ai-detect

Solid

Детекция и коррекция AI-сгенерированного текста по методике DrMax LinguaForensic v3.9.4 (284 лингвистических признака + 16 структурных маркеров + knockoff + fluency F1–F7 + GEO G0–G5 + adversarial humanization + Programmatic/Affiliate SEO domain + alignment-style proxies). 5 режимов: быстрая детекция, полная детекция, стратегический рерайт, сравнительный анализ, циклический рерайт. Use when: проверь текст на AI, роботность, AI-детект, детекция текста, похоже на нейросеть, гуманизация, очеловечить текст, рерайт под человека, снизить детектируемость, цитируемость в AI Overview, GEO-оптимизация текста, LinguaForensic, knockoff, fluency. SKIP: написание с нуля (→drmax-cocoon-engine-x4); типографика (→ru-text); редактура без детекта (→drmax-text-humanization).

AI & Automation 117 stars 0 forks Updated today MIT

Install

View on GitHub

Quality Score: 85/100

Stars 20%
69
Recency 20%
100
Frontmatter 20%
70
Documentation 15%
61
Issue Health 10%
50
License 10%
100
Description 5%
100

Skill Content

# LinguaForensic AI Text Detector v3.9.4 ## Protocol 1. Open the **canonical original** and apply it **byte-identically** — do not summarize, translate, or “improve” the skill text: - Primary: [references/AI-detect-v-3-9-4-full.md](references/AI-detect-v-3-9-4-full.md) 2. Older versions in `references/` (`v3.8.6`, `v3.8.12`, `v3.8.5`, `v3.4`) are **historical only** — use them only to reproduce an old report. 3. Output is probabilistic. Never claim “proved authorship”. 4. For pure editorial naturalness **without** detector optimization → use `drmax-text-humanization` (downstream of GIST). 5. For replaceability (not style) → X4 `/заменяемость` / GIST 4.3. ## Version map | Version | Status | Path | |---|---|---| | **3.9.4 full** | **Current for new work** | `references/AI-detect-v-3-9-4-full.md` | | 3.8.12 | Superseded (prompt-channel post 70) | corpus `.../70/AI-detect-v-3-8-12.md` | | 3.8.6 | Superseded (previous skill body) | `references/AI-detect-v-3-8-6.md` if present | | 3.8.5 / 3.4 | Archive | `references/` | ## Related - `drmax-text-humanization` — editorial layer (not detector evasion) - `drmax-cocoon-engine-x4` — page design / replaceability - `seo-drmax-orchestrator` — pipeline routing

Details

Author
VKirill
Repository
VKirill/claude-lane-stack
Created
2 months ago
Last Updated
today
Language
Python
License
MIT

Integrates with

OpenAI · AI

Bundled in these plugins

claude-lane-stack

Similar Skills

Semantically similar based on skill content — not just same category

AI & Automation Solid

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: cocoon/IA (→drmax-cocoon-engine-x4); AI-style measure (→ai-detect, not always-on).

117 Updated today
VKirill
Data & Documents Listed

humanizer

Audit, rewrite, or draft text so it carries zero AI-writing tells and makes only honest, sourced, self-consistent claims. Built from Wikipedia's "Signs of AI writing" (WikiProject AI Cleanup), open-source detector heuristics, and a writing-integrity contract. Use for ALL writing and editing tasks (blogs, LinkedIn, Quora, PR, case studies, emails, landing pages, executive ghostwriting) even when the user doesn't say "humanize". Also trigger when asked to detect AI patterns, de-AI a draft, audit claims, or check whether text would pass as human. Applies to everything except code and raw data.

0 Updated 2 months ago
Aparnabuilds
AI & Automation Featured

linkedin-humanizer

Remove the AI tells human readers and LinkedIn's AI-slop filter react to in a post or comment: 2026 vocabulary by paragraph density, reveal bridges, staccato fragments, stacked triads, performed sincerity. Tiered rewriter (forensic / strict / aesthetic / all) plus `--mode audit` pass-fail review and `--mode profile` voice profile builder. Not for beating AI detectors (no edit reliably does). Keywords: humanize, de-AI, reads like ChatGPT, AI slop, scrub AI tells, review this draft, audit before posting.

3,521 Updated 3 days ago
sergebulaev