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

94%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

—

The risk profile of this skill

Quality

Content

88%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-structured, highly actionable body with clear sequenced workflows and explicit validation/feedback loops for its file-editing operations. Its main weakness is progressive disclosure: three referenced paths (examples/README.md, examples/technical.json, detector/validate.js) do not exist in the bundle.

Suggestions

Add the missing examples/ directory (README.md and the example config files such as technical.json) referenced by the --style section, or remove those references.

Ship detector/validate.js (referenced as the optional preservation validator) or drop the command block pointing to it.

Tighten the research-citation framing paragraph and the "Why it belongs here rather than in the pattern catalog" justification to reduce length without losing the provenance rule.

Dimension	Reasoning	Score
Conciseness	The body is mostly dense, domain-specific instruction rather than padding about concepts Claude already knows, but the research-citation framing paragraph and lengthy justifications (e.g., "Why it belongs here rather than in the pattern catalog") could be trimmed.	4 / 5
Actionability	Provides copy-paste-ready commands (node scripts/normalize-quotes.js …, node scripts/check-style.js …) plus concrete mode definitions, exemption rules, and a specified four-section output format — fully actionable guidance for both code and instruction paths.	5 / 5
Workflow Clarity	Each mode has an explicit numbered sequence with validation checkpoints and feedback loops (audit→rewrite→second-pass audit; read→edit→re-read and confirm resolved), and the optional mechanical validator plus iterate-to-convergence cap add error recovery.	5 / 5
Progressive Disclosure	Good structure with the catalog offloaded to references/patterns.md and scripts referenced by path, but examples/README.md, examples/technical.json, and detector/validate.js are referenced in the body yet absent from the bundle, leaving dangling navigation links.	4 / 5
	Total	18 / 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, third-person description that states concrete capabilities, gives comprehensive natural trigger phrases, and cleanly answers both what the skill does and when to use it. It is specific and distinct with negligible overlap risk.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete capabilities — "Audit and rewrite content to remove AI writing patterns," plus detect-only mode, edit-in-place mode, voice profiles, and an iterate-to-convergence pass — giving comprehensive coverage of the domain.	5 / 5
Completeness	Explicitly answers what ("Audit and rewrite content to remove AI writing patterns") and when ("Use this skill when asked to…") with concrete trigger phrases, satisfying both halves.	5 / 5
Trigger Term Quality	Quotes five natural user phrases ("remove AI-isms," "clean up AI writing," "edit writing for AI patterns," "audit writing for AI tells," "make this sound less like AI") with synonym variation users would actually say.	5 / 5
Distinctiveness Conflict Risk	Occupies a clear niche (AI-writing-pattern removal) with distinctive triggers unlikely to fire for unrelated skills, so conflict risk is minimal.	5 / 5
	Total	20 / 20 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

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

	Total	15 / 16 Passed

Repository: conorbronsdon/avoid-ai-writing
Path: skills/avoid-ai-writing/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.