CtrlK
BlogDocsLog inGet started
Tessl Logo

cleanup-unused-assets

Reduce plugin size by scanning resources/icons and removing unreferenced assets.

64

Quality

76%

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 ./.agents/skills/cleanup-unused-assets/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

85%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The content is a lean, well-sequenced workflow with strong validation checkpoints for a destructive asset-removal task. Its main gap is actionability in the core detection step, which relies on vague guidance rather than a concrete search command.

Suggestions

Make the reference search concrete, e.g. "For each asset, run `grep -rn "<filename>" src/ plugin.xml` and treat zero hits as unused."

Replace "other asset directories" with a specific list (e.g., resources/icons, resources/images, META-INF) or a discovery command so the scan step is unambiguous.

Optionally note how to handle near-matches or dynamic references so deletions are safe rather than purely zero-reference based.

DimensionReasoningScore

Conciseness

The body is lean and assumes Claude's competence — it gives gradle/git commands and step headers without explaining what icons or plugins are, and the only minor redundancy (a duplicated objective line) does not rise to unnecessary concept explanation.

3 / 3

Actionability

It provides concrete executable commands (./gradlew test/verifyPlugin/buildPlugin/testClasses) and a git message example, but the core detection step is vague — "Check if each asset is referenced in code or plugin.xml" and "other asset directories" lack a specific search command, leaving key details missing.

2 / 3

Workflow Clarity

The six numbered steps are clearly sequenced with a Baseline validation checkpoint and a Verify step that checks for missing-resource exceptions and regressions, giving an explicit feedback loop for a destructive batch operation.

3 / 3

Progressive Disclosure

At under 50 lines with no external references needed, the skill is well-organized into Objective and numbered Workflow sections, which per the guidelines lets a simple single-purpose skill score 3 on progressive disclosure.

3 / 3

Total

11

/

12

Passed

Description

67%

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 is specific and distinct, clearly stating what the skill does, but it lacks explicit "when to use" trigger guidance and natural user phrasing like "unused assets". Adding a Use-when clause with common variations would raise completeness and trigger quality.

Suggestions

Append an explicit trigger clause, e.g. "Use when reducing IntelliJ plugin size by removing unused icons, images, or other unreferenced assets."

Replace or pair the technical term "unreferenced assets" with the more natural "unused icons/images/assets" so it matches what users actually say.

Mention the broader asset scope (images and other resources) in the trigger to improve coverage of common variations.

DimensionReasoningScore

Specificity

The description lists multiple concrete actions — "scanning resources/icons and removing unreferenced assets" — tied to a specific location, matching the anchor for listing several specific concrete actions rather than vague language.

3 / 3

Completeness

The "what" is explicit (scan resources/icons, remove unreferenced assets), but there is no "Use when..." clause or equivalent trigger guidance, which per the guidelines caps completeness at 2.

2 / 3

Trigger Term Quality

It includes relevant terms like "plugin size", "icons", and "assets", but uses the technical "unreferenced" and omits natural variations users would say such as "unused icons/assets" or "clean up", so coverage is incomplete.

2 / 3

Distinctiveness Conflict Risk

The combination of plugin resources/icons and unreferenced-asset removal defines a clear niche unlikely to trigger for unrelated skills, matching the distinct-triggers anchor.

3 / 3

Total

10

/

12

Passed

Validation

100%

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

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
flutter/flutter-intellij
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.