Name: format-source
Rating: 63.2 (1 reviews)
Author: liferay

Blog Docs Log in Get started

format-source

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

Quality

75%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

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

Quality

Content

92%

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

The body is lean, highly actionable, and clearly sequenced with validation feedback for the formatter-driven workflow, but it presents its 47 rules as one large inline document rather than progressively disclosing them via reference files, which limits the progressive-disclosure score.

Suggestions

Consider moving the bulkier rule categories (e.g. naming conventions or ordering rules) into a referenced file under references/ so SKILL.md reads as an overview pointing to detail.

If the rules must stay inline, add a brief table of contents or grouped category index at the top so readers can jump to the relevant rule family without scanning all 47.

Dimension	Reasoning	Score
Conciseness	Each of the 47 rules is a tight 'Why' sentence plus a concrete diff, with no over-explanation of basic concepts and no padding; the length reflects breadth of scope rather than verbosity, so every token earns its place.	3 / 3
Actionability	Exact runnable commands ('cd <module-root> && <gradlew> formatSource', 'ant format-source-current-branch') and copy-paste-ready before/after diffs for every rule provide fully executable, specific guidance.	3 / 3
Workflow Clarity	The overall flow is explicitly sequenced ('run the formatter, apply the manual rules, then rerun the formatter') with a feedback loop ('if there are issues ... the formatter will list them. Fix them.') and a conflict-resolution rule ('the formatter wins'), so validation checkpoints are present for the batch operation.	3 / 3
Progressive Disclosure	The shell-script delegation is a well-signaled one-level reference with a clear Local-Checkout/Remote-Fallback resolution order, but the 47 manual rules sit as a monolithic inline block with no bundle files to split them into, fitting 'content that should be separate is inline' despite good in-file navigation.	2 / 3
	Total	11 / 12 Passed

Description

57%

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 to its Liferay niche and uses correct third-person voice, but it states only one action and omits any explicit 'Use when ...' trigger guidance, capping both trigger-term quality and completeness at 2.

Suggestions

Append a 'Use when ...' clause naming the trigger situations, e.g. 'Use when formatting Java, JavaScript, JSON, JSP, Markdown, properties, shell, XML, or YAML source to meet Liferay's standards'.

Expand the action list beyond a single verb to name the concrete operations (apply the automatic source formatter, apply manual rules the formatter misses, skip generated files).

Add common user-facing terms like 'lint', 'code style', and 'style guide' alongside 'format' to broaden natural trigger coverage.

Dimension	Reasoning	Score
Specificity	Names the domain ('source files', 'Liferay's coding standards') and a concrete action ('Format ... to align'), but lists only a single action rather than multiple specific formatting operations, matching the 'names domain and some actions, but not comprehensive' anchor.	2 / 3
Completeness	The 'what' is explicit ('Format source files to align with Liferay's coding standards') but there is no 'Use when ...' clause or equivalent trigger guidance, so per the judging guidelines completeness is capped at 2.	2 / 3
Trigger Term Quality	'format source files' and 'Liferay's coding standards' are terms a user might say, but common variations (lint, style, code style, formatting) are missing, fitting 'some relevant keywords but missing common variations'.	2 / 3
Distinctiveness Conflict Risk	Scoping to 'Liferay's coding standards' carves out a clear niche unlikely to trigger for unrelated skills, matching 'clear niche with distinct triggers; unlikely to conflict'; voice is correctly third person ('Format').	3 / 3
	Total	9 / 12 Passed

Validation

93%

Warnings & errors only

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

Validation — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
skill_md_line_count	SKILL.md is long (1044 lines); consider splitting into references/ and linking	Warning

	Total	15 / 16 Passed

Repository: liferay/liferay-portal
Path: .claude/skills/format-source/SKILL.md
Commit: ce5402e

Reviewed: 3 days ago

Table of Contents

Discovery Implementation Validation

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.