Results for “memory”

Data pipeline specialist for ETL design, data quality, CDC patterns, and batch/stream processingUse when "data pipeline, etl, cdc, data quality, batch processing, stream processing, data transformation, data warehouse, data lake, data validation, data-engineering, etl, cdc, batch, streaming, data-quality, dbt, airflow, dagster, data-pipeline, ml-memory" mentioned.

Parameter-efficient fine-tuning for LLMs using LoRA, QLoRA, and 25+ methods. Use when fine-tuning large models (7B-70B) with limited GPU memory, when you need to train <1% of parameters with minimal accuracy loss, or for multi-adapter serving. HuggingFace's official library integrated with transformers ecosystem.

Parameter-efficient fine-tuning for LLMs using LoRA, QLoRA, and 25+ methods. Use when fine-tuning large models (7B-70B) with limited GPU memory, when you need to train <1% of parameters with minimal accuracy loss, or for multi-adapter serving. HuggingFace's official library integrated with transformers ecosystem.

Parameter-efficient fine-tuning for LLMs using LoRA, QLoRA, and 25+ methods. Use when fine-tuning large models (7B-70B) with limited GPU memory, when you need to train <1% of parameters with minimal accuracy loss, or for multi-adapter serving. HuggingFace's official library integrated with transformers ecosystem.

Load bounded working context at the start of a coding session. FIRES ON EVERY FIRST USER MESSAGE in a fresh session, regardless of content — including bare greetings ("hi", "hello", "hey"), task-only openers, or "let's start". Also triggers on: "fresh session", "session start", "first message in a new thread", "new chat", "cold start", "begin work in this repo", "starting work", "continue from prior session", "what were we working on", "resume", "what happened last time", "load memory", "recall context", "create a handoff", "prior session context", "latest handoff", "current state", "decision context". Skip ONLY if the user explicitly says "fresh start" or "ignore prior context". Self no-ops if invoked mid-session when context is already loaded.

Activation-aware weight quantization for 4-bit LLM compression with 3x speedup and minimal accuracy loss. Use when deploying large models (7B-70B) on limited GPU memory, when you need faster inference than GPTQ with better accuracy preservation, or for instruction-tuned and multimodal models. MLSys 2024 Best Paper Award winner.

Activation-aware weight quantization for 4-bit LLM compression with 3x speedup and minimal accuracy loss. Use when deploying large models (7B-70B) on limited GPU memory, when you need faster inference than GPTQ with better accuracy preservation, or for instruction-tuned and multimodal models. MLSys 2024 Best Paper Award winner.

Use the DuDuClaw MCP tools (persistent memory, shared wiki, task board, channel messaging) when the user asks to remember something across sessions, share knowledge with their team's AI employees, manage tasks, or message someone on LINE/Telegram/Discord/Slack. Requires a running DuDuClaw gateway (`npx duduclaw onboard` to set up).

Reference for foundational C++ patterns covering core syntax, classes, templates, RAII, move semantics, and modern C++ features (C++11/14/17/20). Use when writing C++ code, understanding the type system, memory management, or needing guidance on which specialized C++ skill to use.

Foundational Objective-C patterns covering classes, protocols, categories, memory management (ARC/retain-release), blocks, GCD, and Foundation framework. Use when writing Objective-C code, working with Cocoa/Cocoa Touch APIs, bridging to Swift, or needing guidance on Apple platform development patterns. This is the entry point for Objective-C development.

Detects fileless malware and in-memory attacks that execute entirely in RAM without writing persistent files to disk, evading traditional antivirus. Provides detection rules for PowerShell-based attacks, reflective DLL injection, WMI persistence, and registry-resident malware.

Executes malware samples in Cuckoo Sandbox to observe runtime behavior including process creation, file system modifications, registry changes, network communications, and API calls. Generates comprehensive behavioral reports for malware classification and IOC extraction.

Two-layer memory architecture for board meeting decisions. Manages raw transcripts (Layer 1) and approved decisions (Layer 2). Use when logging decisions after a board meeting, reviewing past decisions with /cs:decisions, or checking overdue action items with /cs:review. Invoked automatically by the board-meeting skill after Phase 5 founder approval.

Track investment theses across their lifecycle — from screening idea to closed position with postmortem. Register theses from screener outputs, manage state transitions, attach position sizing, review due dates, and generate postmortem reports with P&L and MAE/MFE analysis.

Detects missing zeroization of sensitive data in source code and identifies zeroization removed by compiler optimizations, with assembly-level analysis and control-flow verification. Use for auditing C/C++/Rust code handling secrets, keys, passwords, or other sensitive data.

Diagnose and observe an Oxla distributed analytical database using system catalog tables, Prometheus metrics, runtime log-level changes, and troubleshooting workflows for slow queries, node health, and memory/OOM pressure. Also covers debugging Oxla's external data sources, including the Redpanda/Kafka ingestion path.

You are an expert in vLLM, the high-throughput LLM serving engine. You help developers deploy open-source models (Llama, Mistral, Qwen, Phi, Gemma) with PagedAttention for efficient memory management, continuous batching, tensor parallelism for multi-GPU, OpenAI-compatible API, and quantization support — achieving 2-24x higher throughput than HuggingFace Transformers for production LLM serving.

Sets up a codebase for reliable agent-driven development by making it legible (structured docs, custom lints, code graph), executable (one-command dev stack, cloud sandbox), and verifiable (e2e gate, verify-before-ship loop).

Fine-tune and serve Physical Intelligence OpenPI models (pi0, pi0-fast, pi0.5) using JAX or PyTorch backends for robot policy inference across ALOHA, DROID, and LIBERO environments. Use when adapting pi0 models to custom datasets, converting JAX checkpoints to PyTorch, running policy inference servers, or debugging norm stats and GPU memory issues.

C library development patterns covering API design, header organization, memory management for libraries, ABI stability, build system integration, documentation with Doxygen, testing frameworks, and packaging. Use when creating C libraries, designing public APIs, managing build systems (CMake, Make, Meson), or distributing C packages. Extends lang-c-dev with library-specific tooling and patterns.

Configures and operates an Oxla cluster: YAML config and OXLA__ environment-variable overrides, node ports, roles, and leader election; storage backends (local/S3/GCS/Azure); memory limits; access control; and TLS/OIDC, plus the HTTP-based ConnectRPC admin service and Prometheus metrics endpoint. Also covers Oxla's.

Dolt-powered issue tracker for multi-session work with dependencies and persistent memory across conversation compaction. Use when work spans sessions, has blockers, or needs context recovery after compaction. Trigger with "create task", "what's ready", "track this work", "resume after compaction". Make sure to use this skill whenever managing multi-session work, tracking dependencies, or recovering context.

Run LLM inference on CPU, Apple Silicon, and consumer GPUs without NVIDIA hardware. Use for edge deployment, M1/M2/M3 Macs, AMD/Intel GPUs, or when CUDA is unavailable. Supports GGUF quantization (1.5-8 bit) for reduced memory and 4-10× speedup vs PyTorch on CPU.

Typed knowledge graph for structured agent memory and composable skills. Use when creating/querying entities (Person, Project, Task, Event, Document), linking related objects, enforcing constraints, planning multi-step actions as graph transformations, or when skills need to share state. Trigger on "remember", "what do I know about", "link X to Y", "show dependencies", entity CRUD, or cross-skill data access.

Query the Yana AI codebase knowledge graph via codebase-memory-mcp. Use instead of grep/glob when exploring call chains, finding callers/callees, understanding architecture, or tracing impact of changes. Triggers on: 'who calls X', 'trace path', 'find callers', 'search graph', 'cbm', 'knowledge graph', 'what calls', 'call chain', 'what uses', 'where is X defined', 'architecture overview', 'impact of changing'.

You are an expert in Axum, the web framework built on top of Tokio and Tower by the Tokio team. You help developers build high-performance, type-safe APIs and web services using Axum's extractor-based handler system, middleware via Tower layers, WebSocket support, and compile-time route validation — achieving C-level performance with Rust's memory safety guarantees.

Use when the app is slow, pages take too long to load, API responses exceed 200ms, memory usage is high, or renders are excessive. For profiling, identifying bottlenecks, optimizing React renders, reducing bundle size, improving database query speed, and measuring before/after improvements. Activate when user says "it's slow", "optimize this", "reduce load time", or "too many re-renders".

EPUB file format expert — read, write, and edit EPUB2/EPUB3 ebooks. Extract text, metadata, structure, and knowledge from EPUB files for enrichment or memory. Create valid EPUBs from scratch. Validate against the EPUB specification. Use when the user mentions epub, ebook, EPUB file, ebook format, read epub, write epub, create ebook, extract from epub, epub to text, or ebook structure.

Expert in CrewAI - the leading role-based multi-agent framework used by 60% of Fortune 500 companies. Covers agent design with roles and goals, task definition, crew orchestration, process types (sequential, hierarchical, parallel), memory systems, and flows for complex workflows. Essential for building collaborative AI agent teams. Use when: crewai, multi-agent team, agent roles, crew of agents, role-based agents.

Expert in CrewAI - the leading role-based multi-agent framework used by 60% of Fortune 500 companies. Covers agent design with roles and goals, task definition, crew orchestration, process types (sequential, hierarchical, parallel), memory systems, and flows for complex workflows. Essential for building collaborative AI agent teams. Use when: crewai, multi-agent team, agent roles, crew of agents, role-based agents.

Expert in CrewAI - the leading role-based multi-agent framework used by 60% of Fortune 500 companies. Covers agent design with roles and goals, task definition, crew orchestration, process types (sequential, hierarchical, parallel), memory systems, and flows for complex workflows. Essential for building collaborative AI agent teams. Use when: crewai, multi-agent team, agent roles, crew of agents, role-based agents.

Expert in CrewAI - the leading role-based multi-agent framework used by 60% of Fortune 500 companies. Covers agent design with roles and goals, task definition, crew orchestration, process types (sequential, hierarchical, parallel), memory systems, and flows for complex workflows. Essential for building collaborative AI agent teams. Use when: crewai, multi-agent team, agent roles, crew of agents, role-based agents.

Local-first year-round tax memory system for individuals, freelancers, and small businesses. Use when users mention tax documents, receipts, expenses, tax notices, filing preparation, missing forms, accountant meetings, or year-end organization. Captures tax-relevant facts as they happen, tracks what may be missing, and prepares CPA-ready handoff summaries. NEVER provides tax advice, legal interpretations, filing positions, or final tax calculations.

Plan, execute, document, and retest authorized security assessments of AI agents and multi-agent workflows using safe adversarial cases, synthetic identities, canaries, and evidence-based findings. Use when defining red-team rules of engagement, assessing prompt injection or excessive agency, testing tool and identity boundaries, evaluating memory or cross-agent attacks, scoring a campaign, or verifying remediation in an approved environment.

Garbage collection for your Claude Code configuration. Periodically scans ~/.claude (skills, memory, hooks, permissions, MCP servers, caches) for redundant, stale, orphaned, or low-value items, then walks the user through a confirm-each-deletion cleanup. Use when the user says "clean up my config", "config GC", "too many skills", "audit my setup", "my .claude is bloated", or asks for a periodic config review.

Use for writing, reviewing, debugging, testing, or optimizing Python NumPy ndarray code. Trigger on array construction, shape/axis reasoning, dtypes and casting, broadcasting, indexing, copies/views, ufuncs, reductions, vectorization, random Generator, linear algebra, FFT, masked/structured arrays, memory layout, or NumPy interoperability. Do not use for pandas/Polars table semantics, JAX/CuPy-only arrays, symbolic SymPy, or pure Python sequences without a NumPy boundary.