SKILLEMALL.ai
GitHub ↗ RU Sign in

BD humanizer-pro

Transform AI-generated text into authentic human writing. Detects and removes 24 AI patterns, replaces 500+ AI vocabulary terms, analyzes statistical signals (burstiness, vocabulary diversity), and injects personality through strategic misspellings, parenthetical asides, tangents, and random thoughts. Use when humanizing content, checking for AI tells, removing robotic patterns, adding natural voice, making text sound less polished, or when asked to write like a specific person. Works with social posts, articles, emails, marketing copy, documentation—any text that needs to sound genuinely human.

Not recommendedcritical or high security findings
modbender/skill-library-mcp Agent Skills author: modbender MIT 7 files body ≈ 3 000 tokens Open the sourcegithub.com↗ analyzed 2 d ago

Transform AI-generated text into authentic human writing.

As a process D 48/100 · Unfinished process — weak spots: result and completion, inputs and preconditions, consistency

GeneratorData and analyticsWriting and documentstype and topics are labelled automatically from the skill text
Runs in: OpenClaw Claude / Claude Code ChatGPT / Codex Gemini CLI Cursor GitHub Copilot / VS Code Qwen Code Kimi Code CLI Z.ai (GLM) DeepSeek (Deep Code) Mistral Vibe LangChain (deepagents) Goose OpenCode
JSON
Technical rating
B
83/100
safety, quality, tests
Safety 60%
77
Quality 40%
91
Run on models
none yet
Process rating
D
48/100
Unfinished process
Result and completion w 14
0
Inputs and preconditions w 11
0
Progress reporting w 2
0
the three weakest of ten parameters · all ten

What is at stake

The skill contains fragments that, in the wrong hands, cost money or data. Below: what the installer risks and what the author should do.

Obfuscation
If you install

The files contain invisible characters, encoded commands or comments hidden from readers but visible to the model. What you read differs from what the agent sees.

For the author

Remove invisible characters (they usually sneak in through copy-paste) and encoded strings: no catalog will pass them. Instructions for the model must be readable by a human too.

How to improve

  1. Address the high-severity findings: each costs 18 safety points. If one is a false positive, add the rule id to guard.allow in spec.yaml.
For the model run — optional
  • 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 · 2

  • high Obfuscation uni-zero-width references/personality-injection.md:484
    Zero-width / invisible characters (possible hidden text) (3 occurrences)
    ␀
Medium and low: 1
  • medium Obfuscation uni-zero-width references/examples.md:130
    Zero-width / invisible characters (possible hidden text) (4 occurrences) (test fixture / example file)
    ␀
    fixture

Files scanned: 7. 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 48/100

  • 0Result and completion. Does not say what the result is
  • 0Inputs and preconditions. Does not say what the process needs to start
  • 0Progress reporting. Says nothing while it works
  • 40Consistency. Frontmatter name (humanizer-pro) differs from the folder (operator-humanizer)
  • 50When it triggers. No condition that starts the skill
  • 50Failures and branches. 0 branches, has a failure section
  • 60Tools and files. Uses tools (web) that frontmatter does not declare
  • 85Steps. 84 steps, 2 vague phrases
  • 100Execution cost. Instruction body is 3000 tokens
  • 100Running it twice. Mutating operations check current state
  • low 14 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)
  • +3Output format is not stated: the model decides each time
  • +1No license
  • +2Single-language instructions
  • +3Description length 602: enough signal without eating the budget
  • +4Structure: 33 headings
  • +3Step-by-step instructions: 84 items
  • +4Has examples (1 code blocks)
  • +4Reference files are cited in the instructions (4 of 5)
  • +3All 1 scripts are documented

Quality base 70; lint remarks subtract, signals add up to 100. Result: 91.