humanizer

Rewrite AI-sounding text so it reads naturally without changing what it says. Use when editing or reviewing prose for inflated claims, sales language, vague sources, repetitive structure, stock AI words, passive voice, filler, or chatbot artifacts. Based on Wikipedia's "Signs of AI writing."

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

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.

The body is a dense, well-structured, highly actionable reference with concrete before/after examples and an explicit validation-backed workflow. Its main weakness is that the large pattern catalog is all inlined rather than progressively disclosed into separate reference files.

Suggestions

Move the 35-pattern catalog (Content/Language/Style/Chatbot/Filler sections) into a separate reference file such as PATTERNS.md, keeping SKILL.md as an overview that links to it, to improve token efficiency and progressive disclosure.

If the pattern catalog stays inline, add a short table of contents or quick-reference summary at the top so the structure is navigable without scanning all 440 lines.

Either reference scripts/validate-package.py from the body where relevant, or note that it is a packaging-only helper not intended for skill runtime use.

Dimension	Reasoning	Score
Conciseness	Per-line the body is lean with no concept-explaining filler, but the ~440-line catalog of 35 patterns is voluminous for a SKILL.md and parts of it could live in a reference file.	4 / 5
Actionability	Highly actionable throughout: each pattern has 'Words to watch' lists, concrete before/after examples, and explicit executable rules (e.g. search for em/en dashes and remove unless the sample uses them).	5 / 5
Workflow Clarity	Provides a clear sequenced 'What to do' and 'Rewrite process' with an explicit validation checkpoint (checking whether any fact was added or removed) and a feedback loop for error recovery.	5 / 5
Progressive Disclosure	Well-organized into clear labeled sections, but the entire 35-pattern catalog is inlined in SKILL.md rather than split across one-level-deep reference files; the only bundle file (validate-package.py) is not referenced by the body.	4 / 5
	Total	18 / 20 Passed

Description

95%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.

The description is concise, specific, and clearly answers both 'what' and 'when' with a rich set of natural trigger phrases. It is written in third person and avoids vague fluff, making it highly distinct and low-conflict.

Dimension	Reasoning	Score
Specificity	Names the domain and lists several concrete pattern targets ('inflated claims, sales language, vague sources, ... filler, or chatbot artifacts'), with only minor gaps versus a fully enumerated action set.	4 / 5
Completeness	Explicitly states both what it does ('Rewrite AI-sounding text so it reads naturally without changing what it says') and when to use it ('Use when editing or reviewing prose for...') with concrete triggers.	5 / 5
Trigger Term Quality	Comprehensive natural trigger coverage ('AI-sounding text', 'editing or reviewing prose', 'sales language', 'passive voice', 'filler', 'chatbot artifacts') with many synonyms a user would actually say.	5 / 5
Distinctiveness Conflict Risk	Occupies a clear niche (removing AI writing patterns sourced from Wikipedia) with distinct triggers and minimal overlap risk with other skills.	5 / 5
	Total	19 / 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: MODSetter/SurfSense
Path: .agents/skills/humanizer/SKILL.md
Commit: be4a191

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.