Name: avoid-ai-writing
Rating: 72.8 (1 reviews)
Author: conorbronsdon

avoid-ai-writing

Audit and rewrite content to remove AI writing patterns ("AI-isms"). Use this skill when asked to "remove AI-isms," "clean up AI writing," "edit writing for AI patterns," "audit writing for AI tells," or "make this sound less like AI." Supports a detect-only mode, an edit-in-place mode for files, an optional voice profile (casual / professional / technical / warm / blunt), and an iterate-to-convergence pass.

Quality

91%

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

The canonical home for this skill is avoid-ai-writing in conorbronsdon/avoid-ai-writing

Quality

Content

82%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 mature, operationally precise skill body with executable commands, per-mode output formats, and validation steps for its in-place editing workflow. The main weaknesses are a few dense paragraphs that resist skimming and a top-level file that inlines content a stricter progressive-disclosure split would move to references.

Suggestions

Break the long edit-mode and automatic-marks-pass paragraphs into short labeled bullets so the safety boundaries (don't edit quotes/code/tables, confirm prose target first) are scannable.

Move the severity-tier catalog and the 'Never inject these' list into references/patterns.md, leaving SKILL.md a tighter operational overview that points to them — this would push progressive_disclosure toward the top anchor.

Make the edit-mode verify step an explicit validate→fix→revalidate loop (e.g., 'if patterns remain, re-edit and re-run the validator until clean') to match the anchor-5 workflow clarity example.

Dimension	Reasoning	Score
Conciseness	The body is information-dense and assumes Claude's competence (no explanations of what AI-ism detection libraries are), but several paragraphs are very long blocks — notably the edit-mode paragraph and the automatic-marks-pass paragraph — that could be tightened. It sits above anchor 3 (efficient with some unnecessary explanation) but stops short of anchor 5 (every token earns its place) because of those dense runs.	4 / 5
Actionability	Provides fully executable, copy-paste-ready commands backed by real bundled scripts — `node scripts/normalize-quotes.js <rewritten-prose> --reference <original> --write`, `node scripts/check-style.js <file> --config <path>`, `node detector/validate.js <original> <rewritten>` — plus concrete per-mode output-format sections. This matches anchor 5's 'specific examples cover the common cases.'	5 / 5
Workflow Clarity	Each mode has a clearly sequenced numbered workflow (audit → rewrite → diff → second-pass audit; read → edit → verify) with explicit validation checkpoints such as 're-read the file and confirm the flagged patterns are resolved' and a mechanical validator. It is below anchor 5 only because the validate→fix→revalidate feedback loop is stated more implicitly than the crisp numbered retry cycle in the anchor-5 example.	4 / 5
Progressive Disclosure	Structure is good: a clear reference-loading directive points to a real one-level-deep `references/patterns.md` (688 lines holding the catalog), and HTML markers (`<!-- patterns:catalog -->`, `<!-- patterns:profiles -->`) signal injected sections. It is above anchor 3 but below anchor 5 because at 224 lines the top-level file inlines sizable blocks (severity tiers, tone calibration, 'never inject these') that could arguably live in references.	4 / 5
	Total	17 / 20 Passed

Description

100%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, well-constructed description: third-person voice, concrete capabilities, explicit trigger guidance, and a distinct niche. It cleanly satisfies the 'what' and 'when' requirements with natural user phrasings.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions and features — 'Audit and rewrite content,' a detect-only mode, an edit-in-place mode, voice profiles, and an iterate-to-convergence pass — giving comprehensive coverage of the skill's capabilities. It exceeds anchor 4 by enumerating more than 'several' specific actions with no meaningful gap.	5 / 5
Completeness	Explicitly answers both what ('Audit and rewrite content to remove AI writing patterns') and when ('Use this skill when asked to...') with concrete trigger phrases, matching the anchor-5 example structure. It is not the 4 anchor because 'when' is specific and explicit rather than merely present.	5 / 5
Trigger Term Quality	Provides comprehensive natural-language triggers users would actually say — 'remove AI-isms,' 'clean up AI writing,' 'edit writing for AI patterns,' 'audit writing for AI tells,' 'make this sound less like AI' — covering synonyms and phrasings. File extensions don't apply to this non-file-centric skill, so the synonym coverage earns the top anchor.	5 / 5
Distinctiveness Conflict Risk	Occupies a clear niche (removing AI writing patterns / 'AI-isms') with distinct, specialized triggers that no general skill would naturally claim, minimizing conflict risk. The vocabulary ('AI-isms,' 'AI tells') is unique enough that it would not fire for unrelated skills.	5 / 5
	Total	20 / 20 Passed

Validation

81%

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 — 13 / 16 Passed

Validation for skill structure

Criteria	Description	Result
metadata_version	'metadata.version' is missing	Warning
metadata_field	'metadata' should map string keys to string values	Warning
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	13 / 16 Passed

Repository: conorbronsdon/avoid-ai-writing
Path: SKILL.md
Commit: 0c2a936

Reviewed: 3 days 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.