Word Report Proofreading
Paste the following prompt into your AI chat to install this skill:
Install @user_6113fd9f/plan-proofread by following https://skillhub.cn/install/skillhub.md.
About this skill
Problem It Addresses
Before a formal Chinese report is submitted, the most damaging issues are often not simple typos. They include compliance wording, policy or law citations, text-table inconsistencies, broken table of contents or pagination, and untraceable data sources. In long documents, these issues are easy to miss and can affect whether a proposal, feasibility study, or board-level report passes review.
How the Skill Works
The skill turns proofreading into a structured workflow:
- Read .docx, .md, .txt, .pdf, or a folder, and build a chapter index for long documents;
- Review items by P0 to P3 priority, covering public-sector wording, policy citations, logical consistency, basic text errors, terminology, data and tables, formal style, completeness, and layout;
- Check tables against nearby paragraphs, including table titles, units, totals, percentages, and numeric mapping between text and tables;
- Verify data provenance for statistics, rankings, forecasts, or research claims, flagging vague attribution and missing sources;
- Output chapter-level issue lists and summarize results into must-fix, recommended, and to-confirm items.
Local scripts act as initial filters only: check_punctuation.py checks Chinese punctuation, check_text_table_consistency.py checks text-table numbers, check_toc_and_pagination.py checks TOC and pagination, and check_data_sources.py scans data attribution. Layout standards can follow the China International Engineering Consulting style, Bowei V2.6, or a user-defined template; when unspecified, it defaults to Bowei V2.6. The skill is best suited to enterprise development plans, feasibility reports, tender documents, and board-level reports, and is not intended for novels, poetry, or purely creative writing. Items that cannot be verified from the provided materials are marked as to-confirm rather than invented.
Use Cases
- Reviewing a feasibility study before tender submission to find policy citations, terminology, TOC, pagination, and text-table issues.
- Checking a board report for vague data attribution, bare statistics, and missing sources, then recommending source fixes or estimated labels.
- Proofreading an external state-owned enterprise document for official wording, job titles, institution names, and current policy references.
- Reviewing long strategic plans chapter by chapter while tracking full names, abbreviations, indicator definitions, and framework terms.
Best For
- Feasibility or tender writers: need to locate must-fix items, text-table mismatches, and missing data sources before submission.
- Consulting or planning advisors: need formal report review for wording, layout, terminology, and logical consistency.
- SOE or government office staff: need to check external documents for official wording, titles, and policy references.
- Report owners: need consolidated must-fix, recommended, and to-confirm lists to drive team edits.
Related Skills
Generate and edit .pptx decks with python-pptx, applying structured layouts, design rules, native charts, and visual QA to reduce template-like output.
Tencent Cloud Table Recognition V3 is an OCR skill for detecting and recognizing tables in images or PDFs, supporting various table types like linear and borderless tables, with Excel export.
The complete set of online document operation tools provided by Tencent Docs MCP, supporting creation, querying, and editing of smart docs, Excel, PPT, mind maps, and more.
Generates structured and consistently styled academic presentation PPTX files from paper PDFs for graduate seminars.