gerrit-hygiene-operations

Provides rules, patterns, and best practices for code hygiene, formatting, downstream plugin dependencies, and release operations in Gerrit.

Quality

61%

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_hygiene_operations/SKILL.md

Quality

Content

65%

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 code and real identifiers, but it is verbose and monolithic — an executive summary, duplicated summary tables, and per-chapter restatements inflate the token budget, and there are no validation checkpoints for the destructive/batch operations it governs.

Suggestions

Cut the Executive Summary and the per-chapter Summary tables; keep one concise top-level overview and let the chapter rules carry the detail.

Add explicit validation/verification steps to the destructive or batch operations (experiment decommissioning, downstream release rollout) — e.g. confirm no remaining references to a deleted fallback method before merging.

Split the seven chapters into reference files (e.g. references/formatting.md, references/release-ops.md) and keep SKILL.md as a short overview with one-level-deep links.

Dimension	Reasoning	Score
Conciseness	The body carries genuine tribal knowledge but is padded with an Executive Summary, a top-level Summary table, per-chapter Context blocks, and repeated per-chapter Summary tables that restate the same points, so it is mostly efficient but could be tightened well below anchor 3.	2 / 3
Actionability	Most rules pair concrete Do/Don't TypeScript snippets with real identifiers (GrRestApiServiceImpl, getChangesForMultipleQueries, gr-reply-dialog.ts) and an exact `Release-Notes:` footer format, matching the copy-paste-ready anchor 3.	3 / 3
Workflow Clarity	This is a rule catalog rather than a sequenced workflow, and operations that are effectively destructive or batch (experiment decommissioning, downstream release rollout) lack explicit validation checkpoints, capping it at anchor 2 per the feedback-loop guideline.	2 / 3
Progressive Disclosure	The skill is a single monolithic 539-line SKILL.md with no references/scripts/assets bundle and no split-out detail files, so although chapters are well organized, content that should be separate stays inline, matching anchor 2 rather than the one-level-deep reference pattern of anchor 3.	2 / 3
	Total	9 / 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 clearly Gerrit-scoped and reasonably specific, but it omits any explicit "Use when..." trigger guidance, which caps its completeness and trigger-term quality. Adding a trigger clause would lift the weakest dimensions.

Suggestions

Append an explicit trigger clause, e.g. "Use when working in the Gerrit codebase on code hygiene, formatting, downstream plugin releases, or commit/release-note automation."

Replace the abstract "Provides rules, patterns, and best practices" with concrete verbs (e.g. "Enforces formatting rules, audits downstream plugin dependencies, prunes dead experiment code, and injects release-note footers").

Surface natural trigger terms users would say ("Gerrit commit footer", "downstream plugin release", "visual regression flakiness") to broaden keyword coverage.

Dimension	Reasoning	Score
Specificity	Names the Gerrit domain and several areas ("code hygiene, formatting, downstream plugin dependencies, and release operations") but the action verb is the abstract "Provides rules, patterns, and best practices" rather than listing multiple concrete actions, so it sits at anchor 2 rather than 3.	2 / 3
Completeness	It clearly states what the skill provides but lacks any "Use when..." clause or equivalent explicit trigger guidance, which per the guidelines caps completeness at 2.	2 / 3
Trigger Term Quality	Includes relevant natural terms ("Gerrit", "code hygiene", "formatting", "release operations") but misses common variations and has no explicit trigger phrasing, placing it at anchor 2 rather than the full coverage of anchor 3.	2 / 3
Distinctiveness Conflict Risk	The Gerrit-specific framing ("in Gerrit", downstream plugin dependencies, release operations) carves a clear niche with distinct triggers unlikely to collide with other skills, matching anchor 3.	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 (539 lines); consider splitting into references/ and linking	Warning

	Total	15 / 16 Passed

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

Reviewed: 4 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.