Comprehensive PDF manipulation toolkit for extracting text and tables, creating new PDFs, merging/splitting documents, handling forms, and OCR on scanned documents. Use when filling PDF forms, extracting data f...
Skills IA DevOps
Découvrez les skills DevOps, comparez leurs dépôts et consultez leurs instructions.
Catégories: DevOps
Explorer
image-processing
对图片进行处理,支持在图片中插入配文。 两种配文模式:底部边框式(像画框一样)和内部贴纸式(类似小红书效果)。 使用 PIL/Pillow 实现,支持中文和 Emoji。
image-search
对给定选题进行联网图片搜索,查找适合配图的素材。 使用 DuckDuckGo 图片搜索,支持尺寸、颜色、类型、版权过滤。 返回图片 URL、缩略图、来源等结构化信息。
deep-research
对给定选题进行联网深度研究,收集整理资料用于后续内容创作。 使用 DuckDuckGo 多后端搜索引擎,支持时间过滤、区域设置、多关键词扩展搜索。 输出结构化的 Markdown 资料汇总,包含来源引用。
ledger-registry
Reads /ledger/manifest.json, verifies per-ledger checksums, and returns the active ledger map. **Version:** 1.1 **Author:** Entropy Control Theory **License:** MIT **Based on:** Structure DNA v1.0 + PROFILE-G...
dependabot-pr-handler
Automated workflow for researching, validating, and safely merging Dependabot PRs in the Fusion Framework monorepo. Use when asked to review dependencies, handle or merge Dependabot PRs, validate dependency upd...
npm-research
Research npm packages for changelog, security advisories, and breaking changes. Provides structured analysis for dependency upgrades, vulnerability assessment, and impact evaluation.
vercel-react-best-practices
React and Next.js performance optimization guidelines from Vercel Engineering. This skill should be used when writing, reviewing, or refactoring React/Next.js code to ensure optimal performance patterns. Trigge...
prosemirror-notes
Guide for working with the ProseMirror-based notes editor. Use when editing notes feature code, fixing editor bugs, working with todos/checkboxes, wiki_links, decorations, or serialization.
book-writing-workspace
Set up a complete book writing workspace with AI agents, instructions, prompts, and scripts. Use when users want to create a new book/technical writing project with Markdown + Re:VIEW + PDF output workflow. Tri...
pnpm-dependency-analysis
Analyze package usage, resolved versions, direct/transitive dependencies, workspace interdependencies, and blast radius in pnpm monorepos. Perfect for Dependabot PR triage, upgrades, security reviews, and versi...
ba
Task tracker for LLM sessions. Use "$ba ready" to see available work, "$ba claim " to take ownership, "$ba finish " when done.
make-skill-template
Create new Agent Skills for GitHub Copilot from prompts or by duplicating this template. Use when asked to "create a skill", "make a new skill", "scaffold a skill", or when building specialized AI capabilities...
claude-agent-sdk-reference
Document for build custom AI agents with the Claude Agent SDK, include full SDK Reference and Example Codes.
claude-skills-reference
Document for build custom skill for claude code, with full Reference and Example Codes.
vector-mcp-retrieve
Vector Mcp Retrieve capabilities for A2A Agent.
vector-mcp-collection-management
Vector Mcp Collection Management capabilities for A2A Agent.
cabinet-meeting
Conduct a Cabinet meeting when User asks for "Cabinet meeting", "convene the Cabinet", "get perspectives from [agents]", or needs multi-agent consultation on complex decisions. Can be ad-hoc for specific decisi...
log-to-obsidian
Review a session or the git history for today and summarize this for our daily reporting
meeting-intelligence
Prepare for meetings by gathering context and creating comprehensive agendas
proofkit-fmodata
Type-safe FileMaker OData client with Drizzle-inspired ORM and TypeScript code generation. Use when working with FileMaker databases in TypeScript projects, querying FM data, defining typed schemas, generating...
add-to-inbox
Create a new note in the Obsidian inbox with user-specified content, including project context
task-orchestration
Orchestrate the complete development workflow for implementing sub-tasks from a task list. Use for end-to-end feature implementation with quality controls.
pull-request
Guidelines and tools for creating high-quality Pull Requests using the gh CLI. Includes bilingual templates (zh-TW/en) and validation scripts.
Le classement utilise les étoiles du dépôt GitHub indexé. Plusieurs skills peuvent partager ce nombre : ce n’est ni un nombre d’installations ni une note de qualité.