IDA Pro 逆向分析辅助技能。当用户提到逆向、反编译、分析二进制/PE/ELF/APK/DLL/SO、破解、找密码、漏洞分析、病毒分析、firmware 固件分析，或需要分析 exe/dll/so/elf/macho/sys 等文件时，务必使用此技能。 Ensure to use this skill when the user wants to analyze any binary file, regardless of whether they explicitly mention "IDA" or "reverse engineering". This includes requests like "看看这个exe", "分析这个dll", "帮我破解", "找一下密码", "这个软件怎么注册", etc. Use the bundled scripts (scripts/start.ps1, scripts/open.ps1) for deterministic server management and file opening — do NOT write ad-hoc PowerShell commands for these operations.

Use for authorized cloud, container, and Kubernetes security assessment including metadata SSRF, IAM misconfig, container escape paths, and cluster RBAC review.

Internal downstream skill for ctf-sandbox-orchestrator. CTF-sandbox workflow for kernel attack surface, namespace and cgroup boundaries, container isolation assumptions, syscall paths, and escape primitive verification. Use when the user asks to analyze container-to-host escape paths, kernel exploit prerequisites, namespace crossover, capability misuse, or prove whether an exploit primitive crosses the sandbox boundary. Use only after `$ctf-sandbox-orchestrator` has already established sandbox assumptions and routed here.

Socratic drilling — it asks, you answer, it pushes back. Does NOT give you the answer until you've earned it. Use when the user says "drill me on", "quiz me", "socratic", "test me on [subject]", or wants to study actively.

Draft or update the privileged investigation memo from the investigation log. Use when an investigation is far enough along to write the first memo cut, or when new data has been added and the existing draft needs updating.

Manage matter workspaces — create, list, switch, close, or detach the active matter so multi-client practitioners keep one client's context separate from every other. Read by any substantive skill that needs to know what matter it's working in. Use when user says "new matter", "switch matter", "list matters", "close matter", or wants to work at practice-level only.

Read VDR documents and extract issues per house categories and materiality thresholds, producing findings in house memo format. Use when user says "review the data room", "extract issues from [folder]", "diligence review", "what's in the VDR", or points at VDR documents.

Reference: review of SaaS subscription agreements with attention to the terms that matter most in subscription deals — auto-renewal mechanics, price escalation, data portability, uptime SLAs, and subprocessor rights. Loaded by /commercial-legal:review when a SaaS or subscription agreement is detected.

Frontend development guidelines for React/TypeScript applications. Modern patterns including Suspense, lazy loading, useSuspenseQuery, file organization with features directory, MUI v7 styling, TanStack Router, performance optimization, and TypeScript best practices. Use when creating components, pages, features, fetching data, styling, routing, or working with frontend code.

Comprehensive backend development guide for Node.js/Express/TypeScript microservices. Use when creating routes, controllers, services, repositories, middleware, or working with Express APIs, Prisma database access, Sentry error tracking, Zod validation, unifiedConfig, dependency injection, or async patterns. Covers layered architecture (routes → controllers → services → repositories), BaseController pattern, error handling, performance monitoring, testing strategies, and migration from legacy patterns.

Use to select models to run locally with llama.cpp and GGUF on CPU, Mac Metal, CUDA, or ROCm. Covers finding GGUFs, quant selection, running servers, exact GGUF file lookup, conversion, and OpenAI-compatible local serving.

Run evaluations for Hugging Face Hub models using inspect-ai and lighteval on local hardware. Use for backend selection, local GPU evals, and choosing between vLLM / Transformers / accelerate. Not for HF Jobs orchestration, model-card PRs, .eval_results publication, or community-evals automation.

Merge multiple fine-tuned models using mergekit to combine capabilities without retraining. Use when creating specialized models by blending domain-specific expertise (math + coding + chat), improving performance beyond single models, or experimenting rapidly with model variants. Covers SLERP, TIES-Merging, DARE, Task Arithmetic, linear merging, and production deployment strategies.

Compress large language models using knowledge distillation from teacher to student models. Use when deploying smaller models with retained performance, transferring GPT-4 capabilities to open-source models, or reducing inference costs. Covers temperature scaling, soft targets, reverse KLD, logit distillation, and MiniLLM training strategies.

OpenAI's general-purpose speech recognition model. Supports 99 languages, transcription, translation to English, and language identification. Six model sizes from tiny (39M params) to large (1550M params). Use for speech-to-text, podcast transcription, or multilingual audio processing. Best for robust, multilingual ASR.

Open-source AI observability platform for LLM tracing, evaluation, and monitoring. Use when debugging LLM applications with detailed traces, running evaluations on datasets, or monitoring production AI systems with real-time insights.

LLM observability platform for tracing, evaluation, and monitoring. Use when debugging LLM applications, evaluating model outputs against datasets, monitoring production systems, or building systematic testing pipelines for AI applications.

Framework for state-of-the-art sentence, text, and image embeddings. Provides 5000+ pre-trained models for semantic similarity, clustering, and retrieval. Supports multilingual, domain-specific, and multimodal models. Use for generating embeddings for RAG, semantic search, or similarity tasks. Best for production embedding generation.

Managed vector database for production AI applications. Fully managed, auto-scaling, with hybrid search (dense + sparse), metadata filtering, and namespaces. Low latency (<100ms p95). Use for production RAG, recommendation systems, or semantic search at scale. Best for serverless, managed infrastructure.

Open-source embedding database for AI applications. Store embeddings and metadata, perform vector and full-text search, filter by metadata. Simple 4-function API. Scales from notebooks to production clusters. Use for semantic search, RAG applications, or document retrieval. Best for local development and open-source projects.