avoid-ai-writing

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

Quality

46%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./skills/avoid-ai-writing/SKILL.md

Quality

Content

38%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 skill provides a reasonable overview of AI writing pattern detection and shows a good example of input/output, but critically lacks the actual replacement table and detection rules that would make it actionable. The workflow is implied through the example output rather than explicitly defined, and the promised detailed content (43 entries, 21 categories) is neither inline nor referenced in any supporting file.

Suggestions

Include the actual 43-entry replacement table either inline or in a referenced bundle file (e.g., REPLACEMENTS.md) — this is the core actionable data the skill promises but doesn't deliver.

Convert the implied workflow from the example into explicit numbered steps: 1) Scan for patterns, 2) Quote each issue, 3) Rewrite, 4) Summarize changes, 5) Second-pass audit, 6) If issues remain, repeat steps 3-5.

Provide the 21 pattern categories as a structured checklist or reference file rather than a dense paragraph, so Claude can systematically check each one.

Add concrete detection heuristics (e.g., regex patterns for em dashes, specific sentence structures to flag) rather than just naming the categories.

Dimension	Reasoning	Score
Conciseness	The skill includes some unnecessary explanation (e.g., listing all 21 categories in a dense paragraph, explaining when to use it in ways Claude could infer). The example is useful but the 'What It Detects' section is verbose — a concise list or table reference would be more token-efficient.	3 / 5
Actionability	The skill describes what it detects and shows an example input/output, but never provides the actual 43-entry replacement table, the specific detection rules, or concrete instructions for how to perform the audit. Claude is told categories exist but not given the actionable data to execute them.	2 / 5
Workflow Clarity	The four-section output format (issues found, rewrite, what changed, second-pass audit) implies a clear sequence with a validation step (second-pass audit). However, the workflow is described only in the example output rather than as explicit procedural steps, and there's no guidance on what to do if the second-pass audit finds surviving issues (no feedback loop).	3 / 5
Progressive Disclosure	The skill references a '43-entry word/phrase replacement table' and '21 pattern categories' but neither is provided inline nor in any bundle file. There are no references to external files containing this critical data. The skill promises detailed content that doesn't exist anywhere accessible.	2 / 5
	Total	10 / 20 Passed

Description

53%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 identifies a clear niche (removing AI writing patterns) and includes some specificity with the numbered categories and replacement table, but it lacks natural trigger terms users would actually say and has no explicit 'Use when...' clause. The numeric details (21 categories, 43 entries) are implementation details rather than useful selection criteria for Claude.

Suggestions

Add a 'Use when...' clause with natural trigger phrases like 'humanize text,' 'make writing sound less AI-generated,' 'remove robotic tone,' or 'sound more natural.'

Replace implementation details (21 categories, 43-entry table) with examples of the AI patterns addressed, such as 'removes filler phrases, hedging language, repetitive transitions, and overused AI vocabulary.'

Include synonyms and natural user language like 'AI-sounding text,' 'ChatGPT-style writing,' 'robotic tone,' or 'make it sound human.'

Dimension	Reasoning	Score
Specificity	Names the domain (AI writing pattern removal) and mentions concrete elements (21 categories, 43-entry replacement table), but doesn't describe what those categories or replacements actually are. The actions are limited to 'audit and rewrite' without elaborating on specific capabilities.	3 / 5
Completeness	The 'what' is reasonably clear (audit and rewrite content to remove AI patterns using a replacement table), but there is no explicit 'when' clause. There's no 'Use when...' guidance telling Claude when to select this skill, which caps this dimension at 3 per the rubric.	3 / 5
Trigger Term Quality	Includes some relevant terms like 'AI writing patterns,' 'audit,' and 'rewrite,' but misses natural user phrases like 'make it sound more human,' 'remove AI tone,' 'humanize text,' 'sound less robotic,' or 'AI-generated content.' Users rarely say '21 categories' or '43-entry replacement table.'	3 / 5
Distinctiveness Conflict Risk	The focus on removing AI writing patterns is a fairly distinct niche that wouldn't easily overlap with general writing or editing skills. The specific mention of 21 categories and a 43-entry replacement table adds uniqueness, though it could still overlap with general 'improve writing style' skills.	4 / 5
	Total	13 / 20 Passed

Validation

90%

Warnings & errors only

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

Validation — 10 / 11 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	10 / 11 Passed

Repository: administrakt0r/AI-Agents-Safe-Coding-Skills
Path: skills/avoid-ai-writing/SKILL.md
Commit: debb2ec

Reviewed: 14 hours ago

Table of Contents

Discovery Implementation Validation

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.