发现 Skills

Build apps with the Claude API or Anthropic SDK. TRIGGER when: code imports `anthropic`/`@anthropic-ai/sdk`/`claude_agent_sdk`, or user asks to use Claude API, Anthropic SDKs, or Agent SDK. DO NOT TRIGGER when: code imports `openai`/other AI SDK, general programming, or ML/data-science tasks.

Career goal mapping with skill gap analysis, actionable development plans, and milestone tracking. Use when planning career transitions, identifying skill gaps, setting professional development goals, or evaluating career options.

Interactive consulting case interview practice with structured frameworks, feedback mechanisms, and progressive difficulty. Use when preparing for management consulting interviews, case competitions, or business problem-solving exercises.

Verify statistics from raw data with methodology checking, significance testing, claim validation, and bias detection. Use when fact-checking statistical claims, validating research findings, or auditing data analysis.

Constructed voice for writing tasks. The free, skill-based path to 60-80% voice-matched output. Anchors the agent to a training-data author blend (from openwriter.io/voice-match) and progressively layers NEVER rules, presentation fingerprints, and curated examples as the user accumulates a writing corpus. Gets better over time. Use when: "/voice-anchor", "set up my voice", "set up my voice anchor", "anchor my voice", "voice match", "use my voice", "write in my voice" (when no Authors Voice profile is configured), "add to my voice profile", "voice profile status", "voice status". NOT for: users with a paid Authors Voice profile — use the voice-apply skill family for that. This is the free starter tier.

Extract content from Twitter/X articles, summarize key points, and save as structured Obsidian notes. Use when user provides a Twitter/X URL and wants to save it as a note, or mentions "save to Obsidian", "create a note from this tweet/article", or similar requests.

Scaffold Magento 2 backend modules, system.xml admin configs, widgets with parameters and templates, plugins/events/observers, transactional email with trigger setup, and Hyva-compatible .phtml templates with ViewModels. Use when user asks to \"create module\", \"scaffold module\", \"generate plugin\", \"add system config\", \"create widget\", \"setup email template\", \"create hyva template\", or any Magento 2 backend code generation. Do NOT use for frontend-only tasks, CSS/JS theming, or Magento 1.x.

Comprehensive guide for building production-grade AI-integrated backends with multi-provider support, intelligent fallback mechanisms, region configuration, prompt management with variables/tools, and session-based billing. Use when implementing AI features in Django/Python backends or designing LLM-powered API architectures with external data integration.

CLI for Google Workspace (Gmail, Calendar, Drive, Docs, Sheets, etc.) with account-based auth and JSON/text output

Review API/schema/interface changes for backward compatibility and consumer safety.

This skill should be used when creating distinctive, production-grade frontend interfaces with high design quality. It applies when the user asks to build web components, pages, or applications. Generates creative, polished code that avoids generic AI aesthetics.

Quickly locate files (images/screenshots) uploaded via ttyd in the Brainbase environment and attach them for viewing.

Create async background tasks (workflows) using SQS or Hatchet. Use when building queue jobs, background processing, or async tasks.

Write PRDs, specs, and project context optimized for coding assistants (Claude Code, Cursor, Copilot, Custom GPTs). Includes CLAUDE.md generation, session planning, and templates for creating documentation that tools can execute effectively.

Implement, configure, and customize Streamdown — a streaming-optimized React Markdown renderer with syntax highlighting, Mermaid diagrams, math rendering, and CJK support. Use when working with Streamdown setup, configuration, plugins, styling, security, or integration with AI streaming (e.g., Vercel AI SDK). Triggers on: (1) Installing or setting up Streamdown, (2) Configuring plugins (code, mermaid, math, cjk), (3) Styling or theming Streamdown output, (4) Integrating with AI chat/streaming, (5) Configuring security, link safety, or custom HTML tags, (6) Using carets, static mode, or custom components, (7) Troubleshooting Tailwind, Shiki, or Vite issues.

Persistent memory management for Claude Code via AutoMem. Use this skill when: - Starting a session (recall project context, decisions, patterns) - Making architectural decisions or library choices - Fixing bugs (store root cause and solution) - Learning user preferences or code style - Completing significant work (store summary) - Debugging issues (search for similar past problems)

Create a well-documented GitHub issue through interactive questions. Use when the user wants to create a new bug report, feature request, improvement, or any GitHub issue. Guides through gathering context, reading related code, and creating a properly labeled issue.

Quickly install and deploy vLLM, start serving with a simple LLM, and test OpenAI API.

Database migrations and Drizzle ORM guidelines for the vm0 project

Apply when implementing asynchronous payment methods (Boleto, Pix, bank redirects) or working with callback URLs in payment connector code. Covers undefined status response, callbackUrl notification, X-VTEX-signature validation, sync vs async handling, correct delayToCancel configuration for each async method, and redirect-based flows where inboundRequestsUrl does not support browser GET redirects (requires custom public routes).

Apply when connecting React components to Store Framework blocks and render-runtime behavior in VTEX IO. Covers interfaces.json, block registration, block composition, and how storefront components become configurable theme blocks. Use for block mapping, theme integration, or reviewing whether a React component is correctly exposed to Store Framework.

Build Retrieval-Augmented Generation (RAG) systems for LLM applications with vector databases and semantic search. Use when implementing knowledge-grounded AI, building document Q&A systems, or integrating LLMs with external knowledge bases.

Cross-model agent team orchestration with Claude + Codex + Gemini. Applies Elon's 5 Steps (Question → Delete → Simplify → Accelerate → Automate), Munger-style Inversion, and research-backed multi-agent principles. Healthcare-first with HIPAA compliance. Use when the user mentions "team", "agents", "swarm", "codex in the loop", or for complex multi-model collaboration.

Audit experiment integrity before claiming results. Uses cross-model review (GPT-5.4) to check for fake ground truth, score-normalization fraud, phantom results, and insufficient scope. Use when the user says 'audit experiment', 'check experiment integrity', 'audit results', 'verify experiment honesty', or after experiments complete before making claims.