write
Draft academic paper sections with notation protocol, anti-hedging, and humanizer pass. Replaces /draft-paper and /humanizer.
Profile →npx skills add brycewang-stanford/Auto-Empirical-Research-Skills --skill write --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.
# Write Draft paper sections or apply humanizer pass by dispatching the **Writer** agent. **Input:** `$ARGUMENTS` — section name or mode, optionally followed by file path. --- ## Modes ### `/write [section]` — Draft Paper Section Draft a specific section: `intro`, `strategy`, `results`, `conclusion`, `abstract`, or `full`. **Agent:** Writer **Output:** LaTeX section file in paper/sections/ Workflow: #### 1. Context Gathering Before drafting, read all available context: 1. Read existing paper draft in `paper/` (if it exists) 2. Read `master_supporting_docs/` for notes, outlines, research specs 3. Read most recent `quality_reports/research_spec_*.md` or `quality_reports/lit_review_*.md` 4. Read `.claude/references/domain-profile.md` for field conventions 5. Check `Bibliography_base.bib` for available citations 6. Scan `paper/tables/` and `paper/figures/` for generated output 7. Read `quality_reports/results_summary.md` if it exists (from Coder) #### 2. Section Routing Based on `$ARGUMENTS`: - **`full`**: Draft all sections in sequence, pausing between major sections for user feedback - **`intro`**: Draft introduction (most common request) - **`strategy`**: Draft identification and es
- Modes
- /write [section] — Draft Paper Section
- /write humanize [file] — Humanizer Pass Only
- Section Standards
- LaTeX Conventions
- Principles
What does the write skill do?
Draft academic paper sections with notation protocol, anti-hedging, and humanizer pass. Replaces /draft-paper and /humanizer.
How do I install it?
Run `npx skills add brycewang-stanford/Auto-Empirical-Research-Skills --skill write --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.