Documents skills

Browse reusable Agent Skills, each with a clear purpose and practical guidance.

z-excel-editor

Use this skill any time a spreadsheet file is the primary input or output. This means any task where the user wants to: open, read, edit, or fix an existing .xlsx, .xlsm, .csv, or .tsv file (e.g., adding columns, computing formulas, formatting, charting, cleaning messy data); create a new spreadsheet from scratch or from other data sources; or convert between tabular file formats. Trigger especially when the user references a spreadsheet file by name or path — even casually (like "the xlsx in my downloads") — and wants something done to it or produced from it. Also trigger for cleaning or restructuring messy tabular data files (malformed rows, misplaced headers, junk data) into proper spreadsheets. The deliverable must be a spreadsheet file. Do NOT trigger when the primary deliverable is a Word document, HTML report, standalone Python script, database pipeline, or Google Sheets API integration, even if tabular data is involved.

181 repo starsObserved in 1 repos
Documents

z-md-excel

Extract all Markdown tables from a .md file and export to Excel (.xlsx). Use this skill when the user wants to: convert Markdown tables to Excel, extract tables from .md files, export MD table data to spreadsheet, batch convert multiple tables from one Markdown file. Supports multiple tables, GFM alignment markers, inline Markdown stripping. Each table becomes a separate sheet in the output Excel file.

181 repo starsObserved in 1 repos
Documents

z-md-to-word

Convert local Markdown files into Word documents. Use this skill whenever the user provides a .md path and says 转成doc, 转成 Word, Markdown 转 Word, Markdown转doc, md 转 doc, md转docx, 导出 Word, 生成 doc, 生成 docx, or asks for a Word version of an article. This skill should produce a .docx by default, also produce a legacy .doc when useful, embed valid images, skip empty upload placeholders, keep Markdown lists readable, write outputs under output/doc, and verify the generated files before reporting.

181 repo starsObserved in 1 repos
Documents

z-smart-xparse

Parse documents into clean markdown or structured JSON via xparse-cli, with smart PDF auto-split and merge. Use this skill when the user provides a PDF, image, Office file, HTML, OFD, or other supported document and wants it read, converted, summarized, or prepared for downstream agent use. For PDF files, automatically detects large files (>5MB) or long documents (>100 pages) and splits them into manageable chunks, parses each chunk, then merges results into a single coherent output. Handles encrypted PDFs, page ranges, markdown/text output, and detailed structured extraction.

181 repo starsObserved in 1 repos
Documents

z-video-downloader

当用户给出视频链接、链接清单或 z-web-pack 的 04-media-inventory.md,并要求“下载视频”“视频下载”“帮我把这个视频下下来”“下载 YouTube 视频”“下载 B站/哔哩哔哩视频”“下载 m3u8/mp4 直链”“把视频保存到本地”“批量下载这些视频”“下载字幕”时必须使用。本 skill 支持单个、多个、文本清单和媒体清单输入,覆盖 YouTube、Bilibili、Vimeo、X/Twitter、TikTok、抖音、Instagram、Facebook 等 yt-dlp 平台及常见视频直链;支持断点续传、重试、字幕、封面和下载历史,保存到 Video/Downloads 并生成报告。

181 repo starsObserved in 1 repos
Documents

z-video-study-webpage-qwen

当用户要求“理解视频内容”“完整学习视频”“解读视频”“视频学习总结网页”“图文并茂学习网页”“用 Qwen 多模态分析视频”“用 qwen3.7-plus 看视频”“关键知识点匹配画面”“把视频做成学习网页”时必须使用。本 skill 会把本地 MP4 或已下载视频拆成音频转录、时间轴帧图、Qwen 多模态逐段分析,并用既有学习总结网页模板生成图文并茂 HTML,要求每个关键知识点绑定到正确视频画面。

181 repo starsObserved in 1 repos
Documents

ab-update-architecture

Refresh architecture and domain documentation after impactful changes. Use when code has drifted from the documented architecture.

180 repo starsObserved in 1 repos
Documents

audio-voice-recovery

Audio forensics and voice recovery guidelines for CSI-level audio analysis. This skill should be used when recovering voice from low-quality or low-volume audio, enhancing degraded recordings, performing forensic audio analysis, or transcribing difficult audio. Triggers on tasks involving audio enhancement, noise reduction, voice isolation, forensic authentication, or audio transcription.

180 repo starsObserved in 1 repos
Documents

dev-rfc

Create well-structured RFCs and technical proposals for software projects. Use this skill whenever the user wants to write an RFC, technical proposal, design doc, architecture doc, or system design overview. Also trigger when the user says things like "write an RFC", "I need to propose a new system", "create a technical proposal", "document the architecture", "write up the design", "I need a design doc", or "explain the system architecture in a doc". Even if they just say "RFC", "design doc", or "arch doc", use this skill. Covers both RFCs (proposing what to build) and architecture docs (documenting an existing codebase).

180 repo starsObserved in 1 repos
Documents

sync-architecture

Post-implementation documentation-sync detector. Spins up ONE read-only subagent on a completed task's diff to find everything the change introduced that the architecture docs don't yet know about — new endpoints, patterns, dependencies, domain terms, ADR-worthy decisions — routed to the exact doc each belongs in. Autonomous runs apply only append-only safe additions and defer domain/ADR reshapes; interactive runs present the proposed doc deltas to pick. Use after a task's missions are done (from create-task / start-task / start-roadmap) or standalone on a diff.

180 repo starsObserved in 1 repos
Documents