humanizer

Humanize text: strip AI-isms and add real voice.

Quality

65%

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

Fix and improve this skill with Tessl

tessl review fix ./skills/creative/humanizer/SKILL.md

Quality

Content

77%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 highly actionable, well-sequenced editing workflow with an explicit self-audit validation loop and concrete before/after examples for every pattern. Its weaknesses are duplication between the 'Your task' and 'Process' sections and a monolithic single-file structure that inlines a large pattern catalogue which could live in a reference file.

Suggestions

Merge the 'Your task' and 'Process' sections into one workflow; they repeat the same steps including the identical 'What makes the below so obviously AI generated?' prompt.

Move the 34-pattern catalogue (or the less common patterns 30-34) into a references/ file, keeping SKILL.md as an overview with clearly signaled one-level-deep pointers.

Trim patterns that restate knowledge Claude already has (emojis, curly quotes, basic filler phrases) to short word-watch lists, and shorten the ~70-line Full Example.

Dimension	Reasoning	Score
Conciseness	The pattern catalogue is the skill's core payload and mostly earns its tokens, but there is noticeable redundancy: the 'Your task' and 'Process' sections repeat the same steps including the same self-audit prompt, the Full Example runs ~70 lines, and some patterns (emojis, curly quotes, filler phrases) restate things Claude already knows. This is 'mostly efficient but includes some unnecessary explanation or could be tightened', more than the minor trimming of a 4.	3 / 5
Actionability	Every one of the 34 patterns has a concrete before/after example, the workflow names specific tools (read_file, patch, write_file) with guidance on when to use each, and the output format and full worked example make the guidance fully executable. This is fully actionable, copy-paste-ready instruction for an instruction-only skill.	5 / 5
Workflow Clarity	The process is clearly sequenced (identify patterns, rewrite, draft, self-audit, revise, present final, apply edits) with an explicit validation feedback loop: 'What makes the below so obviously AI generated?' is answered and the text is revised before the final version. The 34 patterns function as a checklist, matching the top anchor with explicit validation steps and an error-recovery-style loop.	5 / 5
Progressive Disclosure	No bundle files exist (no references/, scripts/, or assets/), so the entire ~630-line skill including the 34-pattern reference catalogue is inlined in SKILL.md. Internal structure is good with clear section headers, which lifts it above the 'minimal structure' of a 2, but a pattern reference this large is content that could be split into a separate file, matching the 'content that should be separate is inline' anchor.	3 / 5
	Total	16 / 20 Passed

Description

53%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 and concrete about what the skill does, with a distinctive niche and natural trigger term ("humanize"). Its main weakness is the complete absence of when-to-use guidance and missing common synonyms like "de-slop" or "make this sound human", both of which limit discoverability at trigger time.

Suggestions

Add an explicit 'Use when...' clause, e.g. 'Use when the user asks to humanize, de-slop, or de-AI text, or wants writing to sound less like an LLM.'

Include common user phrasings as trigger terms: "de-slop", "make this sound human", "less ChatGPT-y", "sound natural".

Briefly enumerate the concrete actions (identify AI writing patterns, rewrite, match a provided voice sample) to raise specificity beyond two actions.

Dimension	Reasoning	Score
Specificity	"Humanize text: strip AI-isms and add real voice" names the domain and two concrete actions, but does not list the fuller set of capabilities (pattern identification, rewriting, voice matching). It matches the anchor for naming a domain with 1-2 concrete actions without being comprehensive, and is not generic enough to score 2.	3 / 5
Completeness	The description gives a clear 'what' (strip AI-isms, add real voice) but contains no 'Use when...' clause or equivalent explicit trigger guidance, which caps completeness at 3 per the judging guidelines. It is not a 2 because the 'what' is specific, and not a 4 because 'when' is entirely absent rather than merely weakly implied.	3 / 5
Trigger Term Quality	"Humanize" and "AI-isms" are natural terms users would say, but common variations and synonyms ("de-slop", "de-AI", "make this sound human", "sound natural") are missing. This sits at 'some relevant keywords but missing common variations', not at 'good keyword coverage'.	3 / 5
Distinctiveness Conflict Risk	The AI-isms/humanize niche is clearly distinguishable from most other skills with distinct trigger vocabulary. It carries minor overlap risk with general writing/editing skills, matching the 'mostly distinct; minor overlap risk' anchor rather than the 'clear niche with minimal conflict risk' of 5.	4 / 5
	Total	13 / 20 Passed

Validation

75%

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 — 12 / 16 Passed

Validation for skill structure

Criteria	Description	Result
skill_md_line_count	SKILL.md is long (648 lines); consider splitting into references/ and linking	Warning
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	12 / 16 Passed

Repository: NousResearch/hermes-agent
Path: skills/creative/humanizer/SKILL.md
Commit: 68fa7e9

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.