CtrlK
BlogDocsLog inGet started
Tessl Logo

adversarial-document-reviewer

Conditional document-review persona, selected when the document has >5 requirements or implementation units, makes significant architectural decisions, covers high-stakes domains, or proposes new abstractions. Challenges premises, surfaces unstated assumptions, and stress-tests decisions rather than evaluating document quality.

69

Quality

86%

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

86%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 tight, well-organized instruction-only persona skill that assumes Claude's intelligence and provides concrete probing directives with a clear calibration workflow. The only gaps are the absence of a specified output format and worked-example coverage of common cases.

Suggestions

Add a short 'Output format' section specifying how findings should be structured (e.g., finding → assumption/decision challenged → counterargument → confidence) so workflow clarity reaches the explicit-checklist level.

Include 1-2 brief worked examples of applying a technique to a sample decision (e.g., showing premise challenging on a sample goal statement) to lift actionability from probing questions to fully executable guidance.

DimensionReasoningScore

Conciseness

Lean and efficient throughout — it assumes Claude's competence ('You construct counterarguments, not checklists') with no padding about basic review concepts, and every section (techniques, confidence calibration, exclusions) earns its tokens.

5 / 5

Actionability

Concrete, executable directives are given ('For every "we chose X," ask "why not Y?"'; 'describe the specific condition being assumed and the consequence'), but guidance is framed as probing questions rather than step-by-step procedure with worked examples covering common cases.

4 / 5

Workflow Clarity

A clear sequence exists (depth calibration → select depth → run techniques → confidence calibration → suppress <0.50) with a gating checkpoint via the confidence threshold, but the output/findings format itself is not specified.

4 / 5

Progressive Disclosure

A single self-contained, well-sectioned file (~80 lines) with clearly headed sections and no nested references or inlined content that belongs elsewhere; no external bundle files exist, so the well-organized structure fully satisfies the simple-skill exception.

5 / 5

Total

18

/

20

Passed

Description

87%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, specific description that clearly answers both what the persona does and when it should be selected, with a well-delineated niche. It loses only minor points for trigger-term coverage that leans technical over the everyday phrasings a user might say.

DimensionReasoningScore

Specificity

Lists several concrete actions ('Challenges premises, surfaces unstated assumptions, and stress-tests decisions') plus a contrast phrase, but coverage is narrow — all variants of one meta-activity rather than comprehensive, so it sits below the 5 anchor.

4 / 5

Completeness

Both 'what' ('Challenges premises, surfaces unstated assumptions, and stress-tests decisions rather than evaluating document quality') and 'when' ('selected when the document has >5 requirements... makes significant architectural decisions...') are explicitly stated with concrete trigger phrases.

5 / 5

Trigger Term Quality

Real, fairly natural trigger phrases are present ('makes significant architectural decisions, covers high-stakes domains, or proposes new abstractions'), but common everyday synonyms a user would say ('red-team', 'stress-test my plan') are only partially covered, leaving a few natural terms missing.

4 / 5

Distinctiveness Conflict Risk

Occupies a sharply defined niche — an adversarial/falsifying reviewer explicitly scoped against six other reviewer personas — giving it distinct triggers and minimal conflict risk.

5 / 5

Total

18

/

20

Passed

Validation

81%

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

Validation13 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

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
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.