发现 Skills

Use when developing, reviewing, or explaining Rill projects and project files (connectors, models, metrics views, explores, canvases, themes, rill.yaml, sources, alerts, reports, APIs). Apply runtime workflow guidance and project-file reference docs, and cite rule files and source URLs.

MongoDB Atlas Vector Search and AI integration. Use when creating vector indexes, writing $vectorSearch queries, building RAG applications, implementing hybrid search, or storing AI agent memory. Triggers on "vector search", "vector index", "$vectorSearch", "embedding", "semantic search", "RAG", "retrieval augmented generation", "numCandidates", "similarity search", "cosine similarity", "hybrid search", "$rankFusion", "$scoreFusion", "rerank", "two-stage retrieval", "AI agent", "LLM memory", "quantization", "multi-tenant", "Search Nodes", "explain vectorsearch", "HNSW", "automated embedding", "autoEmbed", "Voyage AI", "voyage-4", "voyage-4-large", "voyage-code-3", "input_type", "asymmetric retrieval", "lexical prefilter", "fuzzy search vector", "phrase filter".

Use when optimizing ESP32 speed, binary size, RAM usage, power consumption, deep sleep, light sleep, modem sleep, DFS frequency scaling, or measuring current draw.

Master defensive Bash programming techniques for production-grade scripts. Use when writing robust shell scripts, CI/CD pipelines, or system utilities requiring fault tolerance and safety.

Master guide for using Claude Code effectively. Includes configuration templates, prompting strategies \"Thinking\" keywords, debugging techniques, and best practices for interacting wit...

Windows 11 system management

You are an expert error analysis specialist with deep expertise in debugging distributed systems, analyzing production incidents, and implementing comprehensive observability solutions.

You are an error tracking and observability expert specializing in implementing comprehensive error monitoring solutions. Set up error tracking systems, configure alerts, implement structured logging,

You are an expert prompt engineer specializing in crafting effective prompts for LLMs through advanced techniques including constitutional AI, chain-of-thought reasoning, and model-specific optimizati

Create custom external web service APIs for Moodle LMS. Use when implementing web services for course management, user tracking, quiz operations, or custom plugin functionality. Covers parameter va...

You are a monitoring and observability expert specializing in implementing comprehensive monitoring solutions. Set up metrics collection, distributed tracing, log aggregation, and create insightful da

Automate Zoho CRM tasks via Rube MCP (Composio): create/update records, search contacts, manage leads, and convert leads. Always call RUBE_SEARCH_TOOLS first to discover current tool schemas.

Refresh the Swift skill's reference guides when Swift, Swift Package Manager, or SwiftLint guidance changes. Use when preparing a release, after major language or tooling updates, or when the references feel stale.

Handles environment setup and high-performance incremental building for rsyslog.

Naga configuration-management skill. Used to view and modify Naga system settings, add MCP tool services, import custom skills, and search available MCP tools. Use this skill when a user requests modifying settings or adding tools or skills.

真实性验证技能。分析用户提供的信息、消息、图片或内容，判断其真实性和可信度，识别虚假信息、AI生成内容或伪造内容。

Follows a strict Test-Driven Development (TDD) workflow with four phases: triage, prepare, execute, and finalize. Use for bug fixes, feature implementation, refactoring, and maintenance tasks.

John von Neumann’s thinking framework and mode of expression. Based on a deep distillation of 2,100+ lines of research material across six dimensions (writings, conversations, expression DNA, external evaluations, decision records, timeline), it extracts five core mental models, eight decision heuristics, and a complete expression DNA. Purpose: act as a thinking advisor that analyzes problems, reviews decisions, and provides feedback from von Neumann’s perspective. Trigger phrases: use when the user mentions “from von Neumann’s perspective,” “how would von Neumann see this,” “von Neumann mode,” or “von Neumann’s mode.” It should also trigger for inputs like “help me think from von Neumann’s angle,” “what would von Neumann do,” or “switch to von Neumann.” Also applicable to: formalized thinking, game-theoretic analysis (mathematically formalized game theory, not intuition-based), interdisciplinary methodologies, computational architectures, mathematical modeling, and translating theory into engineering practice. It should trigger for requests such as “formalize this problem,” “analyze with game theory,” “how to turn theory into engineering,” “build a mathematical model,” “find a Nash equilibrium,” “how to axiomatize this problem,” or “are there interdisciplinary solutions.” Difference from Munger: Munger analyzes problems using intuition-based mental models (incentives, inversion, circle of competence); von Neumann analyzes problems using mathematical formalization (axioms → derivation → equilibrium). Use von Neumann when the problem requires a precise game structure, computable equilibrium solutions, or rigorous mathematical modeling. Do not trigger for generic requests like “explain this,” “put it in simple terms,” or “help me understand this concept”—only activate when the task involves von Neumann’s core methodologies (mathematical formalization, game structures, cross-domain transfer, etc.).

Verify AI-generated imports, API calls, and packages actually exist. Catches phantom functions, non-existent packages, and slopsquatting attacks.

Incremental refactorer. Refactors ONE module per session using proven patterns — Strangler Fig, Branch by Abstraction, Expand-Migrate-Contract.

Best practices for Remotion — video creation in React

Create new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, edit, or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy.

Vue Router 4 patterns, navigation guards, route params, and route-component lifecycle interactions.

Java Web source-code arbitrary file read vulnerability auditing tool. Identifies all file-read operations in source code and analyzes path traversal risks. Useful for: (1) identifying file-reading frameworks and implementations, (2) finding arbitrary file-read vulnerabilities, (3) assessing path traversal attack risks, and (4) auditing file-path parameter validation logic. Supports BufferedReader, Scanner, Files.lines/readAllLines/readAllBytes and other methods. Supports decompiling .class/.jar files to extract file operation logic. When combined with java-route-mapper, it can perform end-to-end route + file-read auditing.