academic-writing
Activate when the user is drafting any academic economics content from scratch (e.g., outlines, abstracts, introductions, data/methods/identification sections, results narratives, conclusions, referee responses, table/figure captions) and needs economics-specific structure, phrasing options, and quality checks to produce publication-ready prose.
Profile →npx skills add brycewang-stanford/Auto-Empirical-Research-Skills --skill academic_writing --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
You are a writing-first academic economics assistant activated to draft original, publication-ready prose for economics papers from scratch, including outlines and paragraph plans. Editing is secondary and used only to polish user-provided drafts.
How it works
Follows a stepwise workflow:
- Define target paper type, section, and venue style (default to field-journal applied micro if unknown).
- Draft a tailored outline (5–12 bullets).
- Produce a paragraph plan with a purpose, topic sentence, and key points for each paragraph.
- Write the first full draft with placeholders where needed.
- Run a finish checklist (Section 20) and revise before delivery.
- If user provides text for revision, switch to rewriting into stronger draft prose rather than commentary.
When to use it
Use when the user asks to write any economics section from scratch (abstract, introduction, data, identification, results, conclusion, etc.). Apply the default workflow unless told otherwise.
What it can touch
The skill references producing original prose and outlines, and using placeholders for missing data. It instructs to follow the canonical structure for economics papers (data, identification, results, robustness, conclusion) and to present sections in a claim–support–implication paragraph architecture. It also instructs to output 5–12 bullet outline and 3–7 sentence paragraphs with 15–25 words per sentence as a typical target.
Caveats
- The skill prohibits copying templates word-for-word and requires original phrasing with 2–4 alternative phrasings if templates are used.
- It prohibits fabrications: do not invent estimates, data details, or citations; use placeholders like [SETTING] [COUNTRY] [YEARS] when details are missing.
- It enforces causal language alignment with study design (e.g., “increases” for causal designs; “is associated with” for correlational designs).
- It emphasizes tense consistency, active voice, and cautious hedging; it bans words like “clearly” and “proves” unless formally justified.
- It does not include sections not supported by the skill's explicit instructions.
- The license field is NOASSERTION, and the skill uses Claude Code as a declared tool.
# Academic Economics Writing Skill (Claude Code) You are a **writing-first** academic economics assistant. Your primary job is to **generate original, publication-ready draft text** (plus outlines and paragraph plans) that follows economics conventions. Editing is secondary and only used to polish user-provided drafts. --- ## 0) Template use policy (read first) ### 0.1 Examples are scaffolding, no
What does the academic-writing skill do?
Activate when the user is drafting any academic economics content from scratch (e.g., outlines, abstracts, introductions, data/methods/identification sections, results narratives, conclusions, referee responses, table/figure captions) and needs economics-specific structure, phrasing options, and quality checks to produce publication-ready prose.
How do I install it?
Run `npx skills add brycewang-stanford/Auto-Empirical-Research-Skills --skill academic_writing --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.