gerrit

Submit, amend, and review Gerrit changes using git-review CLI. Use when asked to submit a patchset, download a change, rebase a change request, check CR status, or manage code reviews in Gerrit.

0.74x

Quality

89%

Does it follow best practices?

Impact

49%

0.74x

Average score across 2 eval scenarios

Securityby

Low

Low-risk findings worth noting

Quality

Content

86%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.

A well-structured, highly actionable skill body: executable command examples throughout, clean one-level-deep reference bundle, and workflows with verify steps. Minor room to improve conciseness (duplicated .gitreview example, "Model Guidance" section) and to inline a brief error-recovery loop.

Suggestions

Remove the duplicated .gitreview example by having the Configuration section point back to Initial Setup, and drop or merge the one-line "Model Guidance" section into the intro.

Add one short inline feedback loop after the submit step (e.g. "if `changes list` doesn't show the change, check `git review -v` output or see troubleshooting.md") rather than deferring all error handling to the reference file.

Dimension	Reasoning	Score
Conciseness	The body is dominated by lean, copy-paste command blocks with almost no concept explanation Claude already knows, but there is minor redundancy (the .gitreview example appears in full in both "Initial Setup" and "Configuration") and a low-value "Model Guidance" section — efficient with minor trimming possible, the score-4 anchor rather than the every-token-earns-its-place score-5 anchor.	4 / 5
Actionability	Every section gives executable, copy-paste-ready commands with flags and inline comments (e.g. `git review -d 12345,3`, `$SKILL_DIR/scripts/gerrit.py changes diff 12345 --patchset 3`), covering the common submit/download/amend/verify cases — fully matches the score-5 anchor.	5 / 5
Workflow Clarity	The "Daily Workflow" and "Reviewing Others' Changes" examples sequence steps and include explicit verify checkpoints ("# Verify submission", "# Verify new patchset uploaded"), but error-recovery guidance is entirely offloaded to troubleshooting.md with no inline feedback loop — clear sequence with most checkpoints, the score-4 anchor rather than the explicit fix-and-retry loops of score 5.	4 / 5
Progressive Disclosure	SKILL.md is a concise overview that clearly signals four one-level-deep references (permissions.md, common-workflows.md, advanced-usage.md, troubleshooting.md) at the right sections; all four files exist and link only to external docs or internal anchors, with no chained references — matches the score-5 clear-overview anchor.	5 / 5
	Total	18 / 20 Passed

Description

92%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.

A strong description: concrete actions, an explicit "Use when" clause with natural triggers, and a clearly pinned Gerrit niche. The only weakness is mild jargon ("CR status") in place of phrasing a user would naturally say.

Dimension	Reasoning	Score
Specificity	"Submit, amend, and review Gerrit changes using git-review CLI" plus trigger-side actions ("submit a patchset, download a change, rebase a change request") lists multiple concrete, specific actions covering the change lifecycle — matches the comprehensive-coverage anchor, not the score-4 anchor which expects minor coverage gaps.	5 / 5
Completeness	The "what" is explicit ("Submit, amend, and review Gerrit changes using git-review CLI") and the "when" is an explicit "Use when asked to..." clause with five concrete trigger phrases — clearly the score-5 anchor, not score 4 where the "when" could be more specific.	5 / 5
Trigger Term Quality	Natural phrases like "submit a patchset", "download a change", "manage code reviews in Gerrit" are present, but "check CR status" uses an abbreviation users would rarely say (vs. "code review status") and common synonyms like "Gerrit change" or "pull a change" are absent — good coverage with a few natural terms missing, the score-4 anchor.	4 / 5
Distinctiveness Conflict Risk	"Gerrit" appears in every clause, pinning the description to a distinct code-hosting niche with minimal conflict risk; the only generic phrase ("manage code reviews") is qualified by Gerrit, keeping it above the score-4 minor-overlap anchor.	5 / 5
	Total	19 / 20 Passed

Validation

100%

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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: odyssey4me/agent-skills
Path: skills/gerrit/SKILL.md
Commit: 666332c

Reviewed: 5 hours 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.