high-level-code-review

reviewing a change for semantic correctness, simplicity, design consistency, and completeness

Quality

63%

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/high-level-code-review/SKILL.md

Quality

Content

67%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 body is a well-structured, actionable review methodology with concrete criteria, a severity taxonomy, and a copy-ready output template. Its main weakness is conciseness: the Inputs and Obtaining Context sections overlap, and a list-numbering bug slightly muddies the workflow sequence.

Suggestions

Merge the redundant "Inputs" and "Obtaining Context" sections (both cover goal, git range/diff, and concerns) into a single context-gathering step to remove the overlap that drives the conciseness score down.

Fix the duplicate "4." item in the "Obtaining Context" list so the numbered workflow sequence reads correctly.

Tighten the ALWAYS/NEVER lists by removing items that merely restate the Review Criteria checklists, keeping only the guardrails that add new information.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient and assumes Claude's competence, but the "Inputs" and "Obtaining Context" sections redundantly re-cover the goal and diff, and the ALWAYS/NEVER lists restate criteria, fitting the score-3 anchor of mostly efficient with some unnecessary content that could be tightened.	3 / 5
Actionability	Concrete per-category checklists, a defined severity taxonomy, and an exact output template with a worked example entry provide mostly executable guidance, matching the score-4 anchor of concrete guidance with minor gaps.	4 / 5
Workflow Clarity	The flow (Inputs → Obtaining Context → Review Criteria → Output Format → Completion) is clearly sequenced with ASK-FIRST/READ-FIRST guardrails acting as checkpoints, but there is no explicit validate-then-proceed feedback loop and a duplicate "4." numbering bug exists, matching the score-4 anchor of clear sequence with minor validation gaps.	4 / 5
Progressive Disclosure	With no bundle files present the skill is self-contained and well-organized into clear headed sections (Overview, Inputs, Criteria, Output, ALWAYS/NEVER, Completion), matching the score-4 anchor of good structure with content appropriately placed and only minor organization gaps.	4 / 5
	Total	15 / 20 Passed

Description

58%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 clearly states what the skill does and lists several concrete review dimensions, but it omits any "Use when…" trigger guidance and lacks the common natural term "code review," which limit completeness and trigger-term quality. It is otherwise specific and reasonably distinct from generic skills.

Suggestions

Add an explicit trigger clause, e.g. "Use when reviewing a PR or diff for semantic correctness rather than mechanical mistakes," so the when-to-use is stated and completeness can exceed 3.

Include the natural user phrase "code review" (and a synonym like "PR review") alongside the criteria terms to improve trigger-term coverage.

Consider mentioning "high-level" in the description itself (currently only in the name) to sharpen distinctiveness from low-level review skills.

Dimension	Reasoning	Score
Specificity	"reviewing a change for semantic correctness, simplicity, design consistency, and completeness" names the domain and lists several concrete review aspects, matching the score-4 anchor of multiple specific actions with minor coverage gaps.	4 / 5
Completeness	The description gives a clear "what" but no "Use when…" trigger clause; per the judging guideline a missing explicit trigger caps completeness at 3, matching the score-3 anchor of clear what with when missing.	3 / 5
Trigger Term Quality	"reviewing a change" is a natural phrase, but the criteria terms (semantic correctness, design consistency) lean technical and common variations like "code review" or "PR review" are absent, fitting the score-3 anchor of some relevant keywords missing common synonyms.	3 / 5
Distinctiveness Conflict Risk	Framing around semantic correctness and design consistency carves a distinct high-level-review niche with only minor overlap risk against other review skills, matching the score-4 anchor of mostly distinct with minor overlap.	4 / 5
	Total	14 / 20 Passed

Validation

100%

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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: stellar/stellar-core
Path: .claude/skills/high-level-code-review/SKILL.md
Commit: 457f20b

Reviewed: 2 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.