CtrlK
BlogDocsLog inGet started
Tessl Logo

format-source

Format source files to align with Liferay's coding standards.

59

Quality

69%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./.claude/skills/format-source/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

82%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 highly actionable with copy-paste commands and concrete diff examples, a clearly sequenced workflow with a formatter-driven feedback loop, and good structure that delegates shell/Go specifics to external files. It is slightly long in a few rule rationales and lacks an explicit verification checkpoint.

DimensionReasoningScore

Conciseness

The body assumes Claude's competence (no basics like 'a PDF is...') and each rule carries a one-sentence 'Why' plus tight diff examples, but a few narrative passages (the Brian Chan quote in Rule 45, several longer rationales) could be trimmed, keeping it just below the lean anchor.

4 / 5

Actionability

Copy-paste-ready commands ('cd <module-root> && <gradlew> formatSource', 'ant format-source-current-branch', 'gofmt -w .') and concrete before/after diff examples for every rule give fully executable guidance covering the common cases.

5 / 5

Workflow Clarity

The full workflow is explicitly sequenced (run formatter -> fix listed issues -> apply manual rules -> rerun formatter) with a feedback loop via the formatter listing issues, but there is no explicit 'review the diff / verify' checkpoint, so it sits below the checklist-level anchor.

4 / 5

Progressive Disclosure

Structure is clear (sections plus 47 numbered rules) and shell/Go styling is correctly delegated to well-signaled one-level-deep external files, but the 47 inlined rules make the core long to scan with only headers for navigation, so it is not a clean 5.

4 / 5

Total

17

/

20

Passed

Description

56%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 is concise and names a clear Liferay-specific niche, but it states only one generic action and omits any explicit 'Use when...' trigger guidance, capping completeness at 3.

Suggestions

Add an explicit 'Use when...' trigger clause (e.g., 'Use when formatting source, running the source formatter, or applying Liferay coding standards') to lift completeness above 3.

Expand beyond the single 'Format' verb to list 1-2 more concrete actions (e.g., 'runs the automatic source formatter and applies manual style rules') to raise specificity.

Include natural trigger synonyms users actually say — 'code style', 'lint', 'formatSource' — to broaden trigger-term coverage toward 5.

DimensionReasoningScore

Specificity

The phrase 'Format source files to align with Liferay's coding standards' names the domain but relies on a single generic action verb ('Format'), matching the 'Processes PDF files' anchor rather than the multi-action anchors above.

2 / 5

Completeness

It gives a clear 'what' ('Format source files to align with Liferay's coding standards') but includes no 'Use when...' trigger clause, so per the missing-trigger cap completeness cannot exceed 3.

3 / 5

Trigger Term Quality

'Format source files' and 'coding standards' are the natural phrases a Liferay developer would say, giving good keyword coverage; a few common synonyms ('code style', 'lint', 'formatSource') are absent.

4 / 5

Distinctiveness Conflict Risk

The 'Liferay's coding standards' qualifier carves a clear niche and lowers conflict risk, but 'format source files' alone overlaps with generic formatter skills, keeping it just below the minimal-conflict anchor.

4 / 5

Total

13

/

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

skill_md_line_count

SKILL.md is long (1066 lines); consider splitting into references/ and linking

Warning

Total

15

/

16

Passed

Repository
liferay/liferay-portal
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.