ai-writing-tropes

Detect and eliminate common AI writing tropes from prose. Use when drafting, editing, or reviewing text to avoid the predictable patterns that mark AI-generated writing.

Quality

76%

Does it follow best practices?

Impact

—

No eval scenarios have been run

Securityby

Passed

No known issues

Fix and improve this skill with Tessl

tessl review fix ./ai-writing-tropes/SKILL.md

Quality

Content

77%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

This is a well-structured, concise skill that catalogs AI writing tropes effectively with clear organization and good progressive disclosure design. Its main weakness is the lack of concrete before/after examples showing how to rewrite flagged passages, which would significantly improve actionability. The referenced detail files are well-signaled but not provided in the bundle.

Suggestions

Add 2-3 concrete before/after rewrite examples showing how to fix a passage containing multiple tropes (e.g., transform a 'not X — it's Y' sentence into natural prose)

Include the referenced files (references/word-choice.md, etc.) in the bundle, or inline the most critical details if the bundle won't be provided

Dimension	Reasoning	Score
Conciseness	The content is lean and efficient. It doesn't explain what AI writing tropes are in abstract terms or waste tokens on concepts Claude already knows. Each section delivers specific examples and moves on. The quick self-check is a tight checklist, not a verbose explanation.	3 / 3
Actionability	The skill provides concrete examples of tropes to avoid and a clear self-check list, but it lacks before/after rewrite examples showing how to fix flagged passages. The guidance is 'rewrite that passage' without demonstrating what a good rewrite looks like, making it somewhat incomplete as actionable instruction.	2 / 3
Workflow Clarity	The four-step workflow (draft → check → rewrite → re-read for density) is clear and appropriately sequenced. The self-check section serves as an explicit validation checkpoint. For a non-destructive editing task, this level of workflow structure is sufficient and well-organized.	3 / 3
Progressive Disclosure	The skill references six separate files in a references/ directory with clear one-level-deep links, which is excellent structure. However, no bundle files were provided, so the referenced files don't actually exist in the evaluated bundle, meaning the progressive disclosure structure is well-designed but unverifiable. The inline summaries with 'key offenders' partially compensate.	2 / 3
	Total	10 / 12 Passed

Description

75%

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 has a solid structure with both 'what' and 'when' clauses clearly stated, and occupies a distinctive niche. However, it would benefit from more specific concrete actions (e.g., listing particular tropes or patterns it addresses) and broader trigger term coverage to capture the natural language users would employ when seeking this kind of help.

Suggestions

Add specific examples of the tropes being targeted, e.g., 'Detects and removes filler phrases, excessive hedging, overused transitions like "delve" or "it's worth noting", and formulaic sentence structures.'

Expand trigger terms to include natural user phrases like 'sounds like AI', 'make it sound more human', 'remove AI clichés', 'ChatGPT voice', or 'robotic writing'.

Dimension	Reasoning	Score
Specificity	It names the domain (AI writing tropes in prose) and describes the general action (detect and eliminate), but doesn't list specific concrete actions or examples of what tropes are targeted (e.g., 'remove filler phrases, eliminate passive hedging, fix overuse of em-dashes').	2 / 3
Completeness	Clearly answers both 'what' (detect and eliminate common AI writing tropes from prose) and 'when' (when drafting, editing, or reviewing text to avoid predictable AI patterns), with an explicit 'Use when' clause.	3 / 3
Trigger Term Quality	Includes some relevant terms like 'AI writing tropes', 'drafting', 'editing', 'reviewing text', and 'AI-generated writing', but misses common natural variations users might say such as 'sounds like AI', 'too robotic', 'make it sound human', 'natural writing', 'clichés', or 'ChatGPT-style'.	2 / 3
Distinctiveness Conflict Risk	The focus on AI writing tropes specifically is a clear niche that is unlikely to conflict with general editing, proofreading, or style guide skills. The trigger terms are distinct enough to differentiate from broader writing assistance skills.	3 / 3
	Total	10 / 12 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
metadata_version	'metadata.version' is missing	Warning

	Total	10 / 11 Passed

Repository: joshuadavidthomas/agent-skills
Commit: 4c9cb62

Reviewed: 15 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.