CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

hungarian-humanizer

Detect and remove AI-generated markers from Hungarian text, making it sound like a native Hungarian speaker wrote it. Use when asked to "humanize", "naturalize", or "remove AI feel" from Hungarian text, or when editing .md/.txt files containing Hungarian content. Identifies 26 patterns (12 Hungarian-specific + 14 universal) and 4 style markers.

Quality

89%

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

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.

A well-organized, domain-rich instruction skill that balances inline guidance with a single clearly-signaled reference file. Its main limitation is that validation feedback is a soft 'ask when uncertain' rather than an explicit re-check loop.

Suggestions

Add an explicit verify step to the workflow (e.g. re-read the rewritten text to confirm no AI markers remain and no content was altered) to approach a full validate→fix→retry loop.

Tighten the magyar_voice section's illustrative contrast ('lélektelen vs. élő') into a one-line example to recover a few tokens.

Consider a short inline summary table of all 26 pattern names so the overview is navigable without opening references/patterns.md for pattern lookup.

DimensionReasoningScore

Conciseness

Mostly efficient: the magyar_voice and example sections carry genuine Hungarian-specific expertise Claude would not assume, so they earn their tokens; a few framing passages (e.g. the lélektelen vs. élő contrast) could be tightened without loss, keeping it just below the 5-anchor.

4 / 5

Actionability

Concrete before/after ('Előtte/Utána') pairs for each pattern plus a numbered adaptive workflow give executable guidance; as an instruction-only skill it has no code, but the guidance is specific and covers common cases, sitting between the 4 and 5 anchors.

4 / 5

Workflow Clarity

A clear five-step process and a length-based adaptive workflow with an explicit uncertainty checkpoint ('Kérdezz rá a bizonytalan esetekre') and a 'no unnecessary edits if already natural' guard; not quite the full validate→fix→retry feedback loop of the 5-anchor.

4 / 5

Progressive Disclosure

SKILL.md is a well-structured overview with 7 canonical examples inline while the full 26-pattern catalogue is offloaded to a clearly signaled, one-level-deep reference (references/patterns.md, verified present), matching the 5-anchor.

5 / 5

Total

17

/

20

Passed

Description

95%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, third-person description that concretely states both capability and trigger conditions with natural synonyms and file extensions. Minor specificity gap only in the breadth of distinct action verbs.

DimensionReasoningScore

Specificity

Names the domain (Hungarian text) and several concrete actions — 'Detect and remove AI-generated markers', 'making it sound like a native Hungarian speaker wrote it', 'Identifies 26 patterns … and 4 style markers' — but the action set is narrow (detect/remove/identify) rather than a broad comprehensive list, so it sits just below the 5-anchor.

4 / 5

Completeness

Explicitly answers both 'what' ('Detect and remove AI-generated markers … Identifies 26 patterns') and 'when' with concrete trigger phrases ('Use when asked to humanize, naturalize, or remove AI feel … or when editing .md/.txt files'), matching the 5-anchor.

5 / 5

Trigger Term Quality

Comprehensive natural terms including synonyms ('humanize', 'naturalize', 'remove AI feel') plus file extensions (.md/.txt) and the domain phrase 'Hungarian text', matching the 5-anchor's coverage of synonyms and extensions.

5 / 5

Distinctiveness Conflict Risk

Occupies a clear niche (Hungarian-language AI-marker removal) with distinct, language-specific triggers and a quantified pattern inventory, giving minimal overlap with other skills.

5 / 5

Total

19

/

20

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.

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository

bencium/bencium-marketplace

Path

hungarian-humanizer/skills/hungarian-humanizer/SKILL.md

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.