CtrlK
BlogDocsLog inGet started
Tessl Logo

avoid-ai-writing

Audit and rewrite content to remove 21 categories of AI writing patterns with a 43-entry replacement table

59

Quality

68%

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/avoid-ai-writing/SKILL.md

The canonical home for this skill is avoid-ai-writing in administrakt0r/AI-Agents-Safe-Coding-Skills

SKILL.md
Quality
Evals
Security

Quality

Content

71%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 body is well-structured and concise with a strong concrete example and a built-in second-pass feedback loop, but its actionability is limited because the headline 43-entry replacement table is never actually provided in the body or in any bundle file.

Suggestions

Provide the full 43-entry replacement table (or reference a real bundle file containing it) so the core actionable content is available rather than only illustrated by a few example mappings.

Restate the four-step workflow as explicit numbered steps (Audit -> Rewrite -> Summarize changes -> Second-pass audit) so the sequence is unambiguous rather than inferred from the example.

Break the 21-category enumeration into a short bulleted or grouped list so the dense single sentence is easier to scan.

DimensionReasoningScore

Conciseness

The body is lean with well-organized sections and no padding with concepts Claude already knows; the only minor over-explanation is the dense single-sentence enumeration of all 21 categories that could be tightened.

4 / 5

Actionability

The example gives a concrete prompt and a clear 4-section output structure with sample replacements, but the core 43-entry replacement table is only referenced by example entries rather than provided, leaving key details incomplete.

3 / 5

Workflow Clarity

The example output defines a clear sequence (issues found, rewritten version, what changed, second-pass audit) with a built-in validation loop via the second-pass audit, though steps are illustrated by example rather than as explicit numbered checkpoints.

4 / 5

Progressive Disclosure

As a simple single-purpose skill under 50 lines with clear section headers and no need for external references, the content is well-organized enough to earn the simple-skill exception for progressive disclosure.

5 / 5

Total

16

/

20

Passed

Description

66%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, naming concrete actions and the replacement-table mechanism, but it omits any 'when to use' trigger guidance, which caps completeness and slightly weakens trigger-term coverage and conflict resistance.

Suggestions

Append a 'Use when...' clause with natural triggers like 'remove AI-isms', 'clean up AI writing', or 'make this sound less like AI' to satisfy both completeness and trigger-term quality.

Include common user phrasings such as 'AI-isms' and 'humanize AI text' as synonyms to lift trigger_term_quality to 5.

DimensionReasoningScore

Specificity

Names the domain and concrete actions ('Audit and rewrite content to remove 21 categories of AI writing patterns') plus the '43-entry replacement table' mechanism, listing several specific actions with only minor coverage gaps.

4 / 5

Completeness

The description gives a clear 'what' but no 'when'/trigger clause, so per the guideline a missing 'Use when...' clause caps completeness at 3.

3 / 5

Trigger Term Quality

'remove AI writing patterns' is a natural phrase users would say, giving good keyword coverage, though common variations like 'AI-isms' or 'make this sound less like AI' are absent.

4 / 5

Distinctiveness Conflict Risk

The AI-writing-pattern niche with a 43-entry replacement table is mostly distinct with only minor overlap risk against general editing skills, but it lacks explicit trigger phrases that would fully minimize conflict.

4 / 5

Total

15

/

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.