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-claude/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

67%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 concise and presents a clear workflow with a built-in second-pass validation step. Its primary weakness is actionability: the skill repeatedly advertises a 43-entry replacement table that is never actually supplied, so Claude cannot perform the full replacement without improvising it.

Suggestions

Provide the actual 43-entry replacement table — inline if small, or in a references/ file linked from the body — so Claude can execute the replacements rather than invent them.

Reformat the 21-category enumeration in 'What It Detects' as a structured list so the categories are scannable instead of buried in one run-on sentence.

DimensionReasoningScore

Conciseness

The body is lean and does not over-explain concepts Claude already knows, with the bulk being a concrete illustrative example; the only minor over-explanation is the dense run-on enumeration of 21 categories that could be tightened.

4 / 5

Actionability

A concrete example and a clearly specified four-section output format give real guidance, but the promised '43-entry replacement table' is referenced and never actually provided — in the body or any bundle file — leaving the core mechanism incomplete.

3 / 5

Workflow Clarity

The audit → rewrite → 'what changed' → second-pass audit sequence is clear and includes an explicit feedback loop (re-reading the rewrite to catch surviving tells), with only minor validation gaps keeping it below a 5.

4 / 5

Progressive Disclosure

Sections (When to Use, What It Detects, Example, Limitations) are well organized for a short single-purpose skill, but the 21-category list is a run-on sentence and the promised replacement table has no dedicated home, leaving minor organization gaps.

4 / 5

Total

15

/

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, naming concrete actions and a clear niche for AI-writing detection. Its main weakness is the absence of an explicit 'when to use' trigger clause, which leaves completeness at the rubric cap of 3.

Suggestions

Add an explicit 'Use when...' clause naming natural trigger phrases, e.g. 'Use when asked to remove AI-isms, clean up AI writing, or make text sound less machine-generated.'

Include common synonyms users say — 'AI-isms', 'machine-generated', 'AI-generated' — to broaden trigger-term coverage toward comprehensive.

DimensionReasoningScore

Specificity

Names the domain (AI writing patterns) and multiple concrete actions — 'Audit and rewrite content to remove 21 categories' plus the '43-entry replacement table' mechanism — but stops just short of the comprehensive multi-action enumeration of a 5.

4 / 5

Completeness

The 'what' is clear (audit and rewrite to remove AI writing patterns), but there is no explicit 'Use when...' clause or equivalent trigger guidance, which caps completeness at 3 per the rubric.

3 / 5

Trigger Term Quality

Includes natural terms a user would say ('AI writing patterns', 'AI writing') but omits common variations like 'AI-isms', 'machine-generated', or 'make this sound less like AI', so it falls short of comprehensive.

4 / 5

Distinctiveness Conflict Risk

Targets a clear niche (removing AI writing patterns) with distinct triggers and minimal overlap with other skills, matching the anchor for a clear niche.

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.