CtrlK
BlogDocsLog inGet started
Tessl Logo

bdistill-behavioral-xray

X-ray any AI model's behavioral patterns — refusal boundaries, hallucination tendencies, reasoning style, formatting defaults. No API key needed.

62

Quality

74%

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

Fix and improve this skill with Tessl

tessl review fix ./plugins/AI-Agents-Safe-Coding-Skills/skills/bdistill-behavioral-xray/SKILL.md

The canonical home for this skill is bdistill-behavioral-xray in administrakt0r/AI-Agents-Safe-Coding-Skills

SKILL.md
Quality
Evals
Security

Quality

Content

78%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 content is well-structured, concise, and actionable, providing concrete install and invocation commands while cleanly organizing overview, dimensions, output, and practices; it is a strong, self-contained skill body.

DimensionReasoningScore

Conciseness

The body is lean and does not explain concepts Claude already knows (no primer on AI models, MCP, or HTML reports), with only minor redundancy where use-cases recur across the Overview, When to Use, and Best Practices sections.

4 / 5

Actionability

Provides copy-paste-ready commands ("pip install bdistill", "claude mcp add bdistill -- bdistill-mcp", "/xray", "/xray --dimensions refusal", "/xray-report") covering common cases, with minor gaps such as where the HTML report is written or how to open it.

4 / 5

Workflow Clarity

The install → probe → report sequence is clear and unambiguous ("/xray-report # Generate report from completed probe"), and no validation checkpoints are required since the operation is non-destructive; it stops short of 5 only because the probe-to-report handoff could be stated more explicitly.

4 / 5

Progressive Disclosure

A single self-contained, well-organized file with clear section headers (Overview, When to Use, How It Works, Probe Dimensions, Output, Best Practices) that appropriately delegates the 30-question detail to the tool rather than inlining it, with easy navigation and no need for external references.

5 / 5

Total

17

/

20

Passed

Description

70%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 is specific and distinctive, clearly conveying what the skill examines across AI behavioral dimensions, but it lacks an explicit "Use when..." trigger clause, which caps its completeness and limits its discoverability.

Suggestions

Add an explicit 'Use when...' clause, e.g. 'Use when you need to profile an AI model's behavior, compare models for a task, debug refusals or hallucinations, or audit model behavior for compliance.'

Replace or supplement the metaphorical verb 'X-ray' with a concrete action verb like 'Probe' or 'Profile' so the capability reads as a literal action.

Add a few common natural trigger terms users would say (e.g. 'red team', 'model evaluation', 'test my model', 'compare models') to broaden keyword coverage.

DimensionReasoningScore

Specificity

Names the domain and four concrete behavioral targets — "refusal boundaries, hallucination tendencies, reasoning style, formatting defaults" — but relies on a single metaphorical action verb ("X-ray") rather than multiple distinct actions, so it sits just below the comprehensive multi-action anchor.

4 / 5

Completeness

The "what" is clear (probe behavioral patterns across named dimensions) but there is no "Use when..." clause or equivalent explicit trigger guidance, which caps completeness at 3 per the rubric guideline.

3 / 5

Trigger Term Quality

Includes reasonably natural terms a user debugging model behavior would say ("refusal boundaries", "hallucination tendencies", "reasoning style", "formatting defaults"), but omits common variations like "red team", "model evaluation", "test my model", or "compare models".

4 / 5

Distinctiveness Conflict Risk

The behavioral-X-ray framing plus the specific probe dimensions carve a clear niche (AI behavioral profiling) with distinct triggers and minimal overlap with unrelated skills.

5 / 5

Total

16

/

20

Passed

Validation

93%

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

Validation15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

Total

15

/

16

Passed

Repository
administrakt0r/AI-Agents-Safe-Coding-Skills
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.