polish-skill

Purpose

This Skill polishes English academic text for journal submission through two modes: Quick-fix (default, intelligent single-pass) and Guided (fixed three-step: structure, logic, expression). For file input, it edits the original file in-place using the Edit tool and preserves originals as LaTeX comment annotations for traceability. For pasted text, polished output is presented directly in conversation. The Skill adapts to journal-specific style when a target journal is specified, detects translationese automatically, and avoids high-frequency AI vocabulary by loading anti-AI patterns proactively.

Trigger

Activates when the user asks to:

• Polish, improve, or refine English academic text
• 润色、改善、优化英文学术文本

Example invocations:

• "Polish this paragraph for CEUS" / "润色这段英文"
• "Guided polish my methods section" / "引导模式润色方法部分"
• "Quick fix my introduction" / "帮我快速润色引言"
• "Polish all sections in my paper"

Modes

Mode	Default	Behavior
direct (Quick-fix)	Yes	Intelligent single-pass polish, minimal interaction
guided		Three-step flow: structure, logic, expression with checklist at each step
batch		Quick-fix across multiple sections/files with same settings

Default mode: direct (Quick-fix). User says "polish this" and gets polished output.

Mode inference: "guided polish", "step by step", or "引导模式" switches to guided. "Polish all sections" or "batch" switches to batch.

References

Required (always loaded)

File	Purpose
references/expression-patterns.md	Academic expression patterns overview and module index

Leaf Hints (loaded when needed)

File	When to Load
references/expression-patterns/introduction-and-gap.md	Polishing introduction or background content
references/expression-patterns/methods-and-data.md	Polishing methods, data, or study area content
references/expression-patterns/results-and-discussion.md	Polishing results or discussion content
references/expression-patterns/conclusions-and-claims.md	Polishing conclusion content
references/expression-patterns/geography-domain.md	Content involves spatial, urban, or planning topics
references/anti-ai-patterns/vocabulary.md	Always -- loaded proactively for vocabulary screening
references/anti-ai-patterns/sentence-patterns.md	Always -- loaded proactively for sentence pattern screening
references/anti-ai-patterns/transitions-and-tone.md	Always -- loaded proactively for transition screening

Loading Rules

• Load expression patterns overview at the start; select the appropriate leaf based on section type.
• Load ALL three anti-AI pattern leaves proactively (vocabulary, sentence-patterns, transitions-and-tone).
• When a target journal is specified, also load references/journals/[journal].md.
• Load geography-domain.md when spatial, urban, or planning content is detected.
• If a reference file is missing, warn the user and proceed with reduced capability (except journal templates; see Fallbacks).

Ask Strategy

Before starting, ask about:

1. Target journal (if not specified in trigger) -- determines style loading
2. Which section this text belongs to (only if ambiguous from content or headers)
3. In guided mode only: confirm scope before starting

Rules:

• In direct (Quick-fix) mode, skip pre-questions when the user provides enough context.
• If the user specifies a journal with no template at references/journals/[journal].md, refuse and instruct the user to add a template.
• Never ask more than 3 questions before producing output.
• Use Structured Interaction when available; fall back to plain-text questions otherwise.

Workflow

Quick-fix (Direct) Mode

Step 1 -- Collect Context:

• Determine input type: file path (use Edit tool) or pasted text (output in conversation).
• Load references: expression pattern leaf by section type, all anti-AI pattern leaves, journal template if specified.
• Detect input characteristics: translationese presence, section type, text length for smart adaptation.

Step 2 -- Polish:

• Single intelligent pass covering expression, logic, and structure as needed based on text quality.
• Priority: expression issues first, then logic coherence, then structural adjustments.
• Apply journal style preferences from loaded template.
• Avoid anti-AI vocabulary; flag and rewrite AI-sounding phrases.
• Pay special attention to translationese if detected (literal structures, calques, excessive "of" constructions).
• For file input: use Edit tool; add % [Polish] Original: <original text> annotation before each modification.
• For pasted text: present polished output directly in conversation with key changes highlighted.

Step 3 -- Smart Adaptation:

• Short text (up to ~3 paragraphs): polish entirely in one pass.
• Long text (4+ paragraphs or multiple \section{} markers): split by section, process sequentially, maintain terminology consistency across sections.

Step 4 -- Summary:

• Generate concise report: change count, modification types (expression/logic/structure), notes.
• Include "Recommend running De-AI Skill for further detection check" when substantial rewrites were made.

Guided Mode

Step 1 -- Collect Context: Same as Quick-fix Step 1, plus confirm scope with user.

Steps 2-4 follow the same pattern: Analyze current text, present numbered checklist of problems found, user selects which to fix ("fix 1, 3" or "all"), apply selected fixes in batch using Edit tool with annotations, report changes. Re-read the file before each step to see the result of previous edits.

Step	Focus	Key Checks
2. Structure	Paragraph organization, topic sentences, section flow	Redundancy, ordering, paragraph purpose, section transitions
3. Logic	Argument coherence, claim support, terminology consistency	Argument chains, evidence links; cross-section coherence when multi-section input
4. Expression	Word choice, sentence clarity, tone, conciseness	Anti-AI patterns, translationese, academic register, hedging calibration

Step 5 -- Summary: Same as Quick-fix Step 4.

LaTeX Annotation Format

• Format: % [Polish] Original: <original text> on the line immediately before the replacement text.
• Multi-line originals: each line gets its own % [Polish] Original: prefix.
• Annotations are valid LaTeX comments -- the file still compiles with them present.
• Cleanup: after user confirms acceptance, remove all lines matching ^% \[Polish\] Original: pattern.
• If existing % [Polish] Original: annotations are found, clean them up before adding new ones.

Output Contract

Output	Format	Condition
polished_text	In-place edits (file) or conversation output (pasted text)	Always produced
change_annotations	LaTeX comments (% [Polish] Original:)	File input only
summary_report	Markdown in session (not in file)	Always produced

Edge Cases

Situation	Handling
Input too short (single sentence)	Polish but warn limited context for structural assessment
No section headers in input	Default to expression-focused polishing
Pasted text input	Output directly in conversation; no file operations
File input	Use Edit tool only; never Write (do not overwrite entire file)
Journal specified but no template	Refuse; instruct user to add template at references/journals/[journal].md
Very long input (10+ sections)	Process in batches; maintain cross-section terminology awareness
Existing % [Polish] Original: annotations	Clean up old annotations before adding new ones
Mixed LaTeX and text	Preserve all LaTeX commands; polish surrounding natural language only
Text with obvious translationese	Flag in summary; prioritize translationese fixes in expression pass

Fallbacks

Scenario	Fallback
Structured Interaction unavailable	Ask 1-3 plain-text questions covering highest-impact gaps
Expression pattern leaf missing	Use overview entrypoint for general patterns
Journal template missing for specified journal	Refuse -- instruct user to add the template first
Anti-AI patterns file missing	Proceed without; rely on Claude's vocabulary awareness
File is read-only or Edit fails	Present changes as a diff in conversation; user applies manually

---

Skill: polish-skill Conventions: references/skill-conventions.md