g6
VS-Enhanced Academic Style Humanizer - Transforms writing patterns to achieve authentic scholarly voice Applies transformations from G5 analysis to create natural academic prose Use when: improving AI-assisted writing quality, preparing manuscripts, enhancing scholarly voice
Profile →npx skills add brycewang-stanford/Auto-Empirical-Research-Skills --skill g6 --agent claude-code
Same command for any agent — swap --agent for codex, cursor, copilot.
Weekly change comes from our own snapshots, not the repository page — it measures attention, not adoption.
What it does
Transforms AI-assisted academic writing into natural, scholarly prose while preserving academic integrity, citation accuracy, statistical precision, and methodological clarity. It applies transformations from G5 analysis based on user-selected mode.
How it works
- Starts from the analysis output of G5-AcademicStyleAuditor and applies transformations according to the selected mode (conservative, balanced, aggressive).
- In conservative mode, targets high-risk patterns with minimal changes (about 10-20% of flagged instances).
- In balanced mode, targets high and medium-risk patterns for natural flow with scholarly tone (about 40-60% of flagged instances).
- In aggressive mode, targets all flagged patterns for maximum naturalness (about 80-100% of flagged instances).
- Maintains key elements: academic integrity, citation accuracy, statistical precision, and methodological clarity.
- Utilizes Unicode typographic characters and preserves technical terms, citations, and exact statistical values.
When to use it
Use when: improving AI-assisted writing quality, preparing manuscripts, enhancing scholarly voice.
What it can touch
Includes transformation of original text in YAML-structured input, subject to mode selection and optional parameters (preserve_list, section_type, target_journal, sections). It preserves citations, statistical values, sample sizes, and methodology specifics; it does not transform这些 elements.
Caveats
- Requires adherence to prerequisites (verified by diverga_check_prerequisites) and checkpoint CP_HUMANIZATION_VERIFY during execution.
- Output should maintain ethical responsibility for AI use as stated in aims.
## ⛔ Prerequisites (v8.2 — MCP Enforcement) `diverga_check_prerequisites("g6")` → must return `approved: true` If not approved → AskUserQuestion for each missing checkpoint (see `.claude/references/checkpoint-templates.md`) ### Checkpoints During Execution - 🟡 CP_HUMANIZATION_VERIFY → `diverga_mark_checkpoint("CP_HUMANIZATION_VERIFY", decision, rationale)` ### Fallback (MCP unavailable) Read `.re
What does the g6 skill do?
VS-Enhanced Academic Style Humanizer - Transforms writing patterns to achieve authentic scholarly voice Applies transformations from G5 analysis to create natural academic prose Use when: improving AI-assisted writing quality, preparing manuscripts, enhancing scholarly voice
How do I install it?
Run `npx skills add brycewang-stanford/Auto-Empirical-Research-Skills --skill g6 --agent claude-code` — it drops the skill into your project so the agent can pick it up. Swap the --agent value for codex, cursor or copilot if you use one of those.
Where does this skill come from?
From brycewang-stanford/Auto-Empirical-Research-Skills, a repository with 3,244 stars. We read it straight from the repository tree rather than a submitted listing, so what you see here is what is actually published.
Is a popular skill a good skill?
Not necessarily. Stars measure attention, not adoption — a repository can trend for a week and be abandoned. That is why we show the weekly change from our own snapshots next to the total, instead of a single flattering number.