gemini-review

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

Quality

37%

Does it follow best practices?

Impact

—

No eval scenarios have been run

Securityby

Advisory

Suggest reviewing before use

Optimize this skill with Tessl

npx tessl skill review --optimize ./skills/gemini-review/SKILL.md

Quality

Discovery

32%

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 reads more like a product tagline or feature list than a functional skill description. It lacks concrete actions (what specific tasks does it perform?) and entirely omits trigger guidance (when should Claude select this skill?). The Gemini-specific terminology provides some distinctiveness but the overall description is too terse and vague to reliably guide skill selection.

Suggestions

Add explicit concrete actions such as 'Reviews code changes, analyzes pull requests, identifies bugs and security issues, generates inline review comments using Google Gemini CLI'.

Add a 'Use when...' clause with natural trigger terms like 'Use when the user asks for code review via Gemini, wants to run Gemini CLI for PR analysis, or needs AI-powered code feedback in CI/CD pipelines'.

Replace spec-like details ('1M token context') with user-facing capability descriptions like 'handles large codebases and multi-file reviews'.

Dimension	Reasoning	Score
Specificity	Names the domain (code review) and mentions some specifics (Gemini 2.5 Pro, 1M token context, CI/CD integration), but these read more like feature specs than concrete actions. It doesn't list specific actions like 'analyze pull requests', 'generate review comments', or 'flag security issues'.	2 / 3
Completeness	Partially addresses 'what' (code review with Gemini CLI) but completely lacks a 'when' clause. There is no 'Use when...' or equivalent trigger guidance, which per the rubric should cap completeness at 2, and since the 'what' is also weak, this scores a 1.	1 / 3
Trigger Term Quality	Includes some relevant keywords like 'code review', 'Gemini', 'CI/CD', but misses common user variations like 'pull request review', 'PR feedback', 'review my code', 'gemini cli'. The terms are somewhat technical and product-specific rather than natural user language.	2 / 3
Distinctiveness Conflict Risk	The mention of 'Google Gemini CLI' and 'Gemini 2.5 Pro' provides some distinctiveness from generic code review skills, but 'code review' and 'CI/CD integration' are broad enough to overlap with other code review or CI/CD-related skills.	2 / 3
	Total	7 / 12 Passed

Implementation

42%

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

The skill provides highly actionable, executable code examples for Gemini CLI code review across multiple platforms, which is its primary strength. However, it is severely bloated with marketing content (benchmarks, feature tables, tool comparisons), redundant installation options, and content that should be split across multiple files. The lack of validation steps in CI/CD workflows and the monolithic structure significantly reduce its effectiveness as a skill document.

Suggestions

Remove the 'Why Gemini?' section, benchmark tables, and comparison tables entirely - these are marketing content that wastes tokens and Claude already understands tool tradeoffs

Split into multiple files: keep SKILL.md as a concise overview with quick-start, then create separate files like GITHUB_ACTIONS.md, GITLAB_CI.md, and AUTHENTICATION.md for detailed configurations

Add validation checkpoints to CI/CD workflows: verify diff is non-empty before sending to Gemini, check review output is meaningful before posting, and add error handling for API failures

Consolidate authentication to recommend one primary method with a brief note about alternatives, rather than detailing three full options inline

Dimension	Reasoning	Score
Conciseness	Extremely verbose at ~350+ lines. Includes unnecessary marketing content (benchmark tables, 'Why Gemini?' section), explains basic concepts Claude already knows (what Node.js is, how to install via brew/nvm), includes a comparison table with other tools that's tangential to the skill's purpose, and has redundant information throughout. The benchmark scores and feature/benefit tables waste significant tokens.	1 / 3
Actionability	Provides fully executable code throughout: complete GitHub Actions YAML workflows, GitLab CI config, bash commands for installation/authentication, and specific CLI flags. The CI/CD examples are copy-paste ready with proper secrets handling and step sequencing.	3 / 3
Workflow Clarity	The CI/CD workflows are well-sequenced with clear steps, but there are no validation checkpoints or error recovery steps. For example, the GitHub Action doesn't verify the review output before posting, and there's no feedback loop for handling failed reviews or empty diffs. The headless mode section lacks verification that the review was meaningful.	2 / 3
Progressive Disclosure	Monolithic wall of text with everything inline - installation, authentication (3 options), interactive use, headless mode, GitHub integration (3 options), GitLab CI, configuration, CLI reference, comparison tables, troubleshooting, and anti-patterns all in one file. No bundle files exist to offload detailed content like the full GitHub Action workflows or the comparison tables.	1 / 3
	Total	7 / 12 Passed

Validation

90%

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 — 10 / 11 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	10 / 11 Passed

Repository: alinaqi/claude-bootstrap
Commit: 7e5f7a2

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.