Results for “ram-analysis”

Evaluates RAG pipelines using a filesystem-based benchmark with corpus/ and train.json, running evaluate_rag.py to tune retrieval and generation flags and interpret RAGAS metrics.

Provides a fast in-memory DataFrame library for datasets that fit in RAM, with lazy evaluation, parallel execution, and an Apache Arrow backend for ETL pipelines and analytics.

Analyze suspected malware through static, dynamic, and behavioral techniques, including IOC extraction, YARA or Sigma rules, sandboxing, and anti-analysis behavior detection.

Analyze RAM dumps with Volatility 3 to detect malware, process injection, network connections, and credential theft during incident response.

`analysis-agent`/`task-agent`/`review-agent`: use when latency, throughput, bundle, memory, CPU, query, rendering, or resource cost needs a budget; skip without performance risk.

`analysis-agent`/`task-agent`/`review-agent`: use when uploads, object storage, streaming, MIME, scanning, access, retention, or cleanup changes; skip without file/storage impact.

`analysis-agent`/`task-agent`/`review-agent`: use for recurrence guards on known defects, incidents, or escaped failures; skip speculative risk without a prior failure mechanism.

Analyzes encryption algorithms, key management, and file encryption routines used by ransomware families to assess decryption feasibility, identify implementation weaknesses, and support recovery efforts.

Analyze Windows memory dumps for signs of compromise using the Rekall memory forensics framework, including process injection, hidden processes, and rootkit detection.

Analyze volatile memory dumps using Volatility 3 to extract running processes, network connections, loaded modules, and evidence of malicious activity.

Analyzing pre-change impact across vertical (dependency chains, files) and horizontal (pattern consistency, naming) dimensions. Use to estimate blast radius before a refactor. No code.

Refactoring Analyst

Analyzes network traffic captures and flow data to identify adversary activity during security incidents, including command-and-control communications, lateral movement, data exfiltration, and exploitation attempts.

Analyze amm operations. Use when you need to understand amm mechanisms, evaluate protocol security, or reference on-chain concepts.

Evaluate LLM outputs systematically — benchmarks, automated metrics, human preference, and regression tracking

Analyze sprint retrospectives for patterns and action item tracking. Usage: /retro analyze <retro_data.json>

Conduct gap analyses between current and desired states. TRIGGERS - Use when user needs help with gap-analysis related tasks.

Analyzes .NET project code coverage and CRAP (Change Risk Anti-Patterns) scores to identify risk hotspots, methods blocking coverage gains, and prioritize where to add tests.

Provides file paths to language-specific reference files for polyglot test analysis skills, enabling framework-aware detection of test markers, assertions, and patterns across .NET, Python, TypeScript, Java, Go, Ruby, Rust, Swift, Kotlin, PowerShell, and C++.

`task-agent`/`review-agent`: use when CPU, memory, I/O, database, network, rendering, or cost needs measured bottleneck evidence; skip without a profiling need.

Expert in building Retrieval-Augmented Generation systems. Masters embedding models, vector databases, chunking strategies, and retrieval optimization for LLM applications. Use when: building RAG, vector search, embeddings, semantic search, document retrieval.

Parses and analyzes the Windows Amcache.hve registry hive to extract evidence of program execution, application installation, and driver loading for digital forensics investigations.

`analysis-agent`/`task-agent`/`review-agent`: primary-Skill-selected for races, locks, optimistic conflicts, or worker overlap; never task owner; skip without concurrency impact.

Expert in building Retrieval-Augmented Generation systems. Masters embedding models, vector databases, chunking strategies, and retrieval optimization for LLM applications.

当分析个人或他人成就差异的根本原因，并寻求提升路径时

Analyze closed deals and lost opportunities for patterns

`analysis-agent`/`task-agent`/`review-agent`: use when repeated failure needs a new hypothesis or proof path; skip an initial failure with verified cause and a different action.

Breaks down current state, context, user input, and data into a structured assessment before taking action.

`analysis-agent`/`task-agent`/`review-agent`: use when a service split affects ownership, deployment, scaling, isolation, contracts, or data; skip without a split decision.

Analyze auto-memory for promotion candidates, stale entries, consolidation opportunities, and health metrics.

Analyzes game AI systems in a codebase, covering behavior trees, finite state machines, GOAP, utility AI, pathfinding, steering, perception, difficulty adaptation, NPC dialogue, and AI debugging tools for Unity, Unreal, and Godot projects.

Enumerating failure modes via pre-mortem analysis. Systematically identifies failure scenarios for plans, designs, and features, scoring them with RPN/AP. Does not write code.

Designing and evaluating AI/ML systems: prompt engineering, RAG design, LLM application patterns, AI safety, evaluation frameworks, MLOps, cost optimization. Use for AI pipelines or eval harnesses.

Quantizes LLMs to 8-bit or 4-bit for 50-75% memory reduction with minimal accuracy loss. Use when GPU memory is limited, need to fit larger models, or want faster inference. Supports INT8, NF4, FP4 formats, QLoRA training, and 8-bit optimizers. Works with HuggingFace Transformers.