gerrit-frontend-engineering

Provides guidance and best practices on Polygerrit UI development, frontend architecture, and TypeScript/JS coding standards in Gerrit.

Quality

60%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./configs/skills/gerrit_frontend_engineering/SKILL.md

Quality

Content

50%

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

The content is highly actionable with concrete, executable Don't/Do code examples, but it is severely over-long and monolithic: a single 114KB file with heavily redundant rule framing and no progressive disclosure to separate reference files. Workflow clarity is decent at the per-rule level but lacks end-to-end validation feedback loops.

Suggestions

Split the guide into one SKILL.md overview plus per-chapter reference files (e.g. references/lit-idioms.md, references/testing.md, references/api-integration.md) with clear one-level-deep links, so SKILL.md becomes a navigable index rather than a 2,900-line monolith.

Remove the verbatim redundancy where the 'Rule', 'What', and 'Why' blocks restate the same sentence three times; collapse each rule to a single concise statement plus the Don't/Do example to cut token cost dramatically.

Add an explicit end-to-end workflow with validation checkpoints (e.g. write component -> run queryAndAssert/visualDiff -> fix -> re-validate) for the batch test and API-migration operations the skill covers.

Dimension	Reasoning	Score
Conciseness	The ~2,940-line body is heavily padded with executive summaries, per-rule 'Context/What/Applies To/Why' repetitions (the Rule, What, and Why statements frequently restate identical content verbatim), and verbose marketing-style prose ('uncompromising', 'authoritative source of tribal knowledge'), matching the 'verbose; explains concepts Claude knows; padded with unnecessary context' anchor. Not 2 because the redundant framing vastly inflates token cost beyond what an intelligent reader needs; the same rules could be conveyed in a fraction of the length.	1 / 3
Actionability	Rules provide complete, copy-paste-ready Don't/Do code pairs in TypeScript/HTML, specific utilities (queryAndAssert, classMap, reportServerError), and concrete file references (gr-rest-api-impl.ts), matching the 'fully executable code/commands; copy-paste ready' anchor. Not 2 because examples are real and complete rather than pseudocode; cannot exceed 3 on this scale.	3 / 3
Workflow Clarity	Each rule sequences a problem and a fix and several reference validation utilities (queryAndAssert, assert.shadowDom.equal, parse-before-filter checks), but there is no overarching multi-step workflow with explicit validate->fix->retry checkpoints for the batch/destructive operations (test suites, API migrations) the skill covers, which caps it at 2. Not 1 because individual rules are clearly ordered and many embed fail-fast assertions; not 3 because no end-to-end feedback-loop workflow is presented.	2 / 3
Progressive Disclosure	The entire 114KB guide is a monolithic wall of text in a single SKILL.md with no bundle files (no references/, scripts/, assets/) and no one-level-deep external links, matching the 'monolithic wall of text; poor organization' anchor. Not 2 because nothing is split into separate reference files and the body is far too large to serve as an overview; not below 1 as section headings do exist.	1 / 3
	Total	7 / 12 Passed

Description

70%

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 occupies a clearly distinct niche, but it lacks any 'Use when...' trigger guidance, which caps completeness. Trigger-term coverage is decent but omits common user phrasings like 'code review' or 'Lit'.

Suggestions

Add an explicit trigger clause, e.g. 'Use when modifying Polygerrit UI components, writing Lit/TypeScript in Gerrit, or working on Gerrit frontend architecture'.

Surface natural user phrasings such as 'code review UI', 'Gerrit components', and 'Lit' that a user would actually say when requesting this skill.

Consider naming the concrete actions the skill performs (e.g. 'enforce coding standards, avoid UI regressions, structure Lit components') instead of 'provides guidance and best practices'.

Dimension	Reasoning	Score
Specificity	Names multiple concrete domains (Polygerrit UI development, frontend architecture, TypeScript/JS coding standards in Gerrit), which clearly enumerate what the skill covers, matching the 'Lists multiple specific concrete actions' anchor. Not 2 because it catalogs several distinct capability areas rather than a single domain; not below because the actions are concrete and specific.	3 / 3
Completeness	It states what the skill does ('Provides guidance and best practices on...') but lacks any 'Use when...' clause or explicit trigger guidance, capping completeness at 2 per the guideline. Not 3 because 'when to use' is entirely absent; not 1 because the 'what' is clearly and concretely stated.	2 / 3
Trigger Term Quality	It surfaces likely user terms ('Polygerrit', 'Gerrit', 'TypeScript/JS', 'frontend architecture'), but is missing common phrasings like 'code review', 'Gerrit UI components', or 'Lit' that a user would actually say. Not 3 because coverage of natural user phrasings is incomplete; not 1 because real domain keywords are present.	2 / 3
Distinctiveness Conflict Risk	The narrow Polygerrit/Gerrit frontend niche with TypeScript/JS specifics makes it highly distinguishable and unlikely to trigger for unrelated skills, matching the 'Clear niche with distinct triggers' anchor. Not 2 because the domain is uniquely specific rather than broadly overlapping; not below 3 because the niche is genuinely distinct.	3 / 3
	Total	10 / 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 (2939 lines); consider splitting into references/ and linking	Warning

	Total	15 / 16 Passed

Repository: GerritCodeReview/gerrit
Path: configs/skills/gerrit_frontend_engineering/SKILL.md
Commit: 32dbdfa

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.