paper-polish-workflow
installsforks
How to install paper-polish-workflow?
lylll9436/paper-polish-workflow-skill/paper-polish-workflow
$npx -y skills add Lylll9436/Paper-Polish-Workflow-skill --skill paper-polish-workflowSystematic top-down workflow for polishing academic papers. Structure to logic to expression with user confirmation at each step.
SKILL.md
| 1 | ## Purpose |
| 2 | |
| 3 | This Skill provides a systematic, top-down workflow for polishing academic papers. It works from structure to logic to expression, with user confirmation at each decision point. Expression options are drawn from reference-driven academic patterns rather than ad hoc rewrites, ensuring professional and consistent output suitable for journal submission. |
| 4 | |
| 5 | ## Trigger |
| 6 | |
| 7 | **Activates when the user asks to:** |
| 8 | - Polish, revise, or improve an academic paper section by section |
| 9 | - 润色、精修、逐步改进学术论文 |
| 10 | |
| 11 | **Example invocations:** |
| 12 | - "Polish my paper section by section" / "润色论文" |
| 13 | - "Help me revise my introduction step by step" / "精修论文" |
| 14 | - "Guide me through polishing this draft" / "帮我逐步润色这篇论文" |
| 15 | |
| 16 | ## Modes |
| 17 | |
| 18 | | Mode | Default | Behavior | |
| 19 | |------|---------|----------| |
| 20 | | `interactive` | Yes | Full 4-step flow with user confirmation at each decision point | |
| 21 | | `guided` | | Multi-pass with confirmation at key checkpoints only | |
| 22 | | `direct` | | Single-pass polish using defaults; skip AskUserQuestion | |
| 23 | | `batch` | | Same operation applied across multiple sections sequentially | |
| 24 | |
| 25 | **Default mode:** `interactive` |
| 26 | |
| 27 | **Mode inference:** "quickly" or "just fix" switches to `direct`. "step by step" or "逐步" confirms `interactive` (already default). |
| 28 | |
| 29 | ## References |
| 30 | |
| 31 | ### Required (always loaded) |
| 32 | |
| 33 | | File | Purpose | |
| 34 | |------|---------| |
| 35 | | `references/expression-patterns.md` | Academic expression patterns overview and module index | |
| 36 | |
| 37 | ### Leaf Hints (loaded when needed) |
| 38 | |
| 39 | | File | When to Load | |
| 40 | |------|--------------| |
| 41 | | `references/expression-patterns/introduction-and-gap.md` | Polishing introduction or background content | |
| 42 | | `references/expression-patterns/methods-and-data.md` | Polishing methods, data, or study area content | |
| 43 | | `references/expression-patterns/results-and-discussion.md` | Polishing results or discussion content | |
| 44 | | `references/expression-patterns/conclusions-and-claims.md` | Polishing conclusion content | |
| 45 | | `references/expression-patterns/geography-domain.md` | Content involves spatial, urban, or planning topics | |
| 46 | | `references/anti-ai-patterns.md` | Polishing expression (Step 3) -- screen for AI-sounding phrases | |
| 47 | | `references/journals/ceus.md` | Target journal is CEUS | |
| 48 | |
| 49 | ### Loading Rules |
| 50 | |
| 51 | - Load expression patterns overview at start; select the appropriate leaf based on section type. |
| 52 | - Load anti-AI patterns when polishing expression (Step 3). |
| 53 | - Load journal template when target journal is specified. |
| 54 | - Load `geography-domain.md` when spatial, urban, or planning content is detected. |
| 55 | - If a reference file is missing, warn the user and proceed with reduced capability. |
| 56 | |
| 57 | ## Ask Strategy |
| 58 | |
| 59 | **Before starting, ask about:** |
| 60 | 1. Target journal (if not already known) |
| 61 | 2. Which section to work on |
| 62 | 3. Preferred mode (if ambiguous from trigger) |
| 63 | |
| 64 | **Rules:** |
| 65 | - Never ask more than 3 questions before producing initial output. |
| 66 | - In `direct` mode, skip pre-questions if the user provided enough context. |
| 67 | - In `batch` mode, skip per-item questions; apply settings from the first item. |
| 68 | - Use Structured Interaction when available; fall back to plain-text questions otherwise. |
| 69 | - See `skill-conventions.md > AskUserQuestion Enforcement` for full rules. |
| 70 | |
| 71 | ## Workflow |
| 72 | |
| 73 | ### Step 1: Collect Context |
| 74 | |
| 75 | - Determine input type (file path or pasted text). |
| 76 | - Load required references (expression-patterns overview). |
| 77 | - Identify target journal; load journal template if specified. |
| 78 | - Read input content using the Read tool; extract key numbers, claims, and data points. |
| 79 | - Locate example/reference papers if the user provides them (use Read tool for PDFs). |
| 80 | - In `interactive` or `guided` mode: confirm scope with the user before proceeding. |
| 81 | |
| 82 | ### Step 2: Structure & Logic Confirmation |
| 83 | |
| 84 | - Analyze section macro structure (e.g., Abstract = Background + Gap + Method + Results + Contribution). |
| 85 | - Present a structure table for user confirmation. |
| 86 | - Break content into sentences; assign a logic function to each. |
| 87 | - Present the logic chain for user confirmation. |
| 88 | - Checkpoint: user confirms structure and logic before expression work begins. |
| 89 | - In `direct` mode: run structure and logic analysis internally, proceed to Step 3 automatically. |
| 90 | |
| 91 | ### Step 3: Expression Polish & Consistency |
| 92 | |
| 93 | - Load the section-appropriate expression pattern leaf and anti-AI patterns. |
| 94 | - For each sentence with expression issues, present 2-3 options via AskUserQuestion (`interactive` mode) or apply the best option automatically (`direct` mode). |
| 95 | |
| 96 | ``` |
| 97 | AskUserQuestion({ |
| 98 | question: "Which expression do you prefer for [sentence function]?", |
| 99 | options: [ |
| 100 | { label: "[Expression A]", description: "[full sentence with expression A]" }, |
| 101 | { label: "[Expression B]", description: "[full sentence with expression B]" }, |
| 102 | { label: "[Expression C]", description: "[full sentence with expression C]" } |
| 103 | ] |
| 104 | }) |
| 105 | ``` |
| 106 | |
| 107 | - **Reference paper consultation:** when the user q |
People who liked this also viewed
6 picksType
- grill-with-docsA relentless interview to sharpen a plan or design, which also creates docs (ADR's and glossary) as we go.SkillsJul 2026
- lark-minutes飞书妙记：搜索妙记、查看妙记基础信息、下载/上传音视频、读取或编辑妙记的产物内容、改标题、替换说话人/关键词、申请妙记查看/编辑权限。当给出minute_token、本地音视频文件，要查/改/转妙记产物，或用户明确要主动申请妙记权限时使用；本地音视频转纪要/逐字稿优先走本 skill，不要用 ffmpeg/whisper 本地转写。不负责：获取会议关联妙记，或仅按自然语言标题定位纪要SkillsJul 2026
- lark-markdown飞书 Markdown：查看、创建、上传、编辑和比较 Markdown 文件。当用户需要创建或编辑 Markdown 文件、读取、修改、局部 patch 或比较差异时使用。不负责将 Markdown 导入为飞书在线文档，也不负责文件搜索、权限、评论、移动、删除等云空间管理操作。SkillsJul 2026
- docxUse this skill whenever the user wants to create, read, edit, or manipulate Word documents (.docx files) or Word templates (.dotx files). Triggers include: any mention of 'Word doc', 'word document', SkillsJul 2026
- edit-articleSkills for Real Engineers. Straight from my .agents directory.SkillsJul 2026
- lark-note飞书会议纪要（Note）直查：已知 note_id 时查询纪要详情、展示类型、关联文档 token，并读取 unified 原始逐字记录。当用户已持有 note_id，或从文档显式 vc-node-id 获得 note_id 时使用。不负责会议/日程/妙记定位、文档标题搜索或 Docx 正文读取。SkillsJul 2026
