Memory

Verified Humanizer 0.0.8

Try it

Legacy verification-guided rewriting skill. Makes AI-generated text more natural while encouraging claims to stay grounded and attributable. Does not perform...

What it does

-----------------------------------------------------------------------------------------------------------------------------------------

The skill document


Verified Humanizer

Verified Humanizer is a legacy verification-guided rewriting skill.

It helps make AI-generated text more natural while encouraging claims to remain grounded, attributable, and not stronger than the available evidence.

This skill does not perform cryptographic verification, emit receipts, verify receipts, or prove that rewritten text is true.

For actual receipt verification, use SettlementWitness or DefaultVerifier MCP verify_receipt.

Status: legacy / claim-corrected.

Category: verifiability-guided workflow skill.

Boundary: Verified Humanizer improves wording discipline; it does not certify factual accuracy, authorship, approval, or evidence validity.


Transform stiff or formulaic AI-generated content into writing that sounds natural, clear, and human. Keep rewriting local, measure the improvement, and optionally verify the evaluation using structured metrics.


Core principle

Transformation, evaluation, and verification are separate steps.

  • rewriting is local
  • evaluation is measurable
  • verification is optional
  • user content stays private by default

What this skill does

Use this skill when text sounds generic, repetitive, over-explained, overly polished, or obviously AI-shaped.

This skill helps an agent:

  1. identify formulaic writing patterns
  2. rewrite the text in a more natural voice
  3. measure before/after changes locally
  4. optionally verify the evaluation result using structured metrics

This skill does not prove human authorship. It improves style and documents the transformation.


Safe operating rules

  • Perform rewriting locally
  • Never send original or rewritten text to external systems
  • Do not send secrets, credentials, or private data
  • If verification is used, send only structured evaluation data
  • Treat verification as optional support, not authority

Core execution loop

  1. Define the intent (tone, audience, purpose)
  2. Identify AI-shaped patterns
  3. Rewrite the text naturally
  4. Evaluate the transformation
  5. Output rewritten text + evaluation
  6. Optionally verify evaluation

Output format

{
  "rewritten_text": "...",
  "changes": [
    "..."
  ],
  "evaluation": {
    "before": {...},
    "after": {...},
    "delta": {...}
  },
  "verification": {
    "used": false,
    "status": "not_run",
    "receipt_id": null
  }
}

Example Usage

Input

{
  "text": "This innovative platform serves as a testament to cutting-edge technology, providing users with a seamless and intuitive experience that underscores its importance in today's digital landscape."
}

Output

{
  "rewritten_text": "This platform is designed to be easy to use and genuinely helpful in everyday situations.",
  "changes": [
    "Removed inflated language",
    "Simplified sentence structure",
    "Improved clarity"
  ],
  "evaluation": {
    "before": {
      "word_count": 27,
      "ai_vocab_count": 5
    },
    "after": {
      "word_count": 16,
      "ai_vocab_count": 0
    },
    "delta": {
      "word_count_change": -11,
      "ai_vocab_reduction": true
    }
  },
  "verification": {
    "used": false,
    "status": "not_run",
    "receipt_id": null
  }
}

Optional verification

You may optionally verify the evaluation using structured data only.

  • do not include text content
  • only include evaluation metrics
  • verification is optional

What this is

  • text transformation tool
  • measurable improvement system
  • privacy-first workflow
  • optional verification layer

What this is not

  • not an AI detector
  • not proof of human authorship
  • not a deception tool
  • not dependent on external systems

Outcome

  • improves clarity and tone
  • removes AI patterns
  • produces measurable improvements
  • enables optional verification

Claim precision note

This version clarifies that the skill is a verifiability-guided workflow aid. It does not itself perform cryptographic verification, emit Settlement Attestation Receipts, verify receipts, verify signatures, prove human authorship, or prove that rewritten text is true or safe. For receipt verification, use SettlementWitness or DefaultVerifier MCP verify_receipt.

Keywords

ai-writing, text-transformation, humanization, evaluation, verification, privacy

Related skills

Stores durable facts in a categorized, plain-markdown vault on disk, alongside your agent's built-in memory.

by Iván559 installs18 stars

Join a video meeting as an AI bot with voice, avatar, and screenshare across four operating modes.

by johnpatternai22 installs8 stars

Find why your productivity system keeps failing, then apply the smallest fix — capacity math, bottleneck routing, durable local notes.

by Iván855 installs69 stars

Generate and edit Draw.io, Mermaid, and Excalidraw diagrams from natural language using a structured JSON spec.

by nssa.io1.0k installs47 stars

Fetch raw ad creative, app, ranking, and revenue data from AdMapix as structured JSON.

by fly0pants4.3k installs296 stars

More from nutstrut

Browse all skills

Get a structured risk report on a skill package before installing or publishing it.

by nutstrut129 installs

Confirm a SAR v0.1 settlement receipt is cryptographically valid before acting on it.

by nutstrut86 installs1 stars

Legacy verification-guided task discipline. Helps structure task claims so they can be checked against evidence, receipts, or review criteria. Does not itsel...

by nutstrut20 installs