CtrlK
BlogDocsLog inGet started
Tessl Logo

cleanup-unused-assets

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

58

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

Quality

Content

78%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 concise, well-structured workflow with concrete Gradle commands and validation checkpoints on both ends of a destructive operation. Its main gap is the missing executable command for the usage-scan step and the lack of an explicit error-recovery loop after verification.

Suggestions

Replace the vague 'Check if each asset is referenced in code or plugin.xml' with a concrete command, e.g., `rg -l <asset_name> src/ plugin.xml` or a script invocation, to make the search step copy-paste executable.

Add an explicit feedback loop after Verify (e.g., 'If buildPlugin fails with missing resource exceptions, restore the deleted asset and re-run ./gradlew verifyPlugin').

Deduplicate the objective statement that appears in both the intro paragraph and the '## Objective' section to recover a few tokens.

DimensionReasoningScore

Conciseness

The body is efficient with concrete commands and no concept over-explanation, but the objective is restated ('Reduce plugin size by removing unused icons, images, and resources' appears in both the intro and the Objective section), the kind of minor trim a 4 anchor describes rather than the lean 5.

4 / 5

Actionability

Provides concrete executable commands (./gradlew test, verifyPlugin, buildPlugin, testClasses) and a specific directory (resources/icons), but the core 'Search Usages' step says only to 'check if each asset is referenced in code or plugin.xml' without an actual grep/ripgrep command, a minor gap that keeps it off 5.

4 / 5

Workflow Clarity

A clearly sequenced six-step workflow with validation checkpoints on both ends (Baseline runs test/verifyPlugin before; Verify runs buildPlugin, testClasses, test, verifyPlugin after), so the destructive-operation cap does not apply; it stays at 4 because there is no explicit error-recovery feedback loop (e.g., 'if missing resource exceptions occur, restore the asset and re-verify').

4 / 5

Progressive Disclosure

The skill is under 50 lines, single-purpose, well-organized into labeled sections (Objective, Workflow Instructions 1-6), and needs no external bundle files, so the simple-skill exception lets well-organized sections alone score 5.

5 / 5

Total

17

/

20

Passed

Description

53%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 states a clear, specific purpose and niche but omits any 'Use when...' trigger guidance, which caps completeness at 3 and limits trigger-term quality. Adding an explicit usage trigger with synonyms and file extensions would raise both completeness and trigger quality.

Suggestions

Add an explicit 'Use when...' clause (e.g., 'Use when reducing plugin size, removing unused icons/images, or cleaning up unreferenced resources') to answer the 'when' half of completeness.

Include natural synonyms and concrete file types/extensions (e.g., '.png', '.svg', 'plugin.xml') to broaden trigger-term coverage.

Reinforce distinctiveness by naming the target platform context (e.g., IntelliJ/Gradle plugin) so the skill does not collide with generic asset-cleanup skills.

DimensionReasoningScore

Specificity

Names the domain (plugin size reduction) and two concrete actions ('scanning resources/icons' and 'removing unreferenced assets'), matching the '1-2 concrete actions but not comprehensive' anchor; it is not a 4 because only two actions are listed and coverage is limited.

3 / 5

Completeness

Provides a clear 'what' (reduce plugin size by scanning and removing unreferenced assets) but has no 'Use when...' clause or equivalent trigger guidance, so completeness is capped at 3 per the rubric guideline.

3 / 5

Trigger Term Quality

Contains some relevant natural terms ('plugin size', 'unused assets', 'unreferenced assets', 'icons') but misses common variations, synonyms, and file extensions, fitting the 'some relevant keywords but missing variations' anchor rather than the fuller coverage of a 4.

3 / 5

Distinctiveness Conflict Risk

The plugin-asset-cleanup niche is specific and unlikely to overlap with unrelated skills, fitting 'mostly distinct; minor overlap risk'; it is not a 5 because there are no explicit distinct trigger phrases.

4 / 5

Total

13

/

20

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.