Claude Skills by tools-only

This document explains how to configure and use the SearXNG integration with Local Deep Research.

Creates comprehensive Technical Design Documents (TDD) following industry standards with mandatory sections, optional sections, and interactive gathering of missing information.

Expert guidance for Astral's uv - an extremely fast Python package and project manager. Use when working with Python projects, managing dependencies, creating scripts with PEP 723 metadata, installing tools, managing Python versions, or configuring package indexes. Covers project initialization, dependency management, virtual environments, tool installation, workspace configuration, CI/CD integration, and migration from pip/poetry.

Functions that provide the lowest level public interface to the database. Namely, we use Btree. To learn more about BTree: [https://en.wikipedia.org/wiki/B-tree](https://en.wikipedia.org/wiki/B-tree) We do not use Btree directly. Instead, we have another layer built on the top of Btree. Here is a brief explanation of this layer. An object called netnode is modeled on the top of Btree. Each netnode has a unique id: a 32-bit value (64-bit for ida64). Initially there is a trivial mapping of the ...

Registry related functions. IDA uses the registry to store global configuration options that must persist after IDA has been closed. On Windows, IDA uses the Windows registry directly. On Unix systems, the registry is stored in a file (typically ~/.idapro/ida.reg). The root key for accessing IDA settings in the registry is defined by ROOT_KEY_NAME.

File I/O functions for IDA. You should not use standard C file I/O functions in modules. Use functions from this header, pro.h and fpro.h instead. This file also declares a call_system() function.

Functions that deal with the string list. While the kernel keeps the string list, it does not update it. The string list is not used by the kernel because keeping it up-to-date would slow down IDA without any benefit. If the string list is not cleared using clear_strlist(), the list will be saved to the database and restored on the next startup. The users of this list should call build_strlist() if they need an up-to-date version.

Expert Shopify development assistant specializing in theme development, Liquid templating, app development, and Shopify APIs

Marketing attribution and performance analysis specialist. Use PROACTIVELY for campaign tracking, attribution modeling, conversion optimization, ROI analysis, and marketing mix modeling.

Database architecture and design specialist. Use PROACTIVELY for database design decisions, data modeling, scalability planning, microservices data patterns, and database technology selection.

Security infrastructure and compliance specialist. Use PROACTIVELY for security architecture, compliance frameworks, vulnerability management, security automation, and incident response.

Expert in modern architecture design patterns, NFR requirements, and creating comprehensive architectural diagrams and documentation

Expert Pimcore development assistant specializing in CMS, DAM, PIM, and E-Commerce solutions with Symfony integration

Our expert AI assistant for debugging code (O11y), optimizing vector search (RAG), and remediating security threats using live Elastic data.

Handles production incidents with urgency and precision. Use IMMEDIATELY when production issues occur. Coordinates debugging, implements fixes, and documents post-mortems.

Setup comprehensive CI/CD pipeline with automated testing, building, and deployment

Rollback deployment to previous version with safety checks, database considerations, and monitoring

Use PROACTIVELY to clean up merged branches, stale remotes, and organize branch structure

Create a new Git Flow feature branch from develop with proper naming and tracking

Complete and merge current Git Flow branch (feature/release/hotfix) with proper cleanup and tagging

Create optimized Next.js middleware with authentication, rate limiting, and routing logic

Generate optimized Vercel Edge Functions with geolocation, authentication, and data transformation

Model comprehensive market and customer responses with segment analysis, behavioral prediction, and optimization

Based on ICLR 2024 paper (arXiv 2306.11695) - A Simple and Effective Pruning Approach for Large Language Models

Comprehensive guide to different Mixture of Experts architectures and their design patterns.

Complete guide to MLflow Model Registry for versioning, lifecycle management, and collaboration.

NanoGPT's `train.py` is a self-contained training script with minimal dependencies.

Understand where to measure at each stage:

The `neon-api` Python SDK is a Pythonic wrapper around the Neon REST API. It provides methods for managing all Neon resources, including projects, branches, endpoints, roles, and databases. For core concepts (Organization, Project, Branch, Endpoint, etc.), see `what-is-neon.md`.

``` terraform/ ├── environments/ │ ├── dev/ │ │ ├── main.tf │ │ ├── variables.tf │ │ ├── outputs.tf │ │ ├── terraform.tfvars │ │ └── backend.tf │ ├── staging/ │ └── prod/ ├── modules/ │ ├── vpc/ │ │ ├── main.tf │ │ ├── variables.tf │ │ ├── outputs.tf │ │ └── README.md │ ├── eks/ │ ├── rds/ │ └── s3-bucket/ └── README.md ```

Comprehensive guide to backup strategies, disaster recovery planning, business continuity, and data protection for IT operations.

``` Tier 1: Alert Triage (L1 Analyst) ├─ Monitor SIEM dashboards and security alerts ├─ Perform initial triage and classification ├─ Escalate confirmed incidents to Tier 2 ├─ Document all activities in ticketing system └─ Response Time: 15 minutes for critical alerts

Define requirements for detecting text order violations between PDF and EPUB.

Define requirements for high-quality text extraction from PDF files.

OpenViking 是由字节跳动公司火山引擎 Viking 团队发起并维护的开源项目，致力于为 AI Agent 生态系统构建强大的上下文工程基础设施。作为新一代的上下文数据库，OpenViking 通过统一的数据抽象层、智能的语义解析引擎和高性能的混合检索系统，为各类 AI 应用提供坚实可靠的后端支撑。

```ruby class User < ApplicationRecord has_many :posts, dependent: :destroy has_many :comments, dependent: :destroy has_many :commented_posts, through: :comments, source: :post

John Carmack-level implementation review via RepoPrompt or Codex. Use when reviewing code changes, PRs, or implementations. Triggers on /flow-next:impl-review.

Interact with Google Chat - list spaces, send messages, read conversations, and manage DMs. Use when user asks to: send a message on Google Chat, read chat messages, list chat spaces, find a chat room, send a DM, or create a new chat space. Lightweight alternative to full Google Workspace MCP server with standalone OAuth authentication.

Interact with Gmail - search emails, read messages, send emails, create drafts, and manage labels. Use when user asks to: search email, read email, send email, create email draft, mark as read, archive email, star email, or manage Gmail labels. Lightweight alternative to full Google Workspace MCP server with standalone OAuth authentication.

You are an expert in **form optimization and friction reduction**. Your goal is to **maximize form completion while preserving data usefulness**. You do **not** blindly reduce fields. You do **not** optimize forms in isolation from their business purpose. You do **not** assume more data equals better leads. ---

Epic completion review - verifies all epic tasks implement spec requirements. Triggers on /flow-next:epic-review.

Generates and queries Salesforce metadata with 120-point scoring. Use when creating custom objects, fields, profiles, permission sets, validation rules, or querying org metadata structures via sf CLI.

Generate templated responses for common legal inquiries and identify when situations require individualized attention. Use when responding to routine legal questions — data subject requests, vendor inquiries, NDA requests, discovery holds — or when managing response templates.

Azure Resource Manager SDK for deploying and managing Weights & Biases ML experiment tracking instances via Azure Marketplace.

Azure Cosmos DB SDK for Java. NoSQL database operations with global distribution, multi-model support, and reactive patterns. Triggers: "CosmosClient java", "CosmosAsyncClient", "cosmos database java", "cosmosdb java", "document database java".

- Working on customer support tasks or workflows - Needing guidance, best practices, or checklists for customer support

Query and manage your Follow Up Boss real estate CRM — contacts, notes, tasks, deals.

Optimize any form that is NOT signup or account registration — including lead capture, contact, demo request, application, survey, quote, and checkout forms. Use when the goal is to increase form completion rate, reduce friction, or improve lead quality without breaking compliance or downstream workflows.

Azure Bot Service Management SDK for Python. Use for creating, managing, and configuring Azure Bot Service resources. Triggers: "azure-mgmt-botservice", "AzureBotService", "bot management", "conversational AI", "bot channels".

Use when about to ask the user a factual question, propose a solution, diagnose an error, or choose between approaches. Triggers on: 'Do you have X installed?', 'What version?', 'Is X configured?', 'We should...', 'The fix is...', 'Options: 1...', 'Based on my understanding...', 'I believe X supports...'. Before deciding anything, spin up parallel subagents to WebSearch for current docs, community solutions, framework best practices, and GitHub issues. Your memory is stale — verify everything.