DrMax LexAdapt v1.5 — лексическое упрощение текста под CEFR (EN) / ТРКИ (RU) без внешних словарей. Режимы Audit / Silent / Batch. Use when: упростить текст, CEFR, ТРКИ, A2 B1, readability level, lexadapt, адаптировать под уровень языка. SKIP: SEO-гуманизация (→drmax-text-humanization), AI-детект (→ai-detect), перевод (not this skill).
Scanned 9/3/2026
Install to Claude Code
Skills Directorynpx -y skills add VKirill/claude-lane-stack --skill drmax-lexadapt --agent claude-codeInstalls into .claude/skills of the current project.
Are you the author of Drmax Lexadapt?
Add the live security badge to your README — it updates automatically with every re-scan.
[](https://www.skillsdirectory.com/skills/vkirill-drmax-lexadapt)More formats (shields.io, HTML) on the badges page.
---
name: drmax-lexadapt
description: "DrMax LexAdapt v1.5 — лексическое упрощение текста под CEFR (EN) / ТРКИ (RU) без внешних словарей. Режимы Audit / Silent / Batch. Use when: упростить текст, CEFR, ТРКИ, A2 B1, readability level, lexadapt, адаптировать под уровень языка. SKIP: SEO-гуманизация (→drmax-text-humanization), AI-детект (→ai-detect), перевод (not this skill)."
---
# LexAdapt v1.5
## When
- Need simpler vocabulary for a target proficiency level
- EN → CEFR A1–C2; RU → ТРКИ levels
- Audit full report, Silent rewrite-only, or Batch ≤10 texts
## Protocol
1. Open and apply **1:1**: [ORIGINAL.md](ORIGINAL.md)
2. User must state mode + target level; default mode = Audit
3. No external lexicon APIs — LLM-only complexity estimate (approximate)
4. Preserve meaning; do not invent SEO keywords under the guise of simplification
## Place in pipeline
```
approved draft → LexAdapt (level target) → optional Humanization for rhythm
```
Usually **after** meaning is locked (GIST / fact check), not before strategy.
Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.
No comments yet. Be the first to comment!
Adversarial multi-agent planning skill. Self-orchestrates 5 hostile category members (unspecified-low, unspecified-high, deep, ultrabrain, artistry) via team-mode for ruthless cross-critique debate, distills only the defensible insights, then MANDATORILY hands the distilled insight bundle to the `plan` agent for executable plan formalization. Use when planning needs maximum rigor and surfacing of weak assumptions, blind spots, and over-engineering. Triggers: 'hyperplan', 'hpp', '/hyperplan', ...
