菜单
Manuscript proofreading dispatching the academic-proofreader agent. Checks 6 categories — structure, claims-evidence alignment, identification fidelity, writing quality, grammar, and compilation. Produces report without editing files.
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
基于 SOC 职业分类
| name | proofread |
| description | Manuscript proofreading dispatching the academic-proofreader agent. Checks 6 categories — structure, claims-evidence alignment, identification fidelity, writing quality, grammar, and compilation. Produces report without editing files. |
| argument-hint | [filename or 'all'] |
| allowed-tools | ["Read","Grep","Glob","Write","Task"] |
Run the proofreading protocol by dispatching the academic-proofreader agent.
$ARGUMENTS is a specific .tex file: review that file$ARGUMENTS is all: review paper/main.tex and all files in Paper/sections/$ARGUMENTS is a talk file in Talks/: review as advisory (non-blocking)Delegate to the academic-proofreader agent via Task tool:
Prompt: Review [file] through all 6 check categories.
Categories:
1. Structure — contribution in first 2 pages, standard sequence, transitions
2. Claims-Evidence — numbers match tables exactly, effect sizes with units
3. Identification Fidelity — paper matches strategy memo, estimand correct
4. Writing Quality — anti-hedging, notation consistency, terminology
5. Grammar & Polish — agreement, articles, tense, artifacts, informality
6. Compilation & LaTeX — overfull hbox, undefined refs/cites, XeLaTeX errors
Save report to quality_reports/[FILENAME_WITHOUT_EXT]_proofread_report.md
The academic-proofreader applies deductions (0-100 scale):
| Issue | Deduction |
|---|---|
| Numbers don't match tables | -25 |
| Paper doesn't compile | -20 |
| Broken citations | -15 |
| Broken references | -15 |
| Overfull hbox > 10pt | -10 per |
| Hedging language | -5 per (max -15) |
| Notation inconsistency | -5 |
| Overfull hbox 1-10pt | -1 per |
| Context | Scoring |
|---|---|
| Paper manuscript | Blocking — score gates commits and PRs |
| Talks | Advisory — reported but non-blocking |
Do NOT edit any source files. Only produce the report. Fixes are applied separately.
Sync the overleaf/ folder with the current content of paper/. Copies all LaTeX source, figures, tables, appendix, and bibliography. Puts the model section as overleaf/model.tex (top-level) for easy coauthor access. Run whenever paper/ changes and you want to push to Overleaf.
RA onboarding audit — explore all project folders and code, inspect data files directly, and produce a structured project-state document that enables a clean restart. Use at the start of a project hand-off or when picking up work from multiple prior contributors.
Full bibliography audit for an academic paper. Verifies every citation is (1) structurally correct in the .bib file, (2) actually cited in the paper, and (3) a real publication — author names, year, journal, and title verified via web search. Flags hallucinated or inaccurate references.
Design identification strategy by dispatching the causal-strategist agent (proposer) and identification-critic agent (critic). Produces strategy memo, pseudo-code, robustness plan, and falsification tests. Use when asked to "identify the effect", "design the strategy", or "write the strategy memo".
Show current context status and session health. Use to check how much context has been used, whether auto-compact is approaching, and what state will be preserved.
Show the current research pipeline status for the active project, or display the pipeline guide for a specific project type. Reads the research spec, research journal, and active plans to determine phase, scores, and next steps.