code-simplicity-reviewer

Final review pass to ensure code is as simple and minimal as possible. Use after implementation is complete to identify YAGNI violations and simplification opportunities.

Quality

65%

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 ./.agents/skills/code-simplicity-reviewer/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 agent prompt with a concrete review process and a strong output template, all appropriately self-contained in one file. Its main weaknesses are moderate redundancy — overlapping principle items and a motivational closing section Claude does not need — and the absence of a worked example or re-review loop.

Suggestions

Cut the closing motivational paragraph and merge overlapping checklist items (e.g., fold 'just in case' code into the YAGNI section) to tighten token usage.

Add one brief worked example of a filled-in output template (a real finding with file:lines, reason, and LOC estimate) to make the guidance fully copy-paste ready.

Include a short re-review step in the process (re-check that proposed simplifications preserve functionality) to close the feedback loop and strengthen workflow clarity.

Dimension	Reasoning	Score
Conciseness	The checklist and output template are tight, but the motivational closer ('Perfect is the enemy of good... Every line of code is a liability') repeats principles Claude already knows, and items 1-6 overlap (e.g., "Remove 'just in case' code" restates the YAGNI section). Mostly efficient with several removable passages, fitting the 3 anchor rather than the 'only minor trims' level above.	3 / 5
Actionability	As an instruction-only skill it gives concrete, specific guidance: exact checklist items ('Use early returns to reduce indentation', 'Remove commented-out code'), a 5-step review process, and a copy-ready markdown output template with LOC-reduction fields. Minor gaps (no worked example of a filled-in finding) keep it below the fully copy-paste-ready 5.	4 / 5
Workflow Clarity	'Your review process: 1-5' is a clear sequence ending in a prioritized list and LOC estimate, and the output template enforces structure. This is a read-only review so the destructive/batch validation cap does not apply, but there is no re-review or verification loop after simplifications are proposed, fitting 4 rather than 5.	4 / 5
Progressive Disclosure	No bundle files exist and the ~95-line body is appropriately self-contained with clearly labeled sections (examples, principles, process, output format) and no nested references. Structure is good with only minor organizational gaps — the examples block and closing philosophy could be trimmed or merged — so it sits at 4 rather than the cleanly split, easy-navigation 5.	4 / 5
	Total	15 / 20 Passed

Description

62%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 answers both what and when in third person with a distinctive YAGNI/simplicity niche, but its action list is thin and its trigger vocabulary misses the natural phrases users would say. Adding concrete review activities and common trigger phrasings would lift it.

Suggestions

List the concrete review activities in the description itself (e.g., 'flags unused abstractions, duplicate logic, commented-out code, and premature generalizations') so specificity reaches comprehensive coverage.

Add natural trigger phrases users actually say: 'Use when the user says the code is too complex, asks to simplify or clean up an implementation, or wants a final simplicity pass before finishing.'

Differentiate more sharply from general code review by stating what this pass does NOT cover (e.g., correctness or style), reducing conflict risk with sibling review skills.

Dimension	Reasoning	Score
Specificity	Names the domain (code simplicity) and two concrete actions — 'identify YAGNI violations and simplification opportunities' — but the fuller set of review activities (redundancy removal, challenging abstractions, readability) appears only in the body, not the description. It matches the 'names domain and 1-2 concrete actions' anchor, not the 'several specific actions' level above.	3 / 5
Completeness	Explicitly answers both what ('Final review pass to ensure code is as simple and minimal as possible... identify YAGNI violations and simplification opportunities') and when ('Use after implementation is complete'). The 'when' is a lifecycle stage rather than concrete user triggers, matching the 4 anchor instead of the fully trigger-phrased 5.	4 / 5
Trigger Term Quality	Natural terms like 'simple', 'minimal', 'YAGNI', and 'simplification' are present, but common user phrasings such as 'simplify this', 'clean up', 'refactor', 'over-engineered', or 'too complex' are missing. Fits the 'some relevant keywords but missing common variations' anchor rather than the 'good coverage, a few missing' level.	3 / 5
Distinctiveness Conflict Risk	'YAGNI violations' and 'final review pass after implementation' carve a distinct niche away from general code-review and refactoring skills, but terms like 'simple' and 'review' overlap with closely related skills. Mostly distinct with minor overlap risk, not a fully clean niche.	4 / 5
	Total	14 / 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
metadata_version	'metadata.version' is missing	Warning
metadata_field	'metadata' should map string keys to string values	Warning
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	13 / 16 Passed

Repository: udecode/plate
Path: .agents/skills/code-simplicity-reviewer/SKILL.md
Commit: babb3c2

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.