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

77%

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

Fix and improve this skill with Tessl

tessl review fix ./.claude/skills/code-review/SKILL.md

Quality

Content

71%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 and well-sequenced as a review checklist, but it is a long monolithic document that trades conciseness for completeness and makes no use of progressive disclosure.

Suggestions

Move the lengthy Code Standards sections (e.g. Bank/Tenant Isolation, Database Locking, API Layer rules) into reference files under references/ and keep SKILL.md as an overview pointing to them, improving progressive_disclosure and conciseness.

Tighten the verbose explanatory paragraphs and reduce bolded repetition between the Code Standards and Review Steps sections, which restate the same rules.

Deduplicate the guidance that appears both as a standard (e.g. step 7c restating Bank/Tenant Isolation) by cross-referencing the standard once instead of repeating it.

Dimension	Reasoning	Score
Conciseness	The ~370-line body is dense with genuine project-specific rules (bank isolation, advisory locks, BACKUP_TABLES) that earn their place, but long explanatory paragraphs, bolded repetition, and restated rationale between the Standards and Review Steps sections could be tightened.	3 / 5
Actionability	Concrete commands and paths abound — "git log --oneline main..HEAD", "./scripts/hooks/lint.sh", "git diff main...HEAD \| grep -in advisory" — with copy-paste-ready checks covering the common review cases.	5 / 5
Workflow Clarity	Review steps 1–13 are a clear, ordered sequence with explicit guardrails ("Do NOT fix them yourself — just report", severity tiers in step 13), though it is a reporting workflow without validate-fix-retry feedback loops.	4 / 5
Progressive Disclosure	No bundle files exist and the entire 370-line skill is a single monolithic SKILL.md; section headers give some structure but the detailed standards and per-rule explanations that could live in separate reference files are all inlined.	3 / 5
	Total	15 / 20 Passed

Description

83%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, third-person, and clearly answers both what it does and when to run it. It is a strong, well-scoped trigger description with only minor keyword-coverage gaps.

Dimension	Reasoning	Score
Specificity	"Checks for missing tests, dead code, type safety, lint issues, and coding conventions" lists multiple specific concrete review actions with comprehensive coverage of the review domain.	5 / 5
Completeness	It clearly states what ("Review changed code against project standards... Checks for...") and gives an explicit when ("Run after completing any implementation work"), but the when clause is a single trigger and could be more explicit about other triggering situations.	4 / 5
Trigger Term Quality	Natural terms like "missing tests", "dead code", "type safety", "lint issues", and "coding conventions" are present, but a few common synonyms a user might say (e.g. "code review", "PR review") are not explicitly surfaced.	4 / 5
Distinctiveness Conflict Risk	"Review changed code against project standards" carves a clear code-review niche with distinct triggers and minimal overlap risk against other skills.	5 / 5
	Total	18 / 20 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: d2e8fa7

Reviewed: ~12 hours 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.