스킬 찾기

Set up MISP to collect threat feeds and centrally manage indicators such as suspicious IP addresses and domains. Configure automated synchronization, connect related findings, and export indicators to security monitoring platforms or blocklists.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Centralizing threat indicators from multiple feeds
• Deploying MISP with Docker
• Automating threat feed synchronization

Build a central platform for collecting, analyzing, and sharing cyber threat information. Connect MISP, OpenCTI, TheHive, and Cortex to import feeds, add context to suspicious indicators, manage cases, and track platform activity.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Build a central threat intelligence platform
• Automate threat feed ingestion
• Add context to suspicious IP addresses and domains

Reconstruct activity on a compromised computer by combining file timestamps, event logs, browser history, and other evidence into one timeline. Extract and filter events with Plaso, then review and annotate them collaboratively in Timesketch.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Reconstructing the sequence of a computer compromise
• Comparing events across logs and file records
• Investigating timestamp changes and cleared logs

Set up MISP to collect, store, and correlate threat intelligence from multiple feeds. Use PyMISP to automate searches and imports of indicators of compromise, such as suspicious IP addresses and file hashes, and export data for security monitoring tools.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Collecting threat indicators from multiple feeds
• Automating MISP imports and searches
• Exporting indicators for security monitoring tools

Analyze suspicious Linux ELF executables through file inspection, runtime tracing, and reverse engineering. Identify malware behavior, network destinations, and persistence mechanisms, then organize findings and indicators for investigations involving servers, containers, or cloud infrastructure.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Triaging suspicious executables on Linux servers
• Investigating suspected cryptominers
• Analyzing malware found in containers

Investigate compromised Docker containers by preserving evidence and examining image layers, logs, file changes, and host settings. Summarize suspicious activity, security configuration issues, and vulnerability findings to support incident response.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Investigating a compromised application container
• Examining a suspicious image from a registry
• Checking evidence of a container escape attempt

Set up a local web search server using Bright Data SERP API and unfancy-search. Retrieve results from multiple engines, optionally expand queries with AI, and receive combined rankings with duplicates removed and results grouped by domain.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Adding web search to a Claude Code agent
• Researching a topic through multiple related queries
• Filtering searches by region or domain

Integrate USDC payments into AI agents on Base L2. Guides setup for earning or paying, generates tailored code, and verifies configuration, covering escrow that holds funds until delivery and instant payments for HTTP requests.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Building an agent that charges USDC for services
• Paying another agent for a specific service
• Trying payment flows in a local simulation

Build or rewrite resume sections for a target role and career stage. Get tailored summaries, organized skills, achievement-focused experience entries, and guidance on education, optional sections, and the order in which to present them.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Rewriting a summary for a career change
• Organizing skills for a technical role
• Presenting work experience through achievements

Improve resume layouts with consistent fonts, spacing, section order, and clear headings. The skill recommends formatting that supports quick reading by recruiters and text parsing by applicant tracking systems, with guidance on file formats.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Cleaning up a cluttered resume
• Reviewing formatting for applicant tracking systems
• Standardizing fonts, dates, and headings

Improve resumes for software engineering, technical product management, data, and DevOps roles. Organize technical skills, connect achievements to business results, and highlight projects in a format suited to applicant tracking systems, software used to process job applications, and recruiters.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Organize technical skills for a target role
• Rewrite experience to show technical and business impact
• Choose projects to highlight during a career change

Build searches with Qdrant that find similar content and filter results by attributes. The skill covers document retrieval for AI answers, vector storage, memory optimization, and distributed deployment for larger collections.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Building document retrieval for AI answers
• Combining similarity search with category or date filters
• Reducing memory use for large vector collections

Guide reinforcement learning, training models through rewards, with slime. Prepare data, configure Megatron-LM training and SGLang response generation, and set up asynchronous runs or custom multi-turn workflows for supported language models.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Preparing reward-based training for GLM or Qwen models
• Overlapping response generation and training
• Training agents that use tools across multiple turns

Guides large language model reinforcement learning with miles, covering environment setup, low-precision training, consistency between training and inference, and speculative decoding, where a smaller model proposes tokens for a larger model to verify.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Configure reinforcement learning for large MoE models
• Investigate instability in FP8 training
• Set up speculative decoding for faster rollout generation

Plan and configure large language model training with OpenRLHF to better match human preferences. Covers training method selection, distributed GPU setup, inference acceleration with vLLM, and troubleshooting memory or training stability issues.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Choosing a method for training models on human preferences
• Setting up PPO training with a reward model
• Configuring GRPO training without a critic model

Evaluate language models with over 100 benchmark tests covering knowledge, math, coding, safety, and image understanding. Configure runs on Docker, Slurm computing clusters, or cloud infrastructure, compare models, and export results.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Compare models using the same benchmark tests
• Run large evaluations on a Slurm cluster
• Evaluate safety and image understanding

Use Phoenix to record execution traces, detailed records of an AI application's operations, and investigate problems. Evaluate answers on datasets, compare prompts and models, and set up monitoring through a self-hosted server.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Investigate AI application problems using execution traces
• Evaluate answer quality across a test dataset
• Compare prompts and models through experiments

Run language models locally with llama.cpp on CPUs, Apple Silicon, or AMD and Intel GPUs. The skill guides model setup, memory-saving GGUF format choices, interactive chat, and serving models through an OpenAI-compatible API.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Running a language model on a CPU-only computer
• Setting up local chat on an Apple Silicon Mac
• Choosing model quantization to fit available memory

Deploy language models with vLLM through an OpenAI-compatible API or offline batch processing. Tune response speed, throughput, and GPU memory use with quantization, which reduces numerical precision, and execution across multiple GPUs.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Deploy an OpenAI-compatible language model API
• Generate text from many prompts in a batch
• Serve quantized models with limited GPU memory

Evaluate code generation models with HumanEval, MBPP, and other benchmarks. Test generated programs, compare models across programming languages, and record pass@k scores, which estimate the chance that at least one of k solutions passes the tests.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Comparing code generation models on shared benchmarks
• Measuring correctness across programming languages
• Evaluating models trained to follow instructions

Build AI agents that inspect screenshots, choose actions, and operate a mouse and keyboard. Covers the observation and action loop, desktop control examples, and isolated environments that restrict access to files, credentials, and networks.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Build an AI agent that operates desktop screens
• Connect screenshot analysis to mouse and keyboard actions
• Design an isolated environment for automation

Build and operate AutoGPT agents that carry out multi-step workflows. Covers a visual editor for connecting processing blocks, scheduled and webhook triggers, deployment, execution monitoring, and benchmarks for evaluating agent performance.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Build an AI workflow in a visual editor
• Run agents on a schedule or external event
• Add custom agent abilities with Forge

Run the cognee API server and optional interface on your own machine, check server health, connect SDK or HTTP clients, and configure authentication for personal development or use by multiple users.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Starting a local cognee server and interface
• Connecting SDK or HTTP clients to the server
• Configuring authentication for personal development

Run cognee in Docker, starting with a prebuilt image for local document ingestion and questions. It also covers Docker Compose profiles for adding the UI, MCP server, Postgres, and Neo4j, plus persistent data storage.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Try cognee locally using a prebuilt Docker image
• Test document ingestion and questions through the API
• Start the UI, MCP server, and databases with Docker Compose