go-review

Senior Go code reviewer for comprehensive code reviews focused on correctness, security, performance, and maintainability. Use when reviewing Go code for bugs, best practices, and production readiness.

Quality

62%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./plugins/dev-skills/skills/go-review/SKILL.md

Quality

Content

46%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 skill provides good concrete Go code examples for common issues and a structured review template, which are its strongest elements. However, it is significantly over-verbose, spending many tokens on review philosophy, categorization definitions, and feedback style guidance that Claude already understands. The monolithic structure with no progressive disclosure wastes context window on content that could be referenced on demand.

Suggestions

Remove or drastically reduce the Review Principles, Review Categories, and Feedback Style sections — Claude already knows how to categorize severity, be respectful, and be specific in code reviews.

Extract the review checklist and common Go issues into separate referenced files (e.g., CHECKLIST.md, COMMON_ISSUES.md) to reduce the base skill's token footprint.

Add validation steps to the workflow, such as verifying that all changed files were reviewed and confirming test coverage was checked before rendering a verdict.

Specify concrete commands for PR review (e.g., `gh pr diff <number>` or `git diff main..HEAD`) rather than vague 'fetch PR diff using git'.

Dimension	Reasoning	Score
Conciseness	Significantly verbose. The role description ('10+ years of experience'), extensive review principles, category definitions (Critical/Major/Minor), feedback style section ('Be Respectful', 'Be Educational'), and review checklists all explain things Claude already knows as a senior code reviewer. The common Go issues examples are valuable, but the surrounding scaffolding is heavily padded. The full review template is also unnecessarily detailed for Claude.	2 / 5
Actionability	The common Go issues section provides excellent, executable before/after code examples covering race conditions, SQL injection, resource leaks, floating point, and context propagation. The review template is concrete and usable. However, the task execution section lacks specific commands (e.g., how to fetch PR diffs) and the CLI usage block at the top implies tool integration that isn't fully specified.	4 / 5
Workflow Clarity	The task execution section provides a reasonable sequence (read code → check tests → identify issues → provide examples → make decision), and the review template gives structure. However, there are no validation checkpoints or feedback loops — no step to verify findings, no guidance on re-reviewing after fixes, and no explicit verification that the review is complete or accurate.	3 / 5
Progressive Disclosure	This is a monolithic ~250-line file with no references to external files and no bundle structure. The review checklists, common issues catalog, feedback style guide, and review template could all be split into separate referenced files. Everything is inlined, making the skill heavy to load into context for every invocation.	2 / 5
	Total	11 / 20 Passed

Description

78%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 well-structured with a clear 'what' and explicit 'when' clause, making it functionally complete. Its main weakness is that the capabilities listed are high-level categories (correctness, security, performance) rather than concrete actions, and it's missing some natural trigger terms like 'golang' or 'PR review'. Overall it's a solid description that would enable reliable skill selection.

Suggestions

Replace abstract categories with concrete actions, e.g., 'Identifies race conditions, checks error handling, reviews goroutine usage, validates input sanitization' instead of 'correctness, security, performance, maintainability'.

Add natural trigger term variations such as 'golang', '.go files', 'PR review', 'pull request review', 'code quality' to improve matching.

Dimension	Reasoning	Score
Specificity	Names the domain (Go code review) and mentions several review dimensions (correctness, security, performance, maintainability), but these are abstract categories rather than concrete actions. It doesn't describe specific actions like 'identifies race conditions', 'checks error handling patterns', or 'analyzes memory allocations'.	3 / 5
Completeness	Clearly answers both 'what' (comprehensive code reviews focused on correctness, security, performance, and maintainability) and 'when' (explicit 'Use when reviewing Go code for bugs, best practices, and production readiness') with concrete trigger phrases.	5 / 5
Trigger Term Quality	Includes good natural keywords like 'Go code', 'code review', 'bugs', 'best practices', 'production readiness'. Missing some natural variations users might say such as 'golang', 'code quality', 'PR review', 'pull request', or '.go files'.	4 / 5
Distinctiveness Conflict Risk	Fairly distinct by specifying Go language and the review focus areas. Could potentially overlap with a general code review skill or a Go linting/formatting skill, but the combination of 'Go' + 'comprehensive code review' + specific focus areas makes it mostly distinct.	4 / 5
	Total	16 / 20 Passed

Validation

81%

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 — 9 / 11 Passed

Validation for skill structure

Criteria	Description	Result
allowed_tools_field	'allowed-tools' contains unusual tool name(s)	Warning
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	9 / 11 Passed

Repository: rikdc/ai-skills
Path: plugins/dev-skills/skills/go-review/SKILL.md
Commit: a43676e

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.