Menü
Revise an existing section for style, clarity, and correctness
Mit Codex oder Claude installieren Kopieren Sie diesen Prompt, fügen Sie ihn in Codex, Claude oder einen anderen Assistant ein und lassen Sie die Skill-Seite prüfen und installieren.
Basierend auf der SOC-Berufsklassifikation
| name | edit-section |
| description | Revise an existing section for style, clarity, and correctness |
| user_invocable | true |
When this skill is invoked, follow this structured workflow to revise an existing section of the paper.
The user specifies which section to edit (file path or section key) and what kind of revision (style cleanup, content revision, restructuring, or specific feedback to address).
main.tex.claude/rules/academic-writing.md for banned words, terminology, and style rules.claude/rules/banned-words.md for the full banned-word listguidance/paper-context.md for correct claims, numbers, and paper framing (if it exists)Run through each check category:
A. Banned Words (read banned-words.md for the full current list; key examples: delve, crucial, comprehensive, utilize; AI markers: underscores, showcasing, pivotal, intricate, encompass, aligns with; previewing: "as we show below", "Recall from"; filler: of course, obviously, in other words)
B. Opening Quality -- Does sentence 1 state a concrete finding?
C. Voice and Tense -- Flag passive constructions
D. Quantitative Precision -- Numbers instead of adjectives; cross-check against paper-context.md if available
E. Terminology -- If guidance/paper-context.md defines a terminology table, check compliance. Otherwise flag any terms used inconsistently within the section.
F. Self-Praise -- Flag "striking", "important contribution", "novel"
G. Concision -- Cut repeated ideas, "in other words", sentences that don't earn their place
H. Em-Dashes -- No --- in prose (rewrite with commas, semicolons, colons, or parentheses)
I. Structural AI Tells -- Check for patterns from academic-writing.md: naked "this" without noun, "Importantly,"/"Notably,"/"Specifically," as sentence openers, "Together, these results..." openers (max 1/paper), "In this section, we..." throat-clearing, "This finding" repetition (max 1/paper), "Overall," as paragraph opener. Check soft-ban counts: "highlights" (max 2/paper), "insights" (max 1/paper)
J. Hedge Words -- Delete or quantify: somewhat, quite, very (intensifier), rather (hedge), arguably, perhaps. Replace with magnitudes. (See academic-writing.md "Kill Hedge Words")
K. Nominalizations -- Prefer verbs: "conduct an analysis" → "analyze", "provide evidence" → "show". (See academic-writing.md "Prefer Verbs over Nominalizations")
Read the relevant exemplar from .claude/exemplars/ to check structural patterns (if exemplars exist for this project).
Make targeted edits:
Preserve: Do not change content that is correct and well-written. Minimize diff size.
Check all \cite{} keys against the .bib file. For new citations, verify via Perplexity (see .claude/rules/latex-citations.md if it exists).
Show the user:
[HUMAN EDIT REQUIRED] flags for claims that could not be verifiedCreate a new empirical research project: generates projects/<name>/ with latex, code, scripts, results, literature, and guidance subfolders plus README.md and project-level CLAUDE.md.
Publication-ready figure conventions for empirical finance and economics. Covers matplotlib styling, color palettes, export settings, and common figure types (time series, decile bars, coefficient plots, event studies). Auto-apply when creating any figure, plot, or visualization.
Agent-driven cold-start onboarding. Use the repo shell entrypoint to find or install Python 3.11+, then run the shared bootstrap audit/plan/apply flow and configure WRDS only if the user has it.
Create and compile Beamer presentations following the Rhetoric of Decks philosophy. Use when making seminar or conference slides.
Compile LaTeX to PDF using pdflatex + bibtex cycle
Creates new Claude Code skills, auto-apply skills, or auto-trigger rules, or audits existing ones for quality and effectiveness.