Skip to content
Agent Orchestration
Skill

/drmax-text-humanization

DrMax TEXT HUMANIZATION v1.6.1 RUNTIME — last-mile editorial after X4/GIST export: clarity, naturalness, decision value; no semantic-contract break, no detector-evasion. Use when: очеловечить текст, humanization, довести черновик, GIST handoff, сделать текст естественнее. SKIP:

BOOST
From plugin
claude-lane-stack
12464 skills24 agents5 commands12 hooks
+1
Install
$ npx -y skills add VKirill/claude-lane-stack --skill drmax-text-humanization --agent claude-code

How it fires

How this skill gets triggered: by you, by Claude, or both.

  • Fires itselfAuto-invocation. Claude auto-loads it when your prompt matches the work.Auto-invocation is when the right skill fires by itself at the right moment, driven by a FLOW.md router and a hook, instead of you invoking it by name. It is the difference between a skill being installed and a skill actually getting used.Read the full definition →
  • You can call itInvoke it directly when you want it.
  • Slash command/drmax-text-humanization

Context preview

The summary Claude sees to decide when to auto-load this skill.

DrMax TEXT HUMANIZATION v1.6.1 RUNTIME — last-mile editorial after X4/GIST export: clarity, naturalness, decision value; no semantic-contract break, no detector-evasion. Use when: очеловечить текст, humanization, довести черновик, GIST handoff, сделать текст естественнее. SKIP:

SKILL.md

drmax-text-humanization.SKILL.md
name: drmax-text-humanization
description: "DrMax TEXT HUMANIZATION v1.6.1 RUNTIME — last-mile editorial after X4/GIST export: clarity, naturalness, decision value; no semantic-contract break, no detector-evasion. Use when: очеловечить текст, humanization, довести черновик, GIST handoff, сделать текст естественнее. SKIP: cocoon/IA (→drmax-cocoon-engine-x4); AI-style measure (→ai-detect, not always-on)."

TEXT HUMANIZATION by DrMax v1.6.1

When

  • After X4 `экспорт` or an approved draft: delivery layer only
  • Draft is factually approved; need natural professional prose
  • **Not** for gaming AI detectors (that is a different, discouraged goal)

Protocol

1. Load runtime skill **1:1**: [ORIGINAL.md](ORIGINAL.md) 2. Optional help + scenarios:

  • [HELP.md](HELP.md)
  • [SCENARIOS.md](SCENARIOS.md)

3. Prefer `GIST HUMANIZATION HANDOFF` if available 4. Priority: facts → semantic contract → decision architecture → safety → decision value → specificity → clarity → readability → style 5. Do **not** change protected facts, conditions, limits, or unique GIST factors for “smoothness”

Place in pipeline

X4 export / approved draft → Text Humanization → ai-detect → publish

Related

  • `drmax-cocoon-engine-x4` — structure and GIST 4.3; this skill does not design pages
  • `ai-detect` — LinguaForensic 3.9.4 measure after this pass; not a substitute
  • `drmax-signalforge` — live-URL experiments, not prose polish
Read more
Ships withclaude-lane-stack

Claude Lane Stack is a self-hosted toolkit for coordinating coding agents through CLI processes, task contracts, Git workspaces, and verification receipts (bin/run-controller:117-159, schemas/task-v2.schema.json:1-60).

Get the whole plugin

Other skills on claude-lane-stack.