review

Code review with semantic diffs, expert routing, and auto-TaskCreate. Triggers on: code review, review changes, check code, review PR, security audit.

1.34x

Quality

73%

Does it follow best practices?

Impact

85%

1.34x

Average score across 3 eval scenarios

Securityby

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./data/skills-md/0xdarkmatter/claude-mods/review/SKILL.md

Quality

Content

72%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.

A highly actionable, well-structured code-review skill body with concrete commands and a clear sequenced workflow. Its main gaps are the missing validation feedback loop for the destructive --fix/batch-task steps and a referenced file that is not actually bundled.

Suggestions

Add an explicit validate→fix→retry checkpoint to the --fix flow (e.g., re-run review after applying fixes and only mark the task completed when no CRITICAL issues remain) to lift workflow clarity above 3.

Either create the referenced references/framework-checks.md file or remove the 'Reference Files' section so navigation does not point to a missing bundle file.

Move the full example review markdown template and the large routing/severity tables into a separate reference file, keeping SKILL.md as a lean overview with one-level-deep pointers.

Dimension	Reasoning	Score
Conciseness	The body is mostly lean tables, command blocks, and an architecture diagram that assume Claude's competence with no concept padding; minor redundancy (the CLI integration table re-lists the delta/difft fallbacks already shown inline) keeps it just below 5.	4 / 5
Actionability	Provides copy-paste-ready commands (git diff --cached, gh pr diff, the categorization case script), concrete TaskCreate/TaskUpdate blocks, severity tables, and a full example review markdown, covering the common cases executably.	5 / 5
Workflow Clarity	A clear six-step architecture diagram with per-step command sections gives a strong sequence, but the --fix auto-apply (destructive Edit) and batch auto-TaskCreate steps lack a validate→fix→retry feedback checkpoint, which per the rubric caps workflow clarity at 3.	3 / 5
Progressive Disclosure	Section structure is reasonable and the single 'framework-checks.md' reference is clearly signaled and one level deep, but that referenced file does not exist in any bundle directory, and sizable inline content (the full example review block, multiple large tables) could be split out, leaving it between 3 and 4.	3 / 5
	Total	15 / 20 Passed

Description

75%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 concise, third-person description that clearly names concrete capabilities and provides explicit trigger terms. It would reach the top level by replacing jargon ('auto-TaskCreate') with plain language and using a natural 'Use when...' clause.

Suggestions

Rewrite 'auto-TaskCreate' as plain language (e.g., 'automatically creates tracking tasks for critical issues') so the capability is clear without internal jargon.

Convert the comma-separated 'Triggers on:' list into a natural 'Use when the user asks to review code, check changes, review a PR, or run a security audit.' clause.

Add a common synonym like 'review my changes' or 'look over this diff' to broaden natural trigger coverage.

Dimension	Reasoning	Score
Specificity	Names the domain plus three concrete capabilities ('semantic diffs', 'expert routing', 'auto-TaskCreate'); the actions are specific but slightly jargon-laden rather than fully comprehensive, so it sits above the 3-anchor but below 5.	4 / 5
Completeness	It states both what the skill does and an explicit trigger list ('Triggers on: ...'), but the 'what' leans on jargon ('auto-TaskCreate') and the 'when' is a flat comma list rather than the clearest 'Use when...' phrasing, keeping it just below 5.	4 / 5
Trigger Term Quality	'Triggers on: code review, review changes, check code, review PR, security audit' provides good coverage of natural phrases users would say, though a few common variations are missing.	4 / 5
Distinctiveness Conflict Risk	The code-review niche with triggers like 'review PR' and 'security audit' is mostly distinct with only minor overlap risk against generic lint/test skills.	4 / 5
	Total	16 / 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: NeverSight/skills_feed
Path: data/skills-md/0xdarkmatter/claude-mods/review/SKILL.md
Commit: 2f57aec

Reviewed: about 22 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.