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

75%

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.

An exceptionally actionable, well-sequenced review skill grounded in concrete project-specific rules and commands. Its main weaknesses are conciseness (substantial rule duplication between Standards and Review Steps) and progressive disclosure (a large monolithic file with no reference-file split).

Suggestions

De-duplicate rules between the 'Code Standards' and 'Review Steps' sections — have each Review Step link to the canonical standard ('see Bank/Tenant Isolation above') instead of restating the rule in full.

Split the long, stable standards (e.g. HTTP Middleware, Concurrency, Outbound HTTP, Bank/Tenant Isolation) into reference files under references/ and point to them from SKILL.md, reducing the inline body to the review workflow plus pointers.

Tighten the most discursive paragraphs (e.g. the BaseHTTPMiddleware and Outbound HTTP rationale blocks) to the rule + the one concrete failure mode + the issue reference, trimming explanatory prose.

Dimension	Reasoning	Score
Conciseness	Mostly efficient — no basic-concept padding and all content is non-obvious project-specific knowledge — but the ~545-line body restates many rules twice (e.g. bank scoping in 'Bank/Tenant Isolation' and again in step 7c; pagination in 'API Layer' and step 7d; BaseHTTPMiddleware in 'HTTP Middleware' and step 11e), so it could be tightened.	3 / 5
Actionability	Copy-paste-ready grep commands (`git diff main...HEAD -- '*.py' \| grep -nE ...`), concrete file paths, explicit flag-or-pass criteria per step, and complete BAD/GOOD code examples fully cover the common review cases, matching the score-5 anchor.	5 / 5
Workflow Clarity	A clear numbered 1–13 sequence with per-step checkpoints (run lint, check tests, classify findings) and a severity-tiered report terminus, but it is a report-only workflow with no validate→fix→retry feedback loop, so it sits just below the score-5 anchor.	4 / 5
Progressive Disclosure	Well-organized section headers, but the skill is a single monolithic ~545-line file with no bundle/reference files and no one-level-deep references, so content that would benefit from being split into reference docs is inlined.	3 / 5
	Total	15 / 20 Passed

Description

80%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.

A specific, third-person description that names concrete review actions and includes explicit when-to-run guidance. It is strong but not maximal because the trigger phrasing is generic and lacks the natural synonyms a user would utter.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete review actions — 'missing tests, dead code, type safety, lint issues, and coding conventions' — giving comprehensive coverage of what the skill checks, matching the score-5 anchor.	5 / 5
Completeness	Has a clear 'what' ('Review changed code... Checks for...') and an explicit 'when' ('Run after completing any implementation work'), but the trigger is generic rather than concrete user-facing trigger phrases, fitting the score-4 anchor.	4 / 5
Trigger Term Quality	Good natural-keyword coverage ('code review', 'missing tests', 'dead code', 'type safety', 'lint'), but misses common variations a user might say ('review my diff', 'check my PR', 'review my code'), so it sits above the midpoint but not at comprehensive.	4 / 5
Distinctiveness Conflict Risk	The 'changed code against project standards' niche with specific check categories is mostly distinct from generic review skills, with only minor overlap risk, matching the score-4 anchor.	4 / 5
	Total	17 / 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 — 13 / 16 Passed

Validation for skill structure

Criteria	Description	Result
skill_md_line_count	SKILL.md is long (546 lines); consider splitting into references/ and linking	Warning
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning
referenced_paths_exist	Referenced path issues: 2 missing	Warning

	Total	13 / 16 Passed

Repository: vectorize-io/hindsight
Path: .claude/skills/code-review/SKILL.md
Commit: 9c7f6c6

Reviewed: 1 day 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.