ai-writing-detector

Use when the user asks to detect, scan, audit, score, or flag AI-writing patterns without rewriting the text, including requests for a deterministic local detector result when the host can execute Node.

Quality

91%

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

96%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.

An efficient, executable skill body with a well-sequenced workflow and clear validation guardrails; the bundled detector and flags are real and copy-paste ready. The only soft spot is reliance on unverifiable external sibling-Skill references for progressive disclosure.

Dimension	Reasoning	Score
Conciseness	Lean and terse with no concept tutorials or library padding; the only minor inefficiency is the near-duplicate stdin and --file examples, which still lands at anchor 5.	5 / 5
Actionability	Copy-paste-ready executable commands (node scripts/detect.js --context general / --file) with flags verified against the bundled detect.js, plus an explicit report checklist, matching anchor 5.	5 / 5
Workflow Clarity	The Preferred path is a numbered 5-step sequence with an execution-vs-fallback branch, explicit stop conditions, a two-pass RECHECK limit, and a "never claim execution unless it ran" guardrail, matching anchor 5's validation and feedback-loop criteria.	5 / 5
Progressive Disclosure	The body is a clear overview pushing the engine into scripts/ and cross-Skill detail to one-level-deep sibling paths, but several referenced paths lie outside this bundle and read as navigation cues rather than self-contained refs, matching anchor 4.	4 / 5
	Total	19 / 20 Passed

Description

87%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 tight, third-person description that states concrete actions and an explicit trigger, with a clear detect-only niche that distinguishes it from sibling skills. Minor synonym coverage and implicit outputs keep two dimensions at 4 rather than 5.

Dimension	Reasoning	Score
Specificity	Five concrete verbs ("detect, scan, audit, score, or flag") plus a sharpening negative scope ("without rewriting the text") match anchor 4; not a 5 because produced outputs (score/label) are implied rather than enumerated as actions.	4 / 5
Completeness	Explicitly answers both "what" (detect/scan/audit/score/flag AI-writing patterns without rewriting) and "when" ("Use when the user asks to...") with concrete trigger phrases, matching anchor 5.	5 / 5
Trigger Term Quality	Natural user verbs like "detect, scan, audit, score, or flag" are present, but synonyms a user might actually say (e.g. "AI-generated text", "bot-written") are missing, matching anchor 4.	4 / 5
Distinctiveness Conflict Risk	The detect-only niche is clear and the "without rewriting" clause explicitly separates it from sibling rewrite skills, giving minimal conflict risk per anchor 5.	5 / 5
	Total	18 / 20 Passed

Validation

100%

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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

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