发现 Skills

Structured literature review planning with systematic methodology, source evaluation, and synthesis frameworks. Use when planning academic literature reviews, research surveys, systematic reviews, or scoping reviews.

Comprehensive PDF manipulation toolkit for extracting text and tables, creating new PDFs, merging/splitting documents, and handling forms. When Claude needs to fill in a PDF form or programmatically process, generate, or analyze PDF documents at scale.

Podcast production workflow including episode planning, show notes creation, transcript editing, guest management, and distribution strategy. Use when launching podcasts, planning episodes, or optimizing podcast workflows.

Turn research findings into presentation outlines with narrative arc, data visualization suggestions, audience adaptation, and slide design guidance. Use when creating research presentations, conference talks, or findings briefings.

Enterprise risk management expertise for ERM frameworks, risk assessment, business continuity, insurance strategy, third-party risk, and reputational risk. Use when assessing risks, building continuity plans, or managing organizational risk exposure.

Visual QA via browser MCP tools (Playwright/browser-use). Use when reviewing UI, checking for visual bugs, or inspecting a web interface after frontend changes.

Attack and enumerate Active Directory environments using Kerberos attacks (Kerberoasting, ASREPRoasting), credential dumping (DCSync, Mimikatz), lateral movement (PtH, PtT), and BloodHound analysis. Use when pentesting Windows domains or exploiting AD misconfigurations.

Browser automation in Cursor IDE using MCP protocol server `cursor-ide-browser`. Use when (1) Automating web interactions in Cursor IDE, (2) Navigating web pages, (3) Clicking buttons or links, (4) Filling forms or input fields, (5) Taking screenshots or capturing page snapshots, (6) Debugging web pages by checking console messages or network requests, (7) Extracting information from web pages, (8) Testing web applications, (9) Interacting with web-based documentation or tools, (10) Any task requiring programmatic browser control within Cursor IDE

Source royalty-free images and videos from the Pexels API for design, placeholders, or content. Supports search, curated/popular content, collections, multiple resolutions, and always creates detailed sidecar metadata files.

A tiny skill used by the skillloadmode example.

Sync Markdown projects to Confluence using the markdown_confluence tool. Use it to publish, crawl, and manage Confluence pages from local Markdown files.

Frontend integration for the NextDNS API using Nuxt 4, Next.js, Astro, SvelteKit, or React Router v7. This skill covers secure API key proxying via the BFF pattern, profile management UI, real-time SSE log streaming, analytics chart data preparation, and error handling. Use this skill when building a custom NextDNS dashboard or management interface with any popular full-stack framework. Triggers on tasks involving Nuxt, Vue, Next.js, Astro, React, SvelteKit, Svelte, React Router, Remix, NextDNS dashboard, DNS analytics UI, or log streaming.

Runs a budget-aware, agent-assisted engineering health audit for instruction/config drift, hooks/MCP, verifier surfaces, and AI maintainability. Use when users ask “check claude / check codex / check pi / config check / health” or report agents ignoring instructions, missing validation, or code becoming hard to maintain. Not intended for debugging code or reviewing PRs.

Claude Code command-line interface for AI-assisted development with session management, model selection, and tool control

Transfer data and files using URLs, supporting HTTP, HTTPS, and other protocols

JSON processor for filtering, transforming, and extracting data

Enhance user prompts by analyzing project context (code structure, dependencies, conventions, existing patterns). Use when users provide brief development requests that would benefit from project-specific context to generate more accurate, contextually-aware prompts.

Use when about to claim work is complete, fixed, or passing, before committing or creating PRs - requires running verification commands and confirming output before making any success claims; evidence before assertions always

Implement Terraform Resources and Data Sources in `internal/provider` with comprehensive testing.

Analyzes specifications and feature descriptions for user flow completeness and gap identification. Use when a spec, plan, or feature description needs flow analysis, edge case discovery, or requirements validation.

Systematic root cause analysis for errors, bugs, and unexpected behaviors using the 5 Whys methodology. Use when a user reports errors, build failures, test failures, performance issues, integration problems, or any 'it's not working' scenarios.

Generate detailed implementation plans for complex tasks. Creates comprehensive strategic plans in Markdown format with objectives, step-by-step implementation tasks using checkbox format, verification criteria, risk assessments, and alternative approaches. All plans MUST be validated using the included validation script. Use when users need thorough analysis and structured planning before implementation, when breaking down complex features into actionable steps, or when they explicitly ask for a plan, roadmap, or strategy. Strictly planning-focused with no code modifications.

開発ワークフロー統合ガイド（7 Skills統合版）。Git運用・CI/CD管理・Design-to-Code・Claude Code活用・ワークフロー検証・Worktree管理・CI/CD認証を統合。§ 1（Gitコミット）→ § 2（CI/CD）→ § 3（Design-to-Code）→ § 4（Claude Code）→ § 5（ワークフロー検証）→ § 6（Worktree管理）→ § 7（CI/CD認証）の7セクションで、開発プロセス全体を参照可能

PDF読み込みの正しい方法。ReadツールでPDFを直接読むとエラーになるため、必ずPythonのpdfplumberライブラリを使用。インストール方法、基本的な使い方、ページ単位でのテキスト抽出を含む。PDF読み込み時に使用。