Total 50,315 skills, Document Processing has 738 skills
Showing 12 of 738 skills
Use when normalizing BibTeX, RIS, CSL JSON, citation keys, DOI/arXiv/PMID metadata, references, unused citations, missing citations, or bibliography quality for papers and SOTA work.
Use when the user has an SRT (or transcript text) in one language and wants it translated to another, with punctuation-bounded re-segmentation so cues end at real sentence breaks. Simplified Chinese (zh-CN) and English (en) are first-class targets; other targets follow the same rules. Outputs a target-language SRT or bilingual SRT — no audio, no burn-in. Triggers — "翻译字幕", "翻成中文", "translate this SRT", "中英双语字幕", "把这个 SRT 翻译成 X", "bilingual subtitles".
Archive completed changes and merge specification differences into permanent documents. Used when changes have been deployed, are ready for archiving, or when specifications need to be updated after implementation. Trigger words include "openspec archive", "archive", "archive proposal", "merge specifications", "complete proposal", "update documents", "finalize specifications", "mark as completed".
This skill should be used when the user asks to "update my README", "refresh the README", "README is outdated", "sync README with the codebase", "improve my README", "keep README up to date", "fix the README", "my README is stale", "update the readme file", "README needs updating", "update readme from git history", or "readme is out of date".
Analyze tender and procurement documents (PDF, Word, images) to extract qualification requirements, scoring criteria, key deadlines, prohibited clauses, and submission checklists. Uses SoMark for accurate parsing of complex government and enterprise procurement documents. Requires SoMark API Key (SOMARK_API_KEY).
Use this skill to translate a classifier's in-place verdict into a precise, page-by-page work plan for the docs-sync panel. Activate after docs-impact-classifier returns verdict in_place; reads the candidate page list, fetches the actual page contents, narrows scope to specific sections within each page, and emits the per-page task brief the panel fans out against.
Enables AI-powered parsing and key information extraction from high-frequency documents including invoices, orders, receipts, long texts, and common Chinese identity & credential documents. Supports reusable custom templates for non-standard business files. Features batch concurrent processing to automate document workflows for finance, administration, HR data entry and other departments.
Review and annotate documents/contracts — output annotated docx with comments or tracked changes. Core: contract review (risk clauses, rights imbalance, vague wording, missing clauses); also general document review (grammar, logic, formatting). 批阅文档/合同 — 审阅任意文档并以批注或修订模式输出带标注的 docx。 核心场景：合同/协议审查（风险条款、权利义务、模糊表述、缺失条款）， 也支持通用文档审阅（语法、逻辑、格式）。 Trigger when: user asks to "审阅", "批阅", "批注", "review", "审查合同", "review contract", "review agreement", "annotate document", "check contract", "合同审查", "文档批注", or provides a document (.docx) for review.
Use when processing lecture slide PDFs into Obsidian notes, converting slide decks to a knowledge graph, or preparing study material from course PDFs.
MDV — Markdown superset for documents, dashboards, and slides with embedded charts, KPI stats, and data visualizations exported to HTML or PDF.
Api2pdf integration. Manage data, records, and automate workflows. Use when the user wants to interact with Api2pdf data.
Review experimental results, plots, tables, and figures before they are shown in a meeting, paper, report, or presentation. Use this skill whenever the user wants to present results, check a figure, interpret experiment plots, prepare result slides, validate captions, audit axes/legends/error bars, or make sure results are connected to hypotheses and experimental setup.