad 脚本"), though a few natural phrasings are absent.

4 / 5

Distinctiveness Conflict Risk

Makepad Splash is a narrow niche with distinctive triggers ("splash language", "makepad script", "script!", "cx.eval") unlikely to fire for unrelated skills.

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.

Validation15 / 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
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.