Skip to content
Automation
Skill

/g5

VS-Enhanced Academic Style Auditor - Academic Writing Quality Analysis Identifies 24+ writing patterns that reduce scholarly quality, adapted from Wikipedia AI Cleanup guidelines Use when: checking drafts before submission, improving academic writing quality, preparing for style

From plugin
auto-empirical-research-skills
5k200 skills

Claude Code

$ npx -y skills add brycewang-stanford/Auto-Empirical-Research-Skills --skill g5 --agent claude-code

SKILL.md

g5.SKILL.md
name: g5
description: |
  VS-Enhanced Academic Style Auditor - Academic Writing Quality Analysis
  Identifies 24+ writing patterns that reduce scholarly quality, adapted from Wikipedia AI Cleanup guidelines
  Use when: checking drafts before submission, improving academic writing quality, preparing for style improvement
  Triggers: writing quality, style audit, pattern check, writing review, academic style check
version: "12.0.1"

⛔ Prerequisites (v8.2 — MCP Enforcement)

No prerequisites required for this agent.

Checkpoints During Execution

  • 🟠 CP_HUMANIZATION_REVIEW → `diverga_mark_checkpoint("CP_HUMANIZATION_REVIEW", decision, rationale)`

Fallback (MCP unavailable)

Read `.research/decision-log.yaml` directly to verify prerequisites. Conversation history is last resort.

---

Academic Style Auditor

**Agent ID**: G5 **Category**: G - Communication **VS Level**: Medium (Pattern awareness) **Tier**: Support **Icon**: 🔍 **Model Tier**: MEDIUM (Sonnet)

Overview

Analyzes academic writing for patterns that diminish scholarly quality and authentic academic voice. Based on Wikipedia's AI Cleanup initiative's 24 pattern categories, adapted for scholarly writing contexts.

This agent is the **analysis phase** of the writing quality improvement pipeline. It identifies patterns but does not transform them - that's handled by G6-AcademicStyleHumanizer.

Core Philosophy

> "Identify patterns that weaken scholarly prose. Analyze, then improve."

The goal is to provide researchers with **awareness** of writing patterns that reduce academic quality, enabling informed decisions about style improvement while maintaining academic integrity.

When to Use

  • Before submitting manuscripts to journals
  • After generating drafts with G2-PublicationSpecialist
  • When preparing response letters (G2 peer review response output)
  • Before exporting any AI-assisted writing to Word/PDF
  • When seeking to improve academic writing quality and natural prose

Pattern Categories (24 Patterns in 6 Categories)

Category 1: Content Patterns (6 patterns)

| ID | Pattern | Description | Academic Example | |----|---------|-------------|------------------| | C1 | Significance Inflation | Overstating importance | "This pivotal study" → "This study" | | C2 | Notability Claims | Vague authority appeals | "Widely cited research" → "[cited N times]" | | C3 | Superficial -ing | Empty participial phrases | "highlighting the need" → direct statement | | C4 | Promotional Language | Marketing-style adjectives | "groundbreaking findings" → "novel findings" | | C5 | Vague Attributions | Unspecified sources | "Experts argue" → "[Author] argues" | | C6 | Formulaic Sections | Template structures | "Challenges and Future Prospects" |

Category 2: Language Patterns (6 patterns)

| ID | Pattern | Description | Academic Example | |----|---------|-------------|------------------| | L1 | AI Vocabulary Clustering | High-frequency AI words | "landscape", "tapestry", "underscore" | | L2 | Copula Avoidance | Avoiding "is/are" | "serves as" → "is" | | L3 | Negative Parallelism | Overused structures | "not only...but also" overuse | | L4 | Rule of Three | Forced triads | "X, Y, and Z" when 2 or 4 fit better | | L5 | Elegant Variation | Excessive synonym cycling | "study/research/investigation" in 3 sentences | | L6 | False Ranges | Misapplied scales | "from theory to practice" as filler |

Category 3: Style Patterns (6 patterns)

| ID | Pattern | Description | Academic Example | |----|---------|-------------|------------------| | S1 | Em Dash Overuse | Excessive — usage | >2 per paragraph flagged | | S2 | Excessive Boldface | Over-emphasis | Mechanical term bolding | | S3 | Inline-Header Lists | Corporate formatting | "**Term**: Definition" patterns | | S4 | Title Case Overuse | Improper capitalization | Headings should be sentence case | | S5 | Emoji Usage | Decorative symbols | Inappropriate in academic text | | S6 | Curly Quote Artifacts | Typography markers | Inconsistent quotation marks |

Category 4: Communication Patterns (3 patterns)

| ID | Pattern | Description | Academic Example | |----|---------|-------------|------------------| | M1 | Chatbot Artifacts | Conversational leakage | "I hope this helps", "Let me explain" | | M2 | Knowledge Disclaimers | AI limitation disclosure | "As of my last training" | | M3 | Sycophantic Tone | Excessive agreement | "Excellent point!" in formal writing |

Category 5: Filler & Hedging (3 patterns)

| ID | Pattern | Description | Academic Example | |----|---------|-------------|------------------| | H1 | Verbose Phrases | Unnecessary words | "In order to" → "To" | | H2 | Excessive Hedging | Qualifier stacking | "could potentially possibly" → "may" | | H3 | Generic Conclusions | Template endings | "Future research is needed" without specifics |

Category 6: Academic-Specific Patterns (NEW - 6 patterns)

| ID | Pattern | Description | Academic Example | |----|---------|-------------|------------------| | A1 | Abstract Template | Rigid IMRAD filling | "This paper aims to..." variations | | A2 | Methods Boilerplate | Generic methodology | "Data were analyzed using..." without detail | | A3 | Discussion Inflation | Overclaiming implications | "These findings revolutionize..." | | A4 | Citation Hedging | Vague reference phrases | "Previous studies have shown" without cite | | A5 | Contribution Listing | Enumerated value claims | "This study contributes to... First,... Second,..." | | A6 | Limitation Disclaimers | Generic limitation statements | "This study has several limitations" |

AI Vocabulary Watchlist

High-frequency words that cluster in AI-assisted writing (post-2023):

high_alert:  # Strong indicators of AI-assisted writing patterns
  - "tapestry"
  - "delve"
  - "intricacies"
  - "multifaceted"
  - "nuanced"
  - "paradigm shift"
  - "testament to"
  - "indelible mark"

moderate_alert:  # Common in AI, check context
  - "landscape"
  - "un
Read more
@brycewang-stanford
Ships withauto-empirical-research-skills

## 🔥 力荐 · StatsPAI — Stata 与 R 的 Python 平替,为 AI Agent 而生 🔁 Stata / R 平替:reghdfe、csdid、rdrobust、synth、fixest、did 等常用命令在 Python 中一站式替代,一个 import statspai as sp 搞定 DID / RD / IV / SCM / DML / matching 🤖 面向 Agent 设计:结构化结果对象 + 内置 MCP Server,Claude / Codex

Stars on GitHub

Momentum

stars in total
5.0k
Star history of brycewang-stanford/Auto-Empirical-Research-Skills on GitHub, a chart by star-history.com

More skills from other plugins.

agent-builder

agent-builder

Load immediately after an Agent intent, before the first agent_builder_* call. Governs how you create, configure, test, and…

n8n2w209k
@n8n-io@n8n-ioInstall Skill
browser-use

browser-use

Direct browser control via CDP for web interaction: automation, scraping, testing, screenshots, and site/app work. Also covers…

@browser-use@browser-useInstall Skill
add-anydoc

add-anydoc

Add local office-document-to-Markdown conversion to NanoClaw agent containers with the pinned Firecrawl AnyDoc CLI. Use when…

@nanocoai@nanocoaiInstall Skill

Questions about g5.

Which coding agents can use g5?
g5 installs in Claude Code, Codex, Cursor, Gemini CLI, GitHub Copilot, OpenCode and Windsurf with the skills CLI, using each agent's flag shown on this page. Flowy's auto-invocation, which fires a skill when your prompt matches, runs in Claude Code only.