1,215 件 ・ 関連度順
概要と使いどころ
Convert PDF documents to clean structured Markdown for LLM context. Supports two modes: fast (PyMuPDF) and accurate (IBM Docling TableFormer AI). Features aggressive persistent caching, image extraction with metadata, table detection, and batch processing. Use when asked to convert PDFs, extract PDF content, parse documents, or prepare PDF data for AI/LLM consumption.
日本語の概要は準備中です。原文の説明を表示しています。
Evaluate, introduce, or refactor persistence abstractions when direct Eloquent is insufficient. Use for repository requests, complex aggregate reconstruction, or multiple persistence implementations; reject CRUD wrappers without a concrete benefit.
日本語の概要は準備中です。原文の説明を表示しています。
Periodic inbox scan that categorizes new emails by project/client, identifies action-required items, and generates prioritized summary with FYI/requires-response/requires-action/blocked-waiting classifications. Use for inbox overview, project-based email grouping, or action item extraction.
日本語の概要は準備中です。原文の説明を表示しています。
하나의 긴 메서드를 grouping(Reorder/Chunk)·comment로 정돈해 책임을 드러낸 뒤 Arlo Belshee 6단계 네이밍(완전정직 이름 → Extract Method → Intent Revealing → Domain Abstraction)을 하나의 연속 흐름으로 관통하는 self-contained 워크플로우. "이 긴 메서드 이름이 하는 일을 안 드러낸다", "메서드 이름부터 정직하게 만들어서 쪼개줘", "이름 주도로 이 메서드 리팩토링" 요청 시 사용. 단, 여러 파일에 흩어진 개별 이름 스멜의 배치 교체는 /naming-process, 클래스 분리·도메인 이동 같은 대규모 구조 변경은 /system-wide-refactoring이 적합. /intent-revealing-names로 호출.
日本語の概要は準備中です。原文の説明を表示しています。
Analyze code for primitive obsession and plan value object extractions around domain concepts, validation, and grouped primitive fields. Use when the user says `/value-objects`, asks for value object refactoring, or runs `/refactor:value-objects`.
日本語の概要は準備中です。原文の説明を表示しています。
Refactor duplicated code by extracting helpers, shared abstractions, or clearer reusable structure. Use when asked to apply DRY, remove duplication, consolidate repeated logic, or run `/refactor:dry`.
日本語の概要は準備中です。原文の説明を表示しています。
Automates browser interactions for web testing, form filling, screenshots, and data extraction. Use when the user needs to navigate websites, interact with web pages, fill forms, take screenshots, test web applications, or extract information from web pages.
日本語の概要は準備中です。原文の説明を表示しています。
Review whether a Clawix UI pattern, visual decision, copy change, or component extraction belongs in canon, debt, exception, or protected-surface scope.
日本語の概要は準備中です。原文の説明を表示しています。
Load for authentication or authorization changes involving BFF cookies/tokens, JWT validation, claims/user ID extraction, policies, handler access checks, impersonation, or 401/403 bugs; not for UI affordance gating alone.
日本語の概要は準備中です。原文の説明を表示しています。
Run an extremely strict maintainability review for abstraction quality, giant files, and spaghetti-condition growth. Use for a thermo-nuclear code quality review, thermonuclear review, deep code quality audit, or especially harsh maintainability review.
日本語の概要は準備中です。原文の説明を表示しています。
Router and protocol for reading and extracting web content. Decides first WHAT is needed (main text vs. structure vs. screenshot) and then WHICH tool available on the system delivers it. If nothing suitable is present, it recommends installing the web-scraper module.
日本語の概要は準備中です。原文の説明を表示しています。
Extrahiert aus einem Chatverlauf (aktuelle Session oder Transkript-Dateien) einen wiederverwendbaren Skill — oder verbessert einen sehr ähnlichen existierenden Skill, statt ein Duplikat zu erzeugen. Nutze diesen Skill bei „mach daraus einen Skill", „das sollten wir als Skill festhalten", „extrahiere Skills aus diesem/alten Chatverläufen", „diese Arbeitsweise wiederverwendbar machen", oder bei `/skill-extract`. Deckt auch Bulk-Läufe über viele alte Transkripte ab (mit Datenreduktion über Subagenten). Für wiederkehrende AUTOMATISIERUNGEN (Cron/Schedule/Loop) stattdessen den Schwester-Skill workflow-extract nutzen.
日本語の概要は準備中です。原文の説明を表示しています。
Baut aus einem Chatverlauf oder aus bestehenden Automatisierungs-Prompts (z. B. eines anderen Agenten-Systems) eine selbstlaufende, user-neutrale Workflow-Automatisierung: einen wiederkehrenden Prompt bzw. Automations-Skill für Cron/Schedule/Loop. Alias: automations-extractor. Nutze diesen Skill bei „mach daraus eine Automatisierung", „das soll regelmäßig/nächtlich laufen", „extrahiere Workflows aus diesen Chatverläufen/Automationen", „Automation aus dieser Session bauen", oder bei `/workflow-extract`. Ergänzt fehlende Automations-Bausteine (Rotations-Auswahl, Check-Registry, Idempotenz, Log-Hygiene, Freigabe-Gate, Eskalations-Handoff, Monitor-Meldedisziplin) systematisch. Enthält auch den Fleet-Audit-Modus: bestehende Automations-Flotten auf Silent-Failures, Redundanz, Drift und Lücken prüfen („prüfe meine Automatisierungen/Scheduled Tasks/Cron-Jobs"). Soll stattdessen ein abrufbarer Skill (Fähigkeit auf Zuruf) entstehen, den Schwester-Skill skill-extractor nutzen.
日本語の概要は準備中です。原文の説明を表示しています。
- End-to-end workflow to establish where and when a photo or video was captured and whether it is authentic — evidentiary handling, metadata extraction, reverse image search for provenance, visual geolocation, chronolocation from shadows, and manipulation… Use when asked to verify where an image was taken, confirm or refute a claimed location or date, or authenticate media before relying on it
日本語の概要は準備中です。原文の説明を表示しています。
Audit, grade, rewrite, and issue funny evidence-backed tickets for generic AI-slop patterns in prose, social posts, UI/design, and code. Use when asked to de-slop writing, humanize AI copy, grade a draft, review a landing page or generated interface, remove vague claims and repetitive rhetoric, inspect AI-written code for generic abstractions and happy-path-only logic, or ticket someone for a specific quality offense. Do not use to determine whether AI authored something.
日本語の概要は準備中です。原文の説明を表示しています。
Use when screenshots, websites, moodboards, competitors, or visual examples are provided and the task needs design DNA extraction, comparison, remixing, or translation into an original design direction.
日本語の概要は準備中です。原文の説明を表示しています。
Deep security audit for WordPress plugin/theme PHP code, covering issues beyond the basic sanitize/escape/nonce checklist — PHP object injection (unserialize), SSRF in remote requests, CSRF on state-changing GET handlers, mass assignment via $_POST loops, insecure file include / template injection, mail header injection, ZipSlip in archive extraction, type-juggling in auth comparisons, and TOCTOU race patterns in option/meta locks. Use after or alongside wp-security-audit when reviewing complex plugins, REST APIs, integrations that fetch remote URLs, file processors, or any code that handles uploads, archives, or self-rolled auth tokens.
日本語の概要は準備中です。原文の説明を表示しています。
Produces accessible color palettes and CSS design-token implementations for brands and websites. Use when the task asks for "color palette", "brand colors", "color scheme", "WCAG contrast", "dark mode colors", "design tokens", or "CSS custom properties for colors". Covers color theory, WCAG 2.2 contrast compliance, dark mode, AI palette extraction, and color psychology.
日本語の概要は準備中です。原文の説明を表示しています。
Perform quick web searches, local business lookups, and URL content extraction. Covers web_search for general queries, brave_local_search for location-based discovery, and run_crawl4ai_job for deep page crawling. Use when fact-checking, trend spotting, doing competitor analysis, looking up local businesses, extracting page content, or performing content research that doesn't need multi-step deep research.
日本語の概要は準備中です。原文の説明を表示しています。
Review code for quality, simplicity, and maintainability. Identifies unnecessary abstractions, duplicated logic, oversized functions, missing error handling, and naming issues — then fixes them automatically before presenting the result.
日本語の概要は準備中です。原文の説明を表示しています。
Generate professional documents — PDF, Word (.docx), Excel (.xlsx), and invoices — from natural language descriptions or structured data. Covers AI-powered and simple document creation, HTML-to-PDF conversion, PDF extraction/OCR, merging, watermarking, and data export. Use when you need to create campaign decks, reports, proposals, invoices, spreadsheets, or any shareable document — especially for Step 7 monthly presentations, campaign briefs, and analytics reports.
日本語の概要は準備中です。原文の説明を表示しています。
Create and process videos using AI generation (Runway, Pika, Replicate, Sora, Veo) and FFmpeg processing. MCP bridge provides frame extraction (extract_video_frames); the Design Stack media worker handles full FFmpeg processing (resize, trim, compress, GIF, format conversion). Covers social-media-optimized video output. Use when generating AI videos, extracting frames/thumbnails, transcoding videos, creating GIFs from clips, or preparing video for social platforms.
日本語の概要は準備中です。原文の説明を表示しています。
Remove signs of AI-generated code from a codebase while preserving behavior. Use when editing or reviewing code to make it read like a human engineer on this team wrote it. Works through a test-guarded detect-modify-verify loop: pin down the functional contract and edge cases first, write or run tests as a safety net, then rewrite AI tells (redundant comments, emoji, verbose names, reflexive try/except, defensive null-guards, over-decomposition, speculative abstraction, dead code, non-idiomatic constructs, hallucinated dependencies) and re-verify after every change. The tests decide whether a defensive block is slop or a real safeguard.
日本語の概要は準備中です。原文の説明を表示しています。
Automate web scraping and data extraction with Apify -- run Actors, manage datasets, create reusable tasks, and retrieve crawl results through the Composio Apify integration.
日本語の概要は準備中です。原文の説明を表示しています。