CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

gemini-review

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

55

Quality

69%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./skills/gemini-review/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

63%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.

The content is highly actionable, with executable commands and complete CI configurations throughout, and the setup workflow includes verification steps and troubleshooting. Its weaknesses are verbosity (marketing and comparison tables, stale-prone version/quota details) and a monolithic structure that inlines material better split into reference files.

Suggestions

Cut the "Why Gemini for Code Review?", "Benchmark Performance", and "Claude vs Codex vs Gemini" sections — they are marketing material that spends tokens without instructing.

Move the full GitHub Action, GitLab CI, and GEMINI.md example into files under references/ and keep one short example inline with clear links.

Isolate time-sensitive details (model versions, quota limits, extension version requirements) in a single clearly-labeled section so they can be updated without restating them throughout the body.

DimensionReasoningScore

Conciseness

The ~450-line body includes several padded marketing sections Claude does not need — "Why Gemini for Code Review?", benchmark tables ("SWE-Bench Verified 63.8%"), and a "Claude vs Codex vs Gemini" comparison — plus time-sensitive version and quota figures ("Requires Gemini CLI v0.4.0+", "1,000 requests/day", "GPT-5.2-Codex") that will go stale.

2 / 5

Actionability

Nearly every section gives copy-paste-ready, executable commands and configs: install commands with verification ("npm install -g @google/gemini-cli", "gemini --version"), headless invocations ("gemini -p \"...\" --output-format json"), and complete GitHub Action and GitLab CI YAML files covering the common automation cases.

5 / 5

Workflow Clarity

The install → authenticate → review (interactive or headless) → CI sequence is clear, with explicit checkpoints ("Verify installation", "Verify extension", "gemini extensions list") and a troubleshooting table for error recovery, though later sections (GitHub/GitLab/config) are parallel recipes rather than one validated workflow.

4 / 5

Progressive Disclosure

The file is well-sectioned with headers, but it is a single ~450-line monolith with no bundle files; content that clearly belongs in separate references — full CI workflow YAML, the GEMINI.md template, the CLI quick reference, the comparison tables — is all inlined.

3 / 5

Total

14

/

20

Passed

Description

61%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.

The description is specific about the tool and model and reads naturally, but it omits any 'use when' trigger guidance and describes only a single action rather than a range of concrete capabilities. Adding an explicit trigger clause and one or two more concrete actions would lift it substantially.

Suggestions

Append an explicit trigger clause, e.g. "Use when the user asks for Gemini-powered code review, wants a large-context review of a big codebase, or mentions Gemini, /code-review, or PR review automation."

List 2-3 concrete actions instead of one, e.g. "Reviews branch diffs and PRs, posts findings as GitHub/GitLab comments, runs in CI".

Include common user synonyms such as "PR review" or "pull request review" in the description so trigger matching catches natural phrasings.

DimensionReasoningScore

Specificity

The description names the domain and one concrete action ("code review") plus the tool ("Google Gemini CLI", "Gemini 2.5 Pro") and features ("1M token context", "CI/CD integration"), but does not list several specific actions like the score-4 anchor requires.

3 / 5

Completeness

It has a clear 'what' (Gemini CLI code review with 2.5 Pro) but no 'Use when...' clause or equivalent trigger guidance in the description itself, which caps completeness at 3 per the rubric guidelines.

3 / 5

Trigger Term Quality

"code review", "Gemini", and "CI/CD" are natural phrases users would say, giving good keyword coverage, though common variations like "PR review" or "pull request" are missing.

4 / 5

Distinctiveness Conflict Risk

Naming "Google Gemini CLI" carves out a distinct niche versus generic review skills, leaving only minor overlap risk with closely related code-review skills; it is not quite the fully distinct trigger set of a 5.

4 / 5

Total

14

/

20

Passed

Validation

93%

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

CriteriaDescriptionResult

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

Total

15

/

16

Passed

Repository

alinaqi/maggy

Path

skills/gemini-review/SKILL.md

Revision

55aabe2

Reviewed

Table of Contents

DiscoveryImplementationValidation

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.

Claim skill