CtrlK
BlogDocsLog inGet started
Tessl Logo

adversarial-reviewer

Adversarial code review that assumes bugs exist and hunts for them. Use when asked to review code, find bugs, audit for correctness, stress-test a PR, or when someone says "tear this apart" or "what's wrong with this". Give no benefit of the doubt — every line is guilty until proven innocent.

80

Quality

100%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Passed

No findings from the security scan

SKILL.md
Quality
Evals
Security

Quality

Content

100%Weight 40%Scale 1-3

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

A tight, well-structured instruction skill: concrete checklist, copy-paste output template, clear severity rubric, and a sequenced process with a verification stop condition. It assumes Claude's competence and avoids padding.

DimensionReasoningScore

Conciseness

Lean checklist bullets with no explanations of concepts Claude already knows and no padding; every section earns its place; not 2 because there is no unnecessary explanation to tighten.

3 / 3

Actionability

Provides a copy-paste output-format template, concrete per-category checklist items, and a severity guide — fully actionable instruction-only guidance; not 2 because there is no pseudocode or vague direction.

3 / 3

Workflow Clarity

A numbered 5-step Process is clearly sequenced with an explicit verification/stop checkpoint ('If you found nothing... stop. Don't manufacture issues'); not a destructive/batch op so no cap applies; not 2 because the checkpoint is explicit, not implicit.

3 / 3

Progressive Disclosure

Single-purpose skill with no bundle files, well-organized into clear navigable sections and no nested references; per the simple-skills note this scores 3; not 2 because content is appropriately inline with nothing that should be split out.

3 / 3

Total

12

/

12

Passed

Description

100%Weight 40%Scale 1-3

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, specific description with explicit 'Use when' triggers and natural phrasing a user would actually say. It clearly distinguishes the skill's adversarial purpose and avoids vague fluff.

DimensionReasoningScore

Specificity

Names multiple concrete actions — 'adversarial code review', 'find bugs', 'audit for correctness', 'stress-test a PR' — matching the anchor for listing multiple specific concrete actions; not 2 because it is comprehensive rather than domain-plus-some.

3 / 3

Completeness

Explicitly answers both what ('hunts for them', 'assumes bugs exist') and when via an explicit 'Use when...' clause with concrete triggers; not 2 because the trigger guidance is explicit rather than implied.

3 / 3

Trigger Term Quality

Covers natural terms users would actually say — 'review code', 'find bugs', 'audit for correctness', 'stress-test a PR', 'tear this apart', 'what's wrong with this'; not 2 because common variations are well covered.

3 / 3

Distinctiveness Conflict Risk

Clear adversarial niche with distinct triggers ('tear this apart', 'stress-test a PR') unlikely to fire for other skills; written in third person, so no voice penalty; not 2 because it does not meaningfully overlap with sibling skills.

3 / 3

Total

12

/

12

Passed

Validation

100%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
emdash-cms/emdash
Reviewed

Table of Contents

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.