Skills

Inspect and explain conversations in the local Deep Agents Code SQLite session store.

Guide for creating effective skills that extend agent capabilities with specialized knowledge, workflows, or tool integrations.

Core agent-browser usage guide.

Searches arXiv for preprints and academic papers, retrieves abstracts, and filters by topic.

Audit an Anthropic Cookbook notebook based on a rubric.

Reference for the Claude API / Anthropic SDK — model ids, pricing, params, streaming, tool use, MCP, agents, caching, token counting, model migration.

Perform a structured code review of changes, checking for correctness, style, tests, and potential issues.

A.I.G Scanner — AI security scanning for infrastructure, AI tools / skills, AI Agents, and LLM jailbreak evaluation via Tencent Zhuque Lab AI-Infra-Guard.

Use to extend an existing agent project with memory, app integration, VPC, multi-agent, migration, model, browser, code interpreter, payments, or resource…

当用户要求 AI/Agent 安全评估、蓝军演习、AI 安全审查、提示词注入测试、MCP/Skill/插件/代码包审计、Agent 工具链滥用测试，或需要生成类似渗透测试报告的 Markdown/HTML 时，必须使用本 skill。本 skill 让 Agent 以授权蓝军视角成为 AI 安全专家，面向 AI…

Set up, repair, or migrate to Cloudflare Turnstile bot verification in an existing frontend and backend, including server-side Siteverify.

Presentation creation, editing, and analysis.

Use when investigating or improving WordPress performance (backend-only agent): profiling and measurement (WP-CLI profile/doctor, Server-Timing, Query Monitor…

Comprehensive spreadsheet creation, editing, and analysis with support for formulas, formatting, data analysis, and visualization.

Build or update a professional-grade design system in Figma from a codebase.

Security guidance and vulnerability review for codebases, APIs, services, CLI tools, libraries, and daemons.

Define, review, or update SECURITY_MODEL.md files that tell security review tools a repository's threat model, trust boundaries, invariants, reportable…

Scan agent skills for security issues.

Use for Vercel cost and performance optimization on deployed projects, especially Next.js, SvelteKit, Nuxt, and limited Astro apps.

Ensure a usable SageMaker execution role exists before deploying or training.

Create a SageMaker endpoint (real-time, real-time scale-to-zero, or async) with autoscaling, CloudWatch alarms, and tagging enabled by default.

Pick the right serving container for a SageMaker model deployment and find its current image URI.

Train or fine-tune sentence-transformers models across `SentenceTransformer` (bi-encoder, dense or static embedding model for retrieval, similarity…

Guide for creating high-quality MCP (Model Context Protocol) servers that enable LLMs to interact with external services through well-designed tools.