发现 Skills

View image or file attachments that you can't directly see. Use this skill when you receive a message with attachments listed as file paths and you need to understand their contents. Especially useful for text-only models that cannot process images natively.

Mitigate incidental code complexity when control flow is tangled, nesting is deep, names are hard to parse, or reasoning requires cross-file hops. Use when a review stalls on readability, you need an analysis-first refactor plan before edits, or you want essential-vs-incidental verdicts, ranked simplification steps, a small structural sketch, and a TRACE assessment (analysis-only; no edits).

Probe and test SDR hardware capabilities (RTL‑SDR, SDRplay, HackRF, etc.). Use when verifying device detection, discovering supported sample rates and gains, testing antenna ports, or troubleshooting SDR hardware issues.

Specialized skill to audit and transform NotebookLM notebooks into "Continuous Learning Platforms." It focuses on pruning outdated content, configuring a "Learning Mentor" persona, and setting up recursive learning tools like quizzes and flashcards.

This skill should be used when identifying, analyzing, and mitigating security risks in Artificial Intelligence systems using the CoSAI (Coalition for Secure AI) Risk Map framework. Use when assessing AI system security, conducting risk analysis for LLM applications, ML pipelines, model training/serving infrastructure, or generating compliance reports aligned with MITRE ATLAS, NIST AI RMF, OWASP Top 10 for LLM, and STRIDE frameworks. Supports both automated assessments and interactive exploration with 30+ query methods.

This skill should be used when working with Zsh shell configuration, autoload functions, fpath management, completions, function generation using established patterns, and comprehensive testing with isolated environments for performance optimization and plugin compatibility validation. Use for creating zsh functions, configuring fpath, testing config changes safely, optimizing shell startup, and Plugin Standard compliance.

Scans Algorand smart contracts for 11 common vulnerabilities including rekeying attacks, unchecked transaction fees, missing field validations, and access control issues. Use when auditing Algorand projects (TEAL/PyTeal).

Guides through Trail of Bits' 5-step secure development workflow. Runs Slither scans, checks special features (upgradeability/ERC conformance/token integration), generates visual security diagrams, helps document security properties for fuzzing/verification, and reviews manual security areas.

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.

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.

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