gemini-review
Google Gemini CLI code review with Gemini 2.5 Pro, 1M token context, CI/CD integration
49
37%
Does it follow best practices?
Impact
Pending
No eval scenarios have been run
Advisory
Suggest reviewing before use
Optimize this skill with Tessl
npx tessl skill review --optimize ./skills/gemini-review/SKILL.mdQuality
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 bullet point than a functional skill description. It lacks concrete actions (what the skill actually does step-by-step), omits a 'Use when...' clause entirely, and relies on technical specifications rather than natural language triggers. The Gemini-specific terminology provides some distinctiveness but isn't enough to compensate for the missing completeness and action specificity.
Suggestions
Add an explicit 'Use when...' clause with natural trigger terms like 'Use when the user wants to review code using Gemini, run automated PR reviews, or integrate Gemini-based code analysis into CI/CD pipelines.'
Replace technical specs with concrete actions, e.g., 'Runs code reviews using Google Gemini CLI, analyzes pull requests, generates review feedback, and integrates review checks into CI/CD workflows.'
Include common user-facing trigger terms such as 'PR review', 'pull request', 'review my code', 'gemini review', and 'automated code review'.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names the domain (code review) and mentions some specifics (Gemini 2.5 Pro, 1M token context, CI/CD integration), but doesn't list concrete actions like 'analyze pull requests', 'generate review comments', or 'flag security issues'. The specifics mentioned are more about the tool's features than actionable capabilities. | 2 / 3 |
Completeness | Provides a partial 'what' (code review with Gemini CLI) but completely lacks a 'when' clause. There is no 'Use when...' or equivalent explicit trigger guidance, and per the rubric guidelines, a missing 'Use when...' clause should cap completeness at 2, but the 'what' itself is also weak and reads more like a feature list than a description, warranting 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 review', 'gemini cli', 'review my code', or 'automated review'. The term '1M token context' is a technical spec, not a natural trigger term. | 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, competitor comparisons), redundant installation instructions, and explanations of concepts Claude already knows. The monolithic structure with no progressive disclosure makes it an inefficient use of context window tokens.
Suggestions
Remove the 'Why Gemini?' section, benchmark tables, and comparison tables entirely — these are marketing content that don't help Claude perform code reviews.
Extract the GitHub Action workflows, GitLab CI config, and authentication options into separate referenced files (e.g., GITHUB-ACTION.md, GITLAB-CI.md, AUTH.md) to reduce the main skill to a concise overview.
Remove Node.js installation instructions — Claude knows how to install Node.js and this is basic prerequisite knowledge.
Add validation steps to CI/CD workflows: check if diff is non-empty before sending to Gemini, verify CLI installation succeeded, and validate review output before posting comments.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is extremely verbose at ~300+ lines. It includes unnecessary marketing content (benchmark tables, 'Why Gemini?' section), explains basic concepts Claude already knows (what Node.js is, how to install it via brew/nvm), and includes a comparison table with competitors that doesn't help Claude perform the task. The benchmark scores and feature/benefit tables are promotional filler. | 1 / 3 |
Actionability | The skill provides fully executable, copy-paste ready code throughout: complete GitHub Action YAML workflows, GitLab CI config, bash commands for installation and authentication, and concrete CLI usage examples with real flags and options. | 3 / 3 |
Workflow Clarity | The CI/CD workflows are clearly sequenced (checkout → install → review → post comment), but there are no validation checkpoints or error handling steps. For example, the GitHub Action doesn't check if the diff is empty, if Gemini CLI installed successfully, or if the review output is valid before posting. Missing feedback loops for CI/CD operations caps this at 2. | 2 / 3 |
Progressive Disclosure | This is a 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, and troubleshooting all in one file. There are no references to separate files for detailed topics like CI/CD setup or configuration guides. | 1 / 3 |
Total | 7 / 12 Passed |
Validation
90%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
d4ddb03
- Reviewed
Table of Contents
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.