BB humanizer
Remove signs of AI-generated writing from text. Use when editing or reviewing text to make it sound more natural and human-written. Based on Wikipedia's comprehensive "Signs of AI writing" guide. Detects and fixes patterns including: inflated symbolism, promotional language, superficial -ing analyses, vague attributions, em dash overuse, rule of three, AI vocabulary words, passive voice, negative parallelisms, and filler phrases.
Promises to strip AI-writing markers: inflated symbolism, em-dash abuse, rule of three, passive voice, filler phrases. Leans on Wikipedia's guide to machine-generated text patterns.
Tests gave it B grade, quality_score 74, process_score 71. No critical issues flagged. Runs across all major platforms. No actual model execution recorded, sandbox empty—unclear how it performs in the wild. 6754 body tokens is modest for the job.
Worth installing if you need automated first-pass cleanup. Expect heuristic results, not miracles.
The same skill from clawhub has been run on models: No improvement D see the result → This is a copy: its text may differ, so the grade is not carried over.
Remove signs of AI-generated writing from text.
As a process B 71/100 · Nearly there — weak spots: when it triggers, inputs and preconditions, running it twice
How to improve
- The SKILL.md body is over 5,000 tokens: move reference detail into references/ and load it when needed.
- Your own cases (evals/evals.json, 4–6 real requests with expected answers): the full check would then run those instead of a model-drafted suite.
- A spec.yaml with trigger phrases and assertions — a behaviour contract for CI; `skilltest init` writes a template.
Guard findings · 0
✓ No critical or high findings
Files scanned: 1. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
body-longSKILL.md body ≈ 6754 tokens (recommended < 5000); move details to references/ - note
edit-residuethe text marks something as outdated (lines 71, 133, 464): check that old rules are not kept next to new ones — the full check reads the text for contradictions
Process rating: all ten parameters 71/100
- 0Inputs and preconditions. Does not say what the process needs to start
- 0Progress reporting. Says nothing while it works
- 20When it triggers. No condition that starts the skill
- 30Running it twice. 23 mutating operations with no state check
- 70Execution cost. Instruction body is 6754 tokens
- 85Steps. 66 steps, 1 vague phrases
- 100Tools and files. Tools declared in frontmatter
- 100Result and completion. Output format and completion criterion are stated
- 100Failures and branches. 1 branches, has a failure section
- 100Consistency. Name and required fields are in place
- low 12 top-level sections: this looks like several domains in one skill
Everything here is measured from the skill text rather than judged by a model, so the numbers are checkable. A parameter weighs more when it is a more common reason for the process to stall.
Quality signals
- +5Description has no quoted example phrases that should trigger the skill
- +4Description does not say when NOT to use the skill (false activations)
- +4No input/output examples
- +2Single-language instructions
- +3Description length 433: enough signal without eating the budget
- +4Structure: 47 headings
- +3Step-by-step instructions: 66 items
- +3Output format is stated explicitly
- +1License stated
Quality base 70; lint remarks subtract, signals add up to 100. Result: 74.