CtrlK
CommunityDocumentationLog inGet started
Tessl Logo

code-reviewer

tessl install github:google-gemini/gemini-cli --skill code-reviewer
github.com/google-gemini/gemini-cli

Use this skill to review code. It supports both local changes (staged or working tree) and remote Pull Requests (by ID or URL). It focuses on correctness, maintainability, and adherence to project standards.

Review Score

72%

Validation Score

12/16

Implementation Score

63%

Activation Score

75%

SKILL.md
Review
Evals

Generated

Validation

Total

12/16

Score

Passed
CriteriaScore

description_trigger_hint

Description may be missing an explicit 'when to use' trigger hint (e.g., 'Use when...')

metadata_version

'metadata' field is not a dictionary

license_field

'license' field is missing

body_output_format

No obvious output/return/format terms detected; consider specifying expected outputs

Implementation

Suggestions 3

Score

63%

Overall Assessment

This skill provides a well-structured workflow for code review with clear sequencing and good use of CLI commands. However, it over-explains review concepts Claude already understands (correctness, maintainability, etc.) and lacks concrete examples of expected output format or sample feedback. The actionability would improve significantly with a concrete example of a review comment.

Suggestions

  • Remove or significantly condense the 'In-Depth Analysis' pillars section - Claude already knows how to evaluate code for correctness, security, etc. Instead, focus on project-specific standards or preferences.
  • Add a concrete example of expected feedback output showing what a 'Critical' finding vs 'Improvement' vs 'Nitpick' looks like in practice.
  • Consider extracting the detailed feedback structure and tone guidelines to a separate REVIEW_FORMAT.md file, keeping SKILL.md as a lean workflow overview.
DimensionScoreReasoning

Conciseness

2/3

The content is reasonably efficient but includes some unnecessary explanation (e.g., the detailed breakdown of review pillars like 'Correctness', 'Maintainability' are concepts Claude already knows well). The workflow structure adds value but could be tighter.

Actionability

2/3

Provides concrete commands for git and gh CLI operations, but the core review analysis section is descriptive rather than instructive. Missing specific examples of what good feedback looks like or concrete output formats.

Workflow Clarity

3/3

Clear sequential workflow with distinct phases (Determine Target → Preparation → Analysis → Feedback → Cleanup). Includes validation checkpoint via preflight, and the branching logic for remote vs local is explicit and well-structured.

Progressive Disclosure

2/3

Content is reasonably organized with clear sections, but everything is inline in one file. The review pillars section and feedback structure could be split into referenced files for a cleaner overview, especially given the skill's length.

Activation

Suggestions 2

Score

75%

Overall Assessment

This description effectively communicates when to use the skill and establishes a clear niche for code review tasks. However, it could be stronger by listing more specific review actions (e.g., 'identify bugs', 'check for security issues') and including additional natural trigger terms users might use when requesting code reviews.

Suggestions

  • Add more specific concrete actions like 'identify bugs, check security issues, suggest refactoring, verify test coverage' to improve specificity
  • Include additional natural trigger terms users might say such as 'check my code', 'diff', 'review changes', 'MR', 'merge request'
DimensionScoreReasoning

Specificity

2/3

Names the domain (code review) and mentions some scope (local changes, staged/working tree, remote PRs), but doesn't list specific concrete actions like 'identify bugs', 'check style violations', or 'suggest refactoring'.

Completeness

3/3

Explicitly answers both what ('review code... focuses on correctness, maintainability, and adherence to project standards') and when ('Use this skill to review code... local changes or remote Pull Requests by ID or URL').

Trigger Term Quality

2/3

Includes some natural terms like 'review code', 'Pull Requests', 'PR', 'URL', 'staged', but misses common variations users might say like 'code review', 'check my code', 'diff', 'changes', 'MR' (merge request).

Distinctiveness Conflict Risk

3/3

Clear niche focused specifically on code review with distinct triggers (PR, Pull Request, staged changes, working tree) that wouldn't easily conflict with general coding or documentation skills.