ワンクリックで
humanizer
Detect and remove AI writing patterns to produce natural, human-sounding prose
Codex または Claude でインストール この Prompt をコピーして Codex、Claude、または他のアシスタントに貼り付けると、Skill ページを確認してインストールできます。
メニュー
Detect and remove AI writing patterns to produce natural, human-sounding prose
Codex または Claude でインストール この Prompt をコピーして Codex、Claude、または他のアシスタントに貼り付けると、Skill ページを確認してインストールできます。
SOC 職業分類に基づく
Author or revise reusable Hexis skills from repeated successful workflows
Semantic recall, exact cross-session search, remembering, and normal continuity
Ingest URLs, documents, and text into the memory system as structured knowledge
Inspect, grant, and revoke scoped connector action policies for sends, replies, labels, spam triage, and provider state changes
Digest and ingest emails into memory, surfacing important threads and action items
Send Gmail messages, reply to threads, apply labels, and triage spam with explicit action authorization
| name | humanizer |
| description | Detect and remove AI writing patterns to produce natural, human-sounding prose |
| category | creative |
| contexts | ["heartbeat","chat"] |
| bound_tools | ["humanize_text"] |
Analyze text for telltale AI-generated writing patterns and rewrite it to sound natural, varied, and human-authored.
Analyze the input: Before rewriting, identify the specific AI patterns present. Common tells include:
Determine the target voice: Ask or infer the desired tone. Options include:
Rewrite with human patterns: Apply transformations that mimic natural writing:
Call the tool: Pass the original text and target voice to humanize_text, which applies rule-based pattern removal and optionally an LLM rewrite pass.
Review the output: Check that the rewrite preserved the original meaning and key information. Humanizing should change the voice, not the substance.