Document Processing AI agent skills

2,011 skills in the archive. Read a skill’s instructions or open its original repository.

• Docs Components

  by @reactjs

  Comprehensive MDX component patterns (Note, Pitfall, DeepDive, Recipes, etc.) for all documentation types. Authoritative source for component usage, examples, and heading conventions.

• Docs Writer Reference

  by @reactjs

  Reference page structure, templates, and writing patterns for src/content/reference/. For components, see /docs-components. For code examples, see /docs-sandpack.

• React Expert

  by @reactjs

  Use when researching React APIs or concepts for documentation. Use when you need authoritative usage examples, caveats, warnings, or errors for a React feature.

• Docs Rsc Sandpack

  by @reactjs

  Use when adding interactive RSC (React Server Components) code examples to React docs using <SandpackRSC>, or when modifying the RSC sandpack infrastructure.

• Docs Writer Blog

  by @reactjs

  Use when writing or editing files in src/content/blog/. Provides blog post structure and conventions.

• Docs Voice

  by @reactjs

  Use when writing any React documentation. Provides voice, tone, and style rules for all doc types.

• Docs Writer Learn

  by @reactjs

  Use when writing or editing files in src/content/learn/. Provides Learn page structure and tone.

• Review Docs

  by @reactjs

  Use when reviewing React documentation for structure, components, and style compliance

• Docs Sandpack

  by @reactjs

  Use when adding interactive code examples to React docs.

• Rewardkit

  by @Arize-ai

  Write Harbor task verifiers using Reward Kit. Use when creating or editing a task's tests/ directory, adding grading criteria, setting up LLM/agent judges, or designing verifiers that produce a reward score.

• Mediaserver Operation

  by @jxxghp

  Use this skill when the user asks to inspect, diagnose, or directly operate a configured Emby, Jellyfin, Plex, ZSpace, UGREEN, TrimeMedia, or Navidrome server. It discovers provider capabilities on demand and supports libraries,…

• The Fool

  by @Jeffallan

  Use when challenging ideas, plans, decisions, or proposals using structured critical reasoning. Invoke to play devil's advocate, run a pre-mortem, red team, or audit evidence and assumptions.

• Datasets

  by @Arize-ai

  Understand what a Phoenix dataset is and reason well about its examples, outputs, splits, and how it feeds evaluators and experiments. Load this whenever a dataset is in view or the user asks what a dataset is, how splits work,…

• Laravel Specialist

  by @Jeffallan

  Build and configure Laravel 10+ applications, including creating Eloquent models and relationships, implementing Sanctum authentication, configuring Horizon queues, designing RESTful APIs with API resources, and building…

• Skill Creator

  by @spinabot

  Create, edit, improve, or audit AgentSkills. Use when creating a new skill from scratch or when asked to improve, review, audit, tidy up, or clean up an existing skill or SKILL.md file. Also use when editing or restructuring a…

• Huggingface Best

  by @huggingface

  Use when the user asks about finding the best, top, or recommended model for a task, wants to know what AI model to use, or wants to compare models by benchmark scores. Triggers on: "best model for X", "what model should I use…

• Hive.Pdf

  by @aden-hive

  Read, write, merge, split, rotate, watermark, encrypt, and OCR PDF files using Python (pypdf, pdfplumber, reportlab, pypdfium2) and command-line tools (poppler-utils, qpdf). Use when the user asks to extract text/tables/images…

• Hive.Worker Delegation

  by @aden-hive

  Concrete patterns for breaking colony work into parallel worker jobs via run_playbook — when fan-out helps, how to model the goal as a tracker table, write the worker skill, author the playbook, pilot, and let convergence…

• Dbs Content Risk Check

  by @dontbesilent2025

  面向创作者的内容发布风险检查。逐句检查自媒体、社交媒体和内容平台的标题、正文、图片文字、字幕、口播、评论、账号资料及视频画面，分别判断平台机器可能识别什么、内容本身存在什么实质问题，并给出具体位置和最小修改动作；需要明确视频语境边界时，额外生成真实准确的三行贴片小字。用户询问「检查敏感词」「发布前排雷」「这篇内容哪里可能违规」「这条小红书能不能发」「视频上放什么声明」时使用。保留强观点、情绪张力、个人风格和传播钩子。

• Dbs Goal

  by @dontbesilent2025

  提取已有约束，只追问影响执行或验收的信息，把模糊愿望和目标整理成可行动、可检查的交付物。用户要求澄清目标、检查任务是否说清或定义交付结果时使用。

• Dbs Report

  by @dontbesilent2025

  把多次 dbs-save 存档合并成可交付的 Markdown 报告。用户要求汇总诊断、整理报告或生成可分享材料时使用。

• Dbs Xhs Title

  by @dontbesilent2025

  从 75 个经过验证的小红书标题公式中选择并生成合适标题。用户要求起小红书标题、改标题或选择标题公式时使用。

• Cangjie Skill

  by @kangarooking

  Distill a book, long-video transcript, podcast, course, or interview into a coherent set of executable skills. Use when the user asks to "拆书" / "蒸馏一本书" / "把 XX 书做成 skill" / "把这个视频/播客/课程蒸馏成 skill" / "turn a book or video into…

• Quarter Clone

  by @ykdojo

  Clone the last quarter of the current conversation, discarding earlier context to reduce token usage while preserving recent work.

• Half Clone

  by @ykdojo

  Clone the later half of the current conversation, discarding earlier context to reduce token usage while preserving recent work.

• Inkos Short Story Analysis

  by @Narcooo

  商业短篇拆稿、情绪链、证据链和反转机制分析。Use to deconstruct a short story into transferable craft.

• Inkos

  by @Narcooo

  Story Creation and Translation AI Agent with Studio Chat, CLI, and TUI - use for long-form novels, short fiction, scripts, storyboards, interactive-film projects, open-world / branching play, fan fiction, spinoffs, style…

• Takedown

  by @anthropics

  Draft a DMCA takedown notice, triage one you received, or draft a §512(g) counter-notice. Use when asserting copyright through a §512(c)(3) takedown with the fair-use and perjury gates, when an incoming takedown needs triage…

• Ip Clause Review

  by @anthropics

  Review the IP clauses in an agreement — assignment, ownership, license grants, warranties, indemnities. Use when reviewing IP terms in employment, consulting, SOW, vendor, or licensing agreements, when asked to check the…

• Tabular Review

  by @anthropics

  Tabular review — one row per document, one column per data point, every cell cited to source. Built for M&A diligence ("review these 200 target contracts for change-of-control, assignment, and MAC clauses") but works for any…

• Cold Start Interview

  by @anthropics

  House cold-start interview (request list + prior memo), or --new-deal for deal-specific context. Modular: identifies which practice areas apply (M&A, Board & Secretary, Public Company, Entity Management), then asks targeted…

• Ai Inventory

  by @anthropics

  EU AI Act per-system inventory — track each AI system's role (provider, deployer, importer, distributor, authorized representative, product manufacturer) and risk tier (prohibited, high-risk, limited, minimal, GPAI,…

• Cold Start Interview

  by @anthropics

  Run the cold-start interview — learns your AI governance practice and writes `~/.claude/plugins/config/claude-for-legal/ai-governance-legal/CLAUDE.md` from your AI policy, a reference impact assessment, and key vendor AI…

• Cold Start Interview

  by @anthropics

  Run the cold-start interview to learn your IP practice and write your practice profile. Use on first install when the practice profile is missing or still contains placeholders, when re-onboarding with --redo, or when re-probing…

• Cold Start Interview

  by @anthropics

  Cold-start setup — learns your jurisdictional footprint and escalation rules from your handbook and termination memos. Asks which states and countries have employees, reads seed documents, and builds a jurisdiction-aware…

• Cease Desist

  by @anthropics

  Draft a cease-and-desist letter (send mode) or triage one you received (receive mode). Use when asserting your rights against an infringer with a demand letter calibrated to your enforcement posture, or when an incoming C&D…

• Batch Extraction

  by @xberg-io

  Use when extracting from many files at once with shared config, bounded parallelism, per-file overrides, and error recovery. Covers the `batch` command, `--file-configs`, `--max-concurrent`, and output layout.

• Extracting Tables

  by @xberg-io

  Use when extracting tabular data from PDFs, spreadsheets, or images. Covers layout-aware table detection, table model selection, output formats (markdown / JSON cells), and known limits.

• Extracting With Ocr

  by @xberg-io

  Use when extracting text from scanned PDFs, photographed pages, or images that have no embedded text layer. Covers OCR backends, language packs, force-OCR, and performance tuning.

• Ads Report

  by @AgriciDaniel

  Render Markdown, HTML, or PDF paid-advertising reports from a validated Claude Ads JSON run bundle. Use for ads report, client report, audit PDF, executive audience reporting, or exporting prior audit and plan results.

• Recall

  by @cursor

  Reconstruct your recent working context from your own chat history, live state, and the shared record (user reports, prior fixes, incidents), then hand back a tight current-state brief. Use for 'recall my work on X', 'catch me…

• Google Drive

  by @cursor

  Work with Google Drive through its MCP tools - search, read, create, organize, share, comment, and export files. Use when creating files in specific folders, moving or renaming, converting Markdown/CSV into Docs/Sheets, managing…

• Resume Modern

  by @nexu-io

  现代极简简历, A4 单页, 适合打印或导出 PDF

• Web Access

  by @eze-is

  所有联网操作必须通过此 skill 处理，包括：搜索、网页抓取、登录后操作、网络交互等。 触发场景：用户要求搜索信息、查看网页内容、访问需要登录的网站、操作网页界面、抓取社交媒体内容（小红书、微博、推特等）、读取动态渲染页面、以及任何需要真实浏览器环境的网络任务。

• Frame Macos Notification

  by @nexu-io

  拟真 macOS 通知 banner + app icon + 标题正文, 适合 video overlay / 产品发布预告

• Invoice

  by @nexu-io

  标准发票: 寄件/收件 + 明细 + 税 + 总额 + 付款指引

• Clawwork

  by @HKUDS

  ClawWork economic survival protocol — work/learn daily cycle

• Dashi Ppt

  by @chuspeeism

  制作 PPT、演示文稿、幻灯片、汇报材料时使用。Dashi PPT 基于预置视觉主题组合页面,生成可离线打开、可在浏览器编辑的 HTML 演示,支持导出 PPTX / PDF 文件。

• Context Compression

  by @vudovn

  Manage and compress conversation context in long sessions. Detect when context is growing large, summarize completed work phases, archive old findings while preserving key decisions. Prevents context degradation.

• Web Games

  by @vudovn

  Web browser game development principles. Framework selection, WebGPU, optimization, PWA.

• Deepsec Docs

  by @vercel-labs

  Use deepsec (an AI-powered vulnerability scanner) — one-shot initialization, resumable setup, project/model credentials, scans, generated or hand-authored matchers, and plugins. Activates when the user asks how to initialize,…

• Yao Ocr

  by @YaoApp

  OCR text recognition expert. ALWAYS invoke this skill when you need to extract text from images or PDFs — including invoices, receipts, ID cards, bank cards, business licenses, tables, handwritten documents, or any visual text…

• Company Analysis

  by @NomaDamas

  국내·해외 상장기업의 공개 공시와 실적발표를 대조해 3대 재무제표의 변화, 사업·경쟁구도, 주요 일정과 조회 시점 주가를 여섯 섹션의 한국어 채팅 분석으로 정리한다. 기업분석·실적발표 정리·수치 검증에 사용하며 매매 추천이나 PDF 보고서는 만들지 않는다.

• Unified Deliverables Flow

  by @HKUDS

  Generate spreadsheets, diagrams, and PDF reports in a phased workflow with explicit iteration budgets and error recovery

• Pdf Generation Troubleshooting

  by @HKUDS

  Systematic fallback workflow for PDF generation through pandoc, reportlab, and fpdf2 with installation verification

• Integrated Report Bundle

  by @HKUDS

  Generate spreadsheet, diagram, and PDF report as a cohesive deliverable set with iteration budgeting per component

• Openpyxl Sandbox Workaround

  by @HKUDS

  Use run_shell with inline Python as a fallback when execute_code_sandbox fails for openpyxl/spreadsheet operations

• Pdf Extract Progressive Tools

  by @HKUDS

  Progressive tool-chain PDF extraction with explicit read_file, run_shell, and execute_code_sandbox sequencing

• Pdf Page Verification Correction

  by @HKUDS

  Iterative workflow to verify PDF page counts and adjust layout parameters until requirements are met

• Pdf Extraction Fallback 7db3aa

  by @HKUDS

  Resilient multi-tier PDF extraction with sequential fallback strategies when initial reading fails

• Pandoc Unicode Workaround

  by @HKUDS

  Handle LaTeX Unicode errors in pandoc PDF generation by normalizing special characters to ASCII

• Pdf Gen Fallback 501bcc

  by @HKUDS

  Fallback pattern for PDF/document generation when execute_code_sandbox fails with opaque errors

• Pdf Extraction Fallbacks

  by @HKUDS

  Multi-fallback PDF/text extraction with early failure detection and sequential tool fallbacks

• Pdf Extraction Fallback

  by @HKUDS

  Multi-stage fallback strategy for PDF/document extraction using sequential tool alternatives

• Unified Deliverable Workflow

  by @HKUDS

  Generate spreadsheets, diagrams, and PDF reports with iteration budgeting and error recovery

• Pdf Extract Shell First

  by @HKUDS

  PDF text extraction with tool cascade prioritizing shell pdftotext before Python fallback

• Pandoc Pdf Error Recovery

  by @HKUDS

  Systematic approach to diagnose and recover from pandoc PDF conversion unknown errors

• Pdf Text Extraction Fallback 85d5ca

  by @HKUDS

  Fallback workflow for extracting text from PDFs when read_file returns binary data

• Pandoc Unicode Sanitize

  by @HKUDS

  Pre-process Markdown to replace non-ASCII characters before pandoc PDF conversion

• Pdf Text Extraction 9424c5

  by @HKUDS

  Extract text from PDF files using pdftotext when read_file returns binary data

• Pdf Verification Check 112b09

  by @HKUDS

  Verify generated PDF files using PyPDF2 to check page counts and integrity

• Pandoc Pdf Error Diagnosis

  by @HKUDS

  Systematic diagnostic workflow for resolving pandoc PDF conversion errors

• Pdf Read File Fallback

  by @HKUDS

  Extract text from PDFs using pdftotext when read_file returns binary data

• Pdf Text Extraction Fallback

  by @HKUDS

  Extract text from PDFs using pdftotext when read_file returns binary data

• Openpyxl Merged Cell Safe Write

  by @HKUDS

  Safe pattern for writing values to merged cells in openpyxl spreadsheets

• Pdf Engine Fallback

  by @HKUDS

  Retry PDF generation with alternative engines when pandoc fails

• Pandoc Pdf Error Resolution

  by @HKUDS

  Systematic debugging workflow for pandoc PDF conversion errors

• Pdf Text Extraction

  by @HKUDS

  Extract text from PDFs using shell tools when read_file fails

• Document Gen Resilient Multiformat

  by @HKUDS

  Resilient multi-format document generation with environment checks, auto-sanitization, and fallback engines

• Document Gen Resilient Workflow

  by @HKUDS

  Robust document generation with engine fallback chain, error diagnostics, and Python alternatives

• Delegated File Edit Verification

  by @HKUDS

  Verify delegated file-edit results directly in the target workspace before accepting success, and rerun with absolute paths if the delegate's report conflicts with reality.

• Irregular Excel Parsing

  by @HKUDS

  Handle Excel files with irregular headers, merged cells, and unknown header row positions using pattern-matching and index-based extraction.

• Document Gen Dual Backend

  by @HKUDS

  Document generation with direct pandoc/ReportLab execution (lightweight default) and optional shell_agent fallback for complex scenarios

• Direct Reportlab Pdf Generation

  by @HKUDS

  Generate complex multi-page PDFs by running reportlab Python code directly via run_shell when shell_agent fails on document creation

• Resilient Document Pipeline

  by @HKUDS

  Unified document generation with tool failure detection, domain knowledge fallback, progressive conversion, and Unicode safety

• Document Gen Unicode Safe

  by @HKUDS

  Unicode-safe fallback workflow for multi-format document generation with character sanitization and explicit error capture

• Deliverable Completion

  by @HKUDS

  Clarifies that file creation tasks are complete when the deliverable is successfully written—no submission step required

• Excel Heredoc Workaround

  by @HKUDS

  Create Excel files with openpyxl by falling back to run_shell with inline Python heredoc when execute_code_sandbox fails

• Locate Missing Artifacts

  by @HKUDS

  Recover generated files in sandboxed environments by searching from confirmed roots and copying to expected locations

• Doc Gen Unicode Diagnostic

  by @HKUDS

  Systematic document generation with unicode sanitization, engine fallback chain, and explicit error diagnosis

• Docx Parse Resilient

  by @HKUDS

  Extract text from DOCX files with shell-primary approach and Python zipfile fallback for maximum reliability

• Excel Heredoc Fallback

  by @HKUDS

  Create Excel files with openpyxl by falling back to shell-based Python heredoc when sandbox execution fails

• Docx Shell Workaround

  by @HKUDS

  Handle docx files using shell-based XML extraction and python-docx via run_shell when standard tools fail

• Diagnostic Stem Delivery

  by @HKUDS

  Audio production with diagnostic analysis, timecode parsing from documents, and verified export workflow

• Document Gen Unicode Safe

  by @HKUDS

  Unicode-safe fallback workflow for multi-format document generation with character sanitization

• Docx Dual Parse

  by @HKUDS

  Extract text from DOCX files using shell or Python zipfile, with environment-aware fallback

• Document Gen Fallback

  by @HKUDS

  Fallback workflow for multi-format document generation when shell_agent encounters errors

• Document Gen Resilient Workflow

  by @HKUDS

  Multi-engine document generation with cascading PDF fallbacks and robust Unicode handling

• Excel Unmerge Before Write

  by @HKUDS

  Unmerge merged cells in openpyxl worksheets before writing values to avoid AttributeError

• Document Gen Resilient

  by @HKUDS

  Multi-path document generation with tool checks, Unicode handling, and Python fallbacks