adversarial-reviewer

Adversarial code review that breaks the self-review monoculture. Use when you want a genuinely critical review of recent changes, before merging a PR, or when you suspect Claude is being too agreeable about code quality. Forces perspective shifts through hostile reviewer personas that catch blind spots the author's mental model shares with the reviewer.

Quality

80%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

—

The risk profile of this skill

Fix and improve this skill with Tessl

tessl review fix ./engineering-team/skills/adversarial-reviewer/SKILL.md

Quality

Content

81%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 well-structured, highly actionable prompt-only skill with a clear sequenced workflow and concrete output template. Its main weakness is redundancy across the introductory sections, which inflates length without adding value.

Suggestions

Remove the duplicated Usage block (it appears identically under both 'Usage' and 'Quick Start') and consolidate into one entry point.

Merge 'Problem This Solves' and 'The Self-Review Trap' into a single section to eliminate the overlapping explanation of the self-review monoculture.

Trim the Features list so it does not simply restate the Description; either expand each feature with a distinct concrete detail or drop the redundant restatement.

Dimension	Reasoning	Score
Conciseness	Content is actionable throughout with no basic-concept padding, but redundancy is noticeable: the Usage block is duplicated verbatim in Quick Start, Features restates the Description, and 'Problem This Solves' overlaps with 'The Self-Review Trap'.	3 / 5
Actionability	Concrete git commands, specific invocation flags, numbered persona review steps with exact questions, and a copy-paste markdown output template make the guidance fully executable.	5 / 5
Workflow Clarity	A clear four-step sequence includes a stop-condition ('Nothing to review'), a per-persona enforcement feedback loop ('must find one, go back and look again'), and explicit dedup/promotion rules.	5 / 5
Progressive Disclosure	A single self-contained file with a table of contents and clear headers offers easy navigation, but duplicated and overlapping intro sections are a minor organization gap.	4 / 5
	Total	17 / 20 Passed

Description

78%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 strong description that clearly states both capability and trigger conditions with natural language. It is slightly abstract on specific actions and has minor overlap with general code-review skills, but is well above average.

Dimension	Reasoning	Score
Specificity	Names the domain ('adversarial code review') and one concrete mechanism ('perspective shifts through hostile reviewer personas') but describes actions abstractly rather than listing multiple concrete capabilities.	3 / 5
Completeness	Explicitly answers both what (adversarial review via hostile personas catching blind spots) and when, with concrete trigger phrases in a clear 'Use when...' clause.	5 / 5
Trigger Term Quality	Natural phrases like 'critical review of recent changes', 'before merging a PR', and 'Claude is being too agreeable' give good keyword coverage, though a few common synonyms are missing.	4 / 5
Distinctiveness Conflict Risk	The adversarial/persona framing is a distinct niche, but the broad 'code review' trigger carries minor overlap risk with general code-reviewer skills.	4 / 5
	Total	16 / 20 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: alirezarezvani/claude-skills
Path: engineering-team/skills/adversarial-reviewer/SKILL.md
Commit: 19392f7

Reviewed: 12 minutes 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.