Document Processing AI Skills

Write correct Sarvam Document AI code (Sarvam Vision) — the doc_ai.parse() / .extract() / .classify() / .split() job lifecycle for OCR, table conversion, schema-based field extraction, document…

與 JLCPCB（及類似 PCB／PCBA 代工廠）的線上客服、工程師、業務窗口溝通。用於催辦審查或 DFM、就生產稿與貼裝確認向工廠提出技術澄清（比對與判讀交給 jlc-production-review）、算確認稿到期時間、訂單被取消後的追問、報價與優惠申請、付款後請對方負責到底、退款追問；先核對網站與信箱，再起草可獨立閱讀、含界線句的訊息，寄出與任何確認都等使用者同意。Use when…

Create comprehensive PRDs through conversational discovery. Use when users want to plan software projects, document requirements, or prepare specifications. Supports beginners to experienced PMs. Asks…

Word 文档处理 | Word Document Processing. 创建、读取、编辑 Word 文档 | Create, read, edit Word documents. 支持 .docx 格式、格式化、表格、图片 | Supports .docx format, formatting, tables, images. 触发词：Word、文档、docx.

Use Docling to understand the content of documents in any supported format — PDF (born-digital or scanned), DOCX, PPTX, XLSX, HTML, Markdown, AsciiDoc, CSV, images, audio, and XML — by converting them…

Build and query a local Markdown knowledge base ("vault"). TWO functions — (1) CONVERT raw files (PDF, Word/docx, PowerPoint/pptx, Excel/xlsx, csv/tsv, images, html, md/txt, json/yaml/code,…

Carry large projects through verifiable tasks, parallel work, and durable progress. Use when asked for Cascade, work in loops, or sustained project execution. Skip small edits.

Deep requirements interview skill using Pre-Question Cognitive Protocol (PQCP). Each question is preceded by synthesis, hypothesis generation, and self-challenge. Produces structured requirements…

Equips leaders to build flat, participative communication cultures that enable successful AI adoption by bridging technical and business teams, democratising data, and establishing feedback loops.…

使用 Chrome 或 computer use 操作知网页面，完成网页检索、文献详情与期刊目录浏览、题录摘要和引用信息提取，以及经用户确认的页面下载。用户明确要求浏览器操作或需核对真实网页时使用；cnki-mcp 文献检索调用由 cnki-search skill 负责。

Scaffold and architect custom Frappe apps including app structure, hooks, background jobs, service layers, and production hardening. Use when creating new apps, setting up app architecture, or…

Create and refine consulting reports, decision memos, and executive presentations, including storylines, exhibits, visual design, and artifact review. Use for PowerPoint decks, executive summaries,…

从 WebFetch/WebSearch 结果生成简洁、易读的 GitHub Trending 中文简报，与已有的 markdown 历史报告对比，并撰写每日或每周趋势总结。当用户要求分析 GitHub 热门趋势、对比今日与历史趋势、用通俗语言解释热门仓库，或为 Codex、Claude Code 等编码助手创建可重复的 GitHub 趋势报告时使用。

Create or revise a complete PaperBanana slide deck, including image slides and native editable PowerPoint objects. Preserve the user's selected presentation tool and existing deck mode.

Standardize, draft, revise, check, and package Chinese undergraduate thesis or graduation-design papers from school templates, task books, proposals, sample papers, source code, screenshots,…

Use when an AI agent or human needs to create, list, rename, or kill named tmux sessions with persistent metadata (repo, task, host) — turning anonymous tmux clutter into a labeled, queryable…

Distill parents into an AI Skill. Import chat history, photos, voice memos, generate Parent Memory + Persona, with continuous evolution. | 把父母蒸馏成 AI Skill，导入聊天记录、照片、语音，生成亲情记忆+人物性格，支持持续进化。

零基础友好的中文 CPA（注册会计师）2026 辅导老师，专为财会/法律基础薄弱的考生打造。WHENEVER 用户 在备考 CPA 并需要：讲解一个看不懂的知识点（如"什么是递延所得税""解释一下合并报表抵销""资本成本怎么算" "无形资产研发支出资本化是什么意思"）、拆解一道例题/真题并指出考点（这题考什么、怎么算、为什么选这个）、 或针对某个考点出练习题来巩固——就触发这个…

Track a working session in memoose and distill it into lessons at the end. Use at the start of a task (load standing rules and preferences), at each step of a multi-step task (declare your Position…

将一张或多张图片转换为经过严格质量校验的分层 PSD；自动准备运行环境，通过当前 Agent 执行转换。输出修复背景、独立透明视觉组件和可编辑 Photoshop 文字图层。仅支持图片输入，不用于 PDF 或 PPTX。

Create, restyle, or rebuild Chinese academic PowerPoint presentations from papers, theses, reports, figures, notes, templates, screenshots, or visual mockups. Use for presentation planning, Template…

Distill your partner into a living AI Skill. Powered by a 3-layer expert system: State Engine (S1-S6 relationship states), Policy Selector (7 intervention strategies), and Counterfactual Engine…

Use when needing to convert PDF pages to PNG images for preview, comparison, or image processing.

Generate an interactive, self-contained HTML course on any Claude documentation topic. Use this skill when the user wants to create an interactive course, tutorial, or deep-dive walkthrough about a…

企業名や企業URLから、事業構造、収益ドライバー、競争優位、成長余地、リスク、将来シナリオを一次情報と根拠ID付きで分析し、経営・戦略・投資判断に使える企業ディープダイブ・レポートを作る。企業分析、競合分析、アナリストレポート、会社調査、デューデリジェンス、事業モデル分析、KPIツリー、投資仮説、戦略資料、経営会議向け企業ブリーフを求められたときに使う。

DeckCraft is the ArtCraft open-source, clean-room PowerPoint-compatible presentation app for macOS (also Windows, Linux, FreeBSD and the web): slides, masters and layouts, shapes, 3-D, text, tables,…

润色和审阅中文计算机科学博士学位论文，去除 AI 痕迹、检查论文规范、生成 Markdown 审阅报告。支持 PDF、DOCX、LaTeX 长文档和直接粘贴文本。用户提到论文、学位论文、博士论文、毕业论文、润色、修改、审阅、摘要、章节等场景时使用，即使没有明确点名这个 skill。

Extract data from subcontractor bid PDFs and produce a comparison spreadsheet. Feeds into /bid-evaluator. Triggers: 'tabulate bids', 'bid comparison', 'compare bids', 'buyout analysis', 'bid tab'.

Prepare, package, resume, and analyze Amber/AmberTools molecular dynamics workflows for local or cluster execution. Use for Amber, AmberTools, pdb4amber, tleap, antechamber, parmchk2,…

Convert AI conversation transcripts (Claude Code, Codex CLI, ChatGPT JSONL; Cursor IDE SQLite) to readable Markdown. Use when the user wants to: (1) convert .jsonl conversation transcripts to .md, (2)…

Scores and strengthens startup pitch decks (pre-seed through Series A) against 35 investor-grade criteria grounded in Sequoia, DocSend, YC, a16z, and Carta data. Use when the user has shared a pitch…

Build a high-quality animated HTML lecture or workshop deck from a storyboard, in any theme. Use whenever someone asks for a slide deck, session deck, workshop slides, lecture screens, a run-of-show…

Use this skill when the user wants to upload a file to a Pipefy card or table-record attachment field. Covers local and downloaded file sources, plus a presigned-URL handshake for uploading files…

Add supplementary materials (PDF, PPTX, DOCX, images) to a lecture session. Converts to Markdown via MarkItDown and indexes into the course wiki — without triggering transcription or slide download.

Submit feedback about az-skills to Hivenet. Use when a skill, tool, doc, CLI, MCP, or API is broken, confusing, missing, outdated, or notably good; when an az-skills task fails after real effort or…

Use when given an engineering or mathematics homework PDF and asked to solve all or selected questions, answer sketch or plot problems, redraw assignment figures, or work from noisy OCR-extracted…

Use when the user asks to convert, export, or save an HTML slide deck as a PDF ("save the slides as PDF", "export the deck to PDF", "make a PDF of the presentation"). Works on decks built by the…

Reviews, rewrites and tailors a CV with Guido Penta's Galactic CV guide, and scores it against a job posting like a screener would. Use when the user shares a CV or asks to fix, tailor or rewrite it.

Use when uploading images or videos, labeling, organizing datasets, creating Roboflow projects (detection/segmentation/keypoint/classification), tags, splits, versions, or RoboQL search.

為既有的 reveal.js HTML 簡報加入效果：逐步出現（fragment）、Auto-Animate、3D 翻卡、GSAP 逐字動畫、Three.js、計時條、點圖放大、手機捲動模式，並控管效能、減少動態效果與離線。當使用者說「加動畫」「加特效」「逐步出現」「卡片翻面」「Auto-Animate」「GSAP」「讓簡報更生動」「有什麼效果可以加」時使用；簡報本體用…

Use when the task matches skill: new project scaffold and this skill's local workflow.

Domain navigator for accessibility, WCAG compliance, performance auditing, and code quality skills. Routes to the right skill for a11y remediation, WCAG 2.2 audits, Core Web Vitals, React quality, and…

Build professional academic economics slide decks in LaTeX/Beamer: turn a paper into a conference, seminar, or job-market talk; build discussant slides; polish or shorten an existing deck. Use when…

演讲锻造系统。把每一页 PPT 讲成一句话，把整套 deck 导成一场演出，而不是把要点堆成一面字墙。 专门用于从零设计有气场、有记忆点、一眼不像 AI 做的演示文稿、汇报 deck、路演 pitch、产品 keynote。 适用场景：创业路演、产品发布、年度复盘、方案提案、技术分享、培训课件、述职汇报、招商招生。 核心方法论：一页一句话 / 黄金三秒 / 节奏编排 / 视觉锤 / 反 AI…

生成或还原咨询风格（麦肯锡/BCG式）的高密度、全可编辑 PowerPoint。用户提到 PPT、slides、deck、汇报材料、提案，或要求把文档/研报/旧PPT/截图转成演示文稿时使用。支持三类输入、双轨渲染（默认全原生可编辑）、自适应确认门禁、12 种视觉风格与 10 个场景框架。

既存PPTXの書式・配置を抽出し、planとnative編集操作からPowerPointを生成・検査する。

Audit a web page for RGAA v4.1.2 Theme 13 – Consultation accessibility compliance. Checks that time limits are controllable, new windows are not opened without warning, downloadable documents are…

面向业务负责人、决策者与 owner 的极简汇报与卡单拍板规范。基于低成本沟通（reply-format-low-cost）与终点导向运行模型。严禁倒苦水铺垫过程，将开放性提问收敛为互斥选项的代价对齐。触发："对上汇报 / 给老板汇报 / 拍板项 / 需要确认 / 卡住了怎么说 / 项目进度汇报 / 极简汇报 / 低成本沟通 / reply-format"。

Execute a single deterministic Python script to harmonize units, create/update metadata, move files to output_data/, and clean up input_data/.

将图片幻灯片转成可编辑 PPTX，或修复已有可编辑 PPT 的漏字、底图残字和重复文字。新转换按原版式拆分；修复保留既有图片对象、裁切与排版，优先复用素材，逐页回装验证。支持共用透明标志。不用于从大纲新做 PPT。

生成、重构、审校或导出正式 PDF 报告时使用,包括日报周报、月报、经营分析、财务报告、预算报告、审计合规报告、专题分析、项目复盘报告。负责让报告可阅读、可打印、可归档、可追溯,排版规范、表格图表可信、不像 AI 模板。只管正式报告的版式与可信度,不用于 PPT 演示、HTML 网页或应用;也不用于拆分/合并/旋转/OCR/加密已有 PDF。