code-review

Review changed code against project standards. Checks for missing tests, dead code, type safety, lint issues, and coding conventions. Run after completing any implementation work.

Quality

85%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Quality

Content

92%Weight 40%Scale 1-3

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

An exceptionally actionable, well-sequenced review checklist built almost entirely of project-specific rules and concrete commands. Its only weakness is structure: it is a single monolithic file with no reference files to offload the lengthy standards catalog.

Suggestions

Extract the large 'Code Standards' catalog into a referenced file (e.g. references/standards.md) and keep SKILL.md as the review-step overview, improving progressive_disclosure.

Consider splitting the integration/MCP/backup-release-specific steps into a separate reference so the core review workflow stays scannable.

Dimension	Reasoning	Score
Conciseness	Nearly every line is project-specific hard rules and concrete examples Claude would not already know; it assumes competence and avoids explaining generic concepts. Not below 3 because the length is project-specific substance, not padding.	3 / 3
Actionability	Provides concrete git commands, exact script/grep commands, specific file paths and set names, and explicit severity classifications — fully executable, copy-paste-ready guidance.	3 / 3
Workflow Clarity	A clearly sequenced 13-step checklist with validation embedded throughout (lint reporting, dead-code/type-safety checks, severity-graded findings). Not below 3 because explicit verification and feedback are present.	3 / 3
Progressive Disclosure	No bundle files exist and the ~260-line body is monolithic with no external references; the large standards catalog is inline rather than split out. Not score 1 because sections are well-organized, but it exceeds the under-50-line simple-skill allowance for a 3.	2 / 3
	Total	11 / 12 Passed

Description

77%Weight 40%Scale 1-3

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

A specific, action-oriented description with an explicit use-when clause, but its trigger guidance is phrased as an auto-instruction rather than natural user keywords, and its scope is broad enough to risk overlap with general coding skills.

Suggestions

Reword the trigger as natural user-facing terms (e.g., 'Use when the user asks to review a diff, check a PR, or audit changed code') to improve trigger_term_quality.

Narrow the 'after completing any implementation work' scope to reduce overlap with general implementation skills.

Dimension	Reasoning	Score
Specificity	Lists multiple specific concrete actions — 'missing tests, dead code, type safety, lint issues, and coding conventions' — matching the top anchor.	3 / 3
Completeness	Explicitly answers both what (the concrete checks) and when ('Run after completing any implementation work'), satisfying the explicit-trigger requirement. Not below 3 because the when-clause is present and explicit.	3 / 3
Trigger Term Quality	Uses abstract category labels rather than natural phrases a user would utter; 'Run after completing any implementation work' is an auto-trigger cue, not user-uttered keywords. Not score 3 because common natural variations are missing.	2 / 3
Distinctiveness Conflict Risk	'Run after completing any implementation work' is a very broad trigger that overlaps with general implementation/review skills; the niche is somewhat specific but not clearly walled off.	2 / 3
	Total	10 / 12 Passed

Validation

87%

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 — 14 / 16 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning
referenced_paths_exist	Referenced path issues: 1 missing	Warning

	Total	14 / 16 Passed

Repository: vectorize-io/hindsight
Path: .claude/skills/code-review/SKILL.md
Commit: ed120a2

Reviewed: 7 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.