BD humanizer
Humanize AI-generated text by detecting and removing patterns typical of LLM output. Rewrites text to sound natural, specific, and human. Uses 24 pattern detectors, 500+ AI vocabulary terms across 3 tiers, and statistical analysis (burstiness, type-token ratio, readability) for comprehensive detection. Use when asked to humanize text, de-AI writing, make content sound more natural/human, review writing for AI patterns, score text for AI detection, or improve AI-generated drafts. Covers content, language, style, communication, and filler categories.
Humanize AI-generated text by detecting and removing patterns typical of LLM output.
As a process D 36/100 · Unfinished process — weak spots: result and completion, when it triggers, inputs and preconditions
The same skill appears in 5 more places: ClawHub, ClawHub, ClawHub, ClawHub, ClawHub
How to improve
- 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: 21. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
✓ No remarks against the Agent Skills spec
Process rating: all ten parameters 36/100
- 0Result and completion. Does not say what the result is
- 0Inputs and preconditions. Does not say what the process needs to start
- 0Failures and branches. Linear process with no failure handling
- 0Progress reporting. Says nothing while it works
- 20When it triggers. No condition that starts the skill
- 30Running it twice. 7 mutating operations with no state check
- 40Consistency. Frontmatter name (humanizer) differs from the folder (ai-humanizer)
- 60Tools and files. Uses tools (web) that frontmatter does not declare
- 85Steps. 33 steps, 1 vague phrases
- 100Execution cost. Instruction body is 1829 tokens
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)
- +3Output format is not stated: the model decides each time
- -46 reference files, but SKILL.md never points to them: the model will not open them
- -32 of 2 scripts are never mentioned in SKILL.md
- +1No license
- +2Single-language instructions
- +3Description length 554: enough signal without eating the budget
- +4Structure: 13 headings
- +3Step-by-step instructions: 33 items
- +4Has examples (1 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 77.
In the sandbox The scripts kept to themselves
The skill's scripts were run in a throwaway machine: no network, fake keys in the home directory, a tracer watching. We wrote down what they did. Reaching for the network or for secrets caps the technical grade at C; a quiet run adds no points.
Запущено 10 скриптов; каждому дали двадцать секунд, поддельный домашний каталог с ключами и сеть, в которой ничего нет.
eslint.config.js | ничего за пределами своей папки |
vitest.config.js | ничего за пределами своей папки |
scripts/analyze.sh | завершился с кодом 133 |
scripts/humanize.sh | завершился с кодом 133 |
src/analyzer.js | ничего за пределами своей папки |
src/cli.js | ничего за пределами своей папки |
src/humanizer.js | ничего за пределами своей папки |
src/patterns.js | ничего за пределами своей папки |
src/stats.js | ничего за пределами своей папки |
src/vocabulary.js | ничего за пределами своей папки |
26 Sept 2026