gemini-review

Google Gemini CLI code review with Gemini 2.5 Pro, 1M token context, CI/CD integration

Quality

—

Does it follow best practices?

Impact

—

No eval scenarios have been run

Securityby

Advisory

Suggest reviewing before use

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 body is highly actionable with abundant executable commands and ready-to-use CI/CD configs, but it is a long, monolithic document padded with promotional/comparison content and organized as an options catalog rather than a sequenced workflow with validation checkpoints. Splitting large reference material into separate files and trimming marketing tables would improve it most.

Suggestions

Move the full GitHub Action / GitLab CI YAML examples and the Claude-vs-Codex-vs-Gemini comparison into separate referenced files (e.g. CI.md, COMPARISON.md) to apply progressive disclosure and cut the main body's token load.

Remove or condense the 'Benchmark Performance' and marketing-style 'Why Gemini' tables, which add tokens without instructional value.

Add a concise ordered 'Review workflow' with explicit checkpoints (get diff -> run review -> verify JSON/markdown output -> post comment), so the multi-step process has validation steps instead of being an options catalog.

Dimension	Reasoning	Score
Conciseness	Most of the body is concrete commands and config, but it is padded with non-essential marketing content ("Benchmark Performance" table, the full "Claude vs Codex vs Gemini" comparison, three overlapping CI/CD YAML examples), matching 'mostly efficient but includes some unnecessary content that could be tightened' rather than the lean score-3 anchor.	2 / 3
Actionability	Commands and full YAML examples are concrete, executable, and copy-paste ready (e.g. `gemini -p "..." --output-format json`, `npm install -g @google/gemini-cli`, complete GitHub Action workflows), matching the 'fully executable, copy-paste ready' anchor.	3 / 3
Workflow Clarity	The body is organized as a catalog of options rather than a sequenced workflow, and the CI/CD examples post automated comments without explicit validation/verification checkpoints or a validate-fix-retry loop, matching 'steps/options listed but checkpoints missing or implicit' rather than the score-3 example with explicit validation.	2 / 3
Progressive Disclosure	It is a single ~450-line monolithic SKILL.md with no bundle files or references, and content that could be split (full CI/CD YAMLs, comparison tables) is kept inline; sections are well-organized so it avoids the score-1 'wall of text', but it lacks the one-level-deep external references the score-3 anchor expects.	2 / 3
	Total	9 / 12 Passed

Description

72%

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 distinctive, naming the Gemini tool, code-review action, and CI/CD integration with natural trigger terms. Its main gap is that the 'when to use' trigger sits in the separate when-to-use field rather than the description, leaving the description itself answering 'what' but not 'when'.

Suggestions

Fold an explicit trigger into the description, e.g. "Use when the user requests Gemini-powered code review or needs large-context (1M token) review of large codebases or CI/CD pipelines."

Expand the action list from the single phrase "code review" to concrete actions like "review PR diffs, post review comments, and analyze large repositories" to lift specificity toward 3.

Dimension	Reasoning	Score
Specificity	Names the domain and a couple of actions ("code review", "CI/CD integration") but does not list multiple distinct concrete actions (e.g. review PRs, analyze diffs, post comments), so it matches the 'names domain and some actions, not comprehensive' anchor rather than the multi-action score-3 example.	2 / 3
Completeness	The description field clearly answers 'what' (Gemini CLI code review) but contains no explicit 'when'/'Use when' trigger; that guidance lives in the separate when-to-use field, so per the rubric's cap on a missing 'Use when' clause in the description it is a 2, not the 3 that requires an explicit trigger in the description itself.	2 / 3
Trigger Term Quality	Natural terms a user would say are present — "Google Gemini", "code review", and "CI/CD" — giving good coverage of how a user would request this, matching the 'good coverage of natural terms' anchor.	3 / 3
Distinctiveness Conflict Risk	"Google Gemini CLI code review with Gemini 2.5 Pro, 1M token context" carves out a clear niche distinct from Claude or Codex review skills, making wrong-skill triggering unlikely, matching the 'clear niche with distinct triggers' anchor.	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
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: alinaqi/claude-bootstrap
Commit: 9dacc46

Reviewed: about 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.