Results for “pe”

Analyzes recent conversation messages to identify a supporter personality type and generate a shareable identity card with tool recommendations.

Add persistent, intelligent memory to AI agents with Mem0 — add/search/update/delete memories per user/agent/session, supports vector + graph + key-value storage, integrates with LangChain, CrewAI, OpenAI Assistants, and any LLM.

This skill should be used when working with reinforcement learning tasks including high-performance RL training, custom environment development, vectorized parallel simulation, multi-agent systems, or integration with existing RL environments (Gymnasium, PettingZoo, Atari, Procgen, etc.). Use this skill for implementing PPO training, creating PufferEnv environments, optimizing RL performance, or developing policies with CNNs/LSTMs.

Periodically scans Claude Code configuration for redundant, stale, or orphaned items and walks the user through a confirm-each-deletion cleanup.

Provides expert guidance on modern Julia 1.10+ development, covering performance optimization, multiple dispatch, tooling, testing, and production-ready practices.

Scaffolds VS Code custom agent files (.agent.md) with YAML frontmatter, tool configuration, handoffs, and instructions for specialized AI personas.

Scans agent skills for security issues including prompt injection, malicious scripts, excessive permissions, secret exposure, and supply chain risks.

Composes ad-hoc teams of AI agents from local markdown personas and dispatches them in parallel on a task, then synthesizes their outputs.

Synthesise completed KUD charts into a developmental progression matrix and per-competency narrative sections. Use when you need a programme-level view of how knowledge, understanding, and performance develop across bands.

Benchmark LLM performance across tasks — latency, quality, cost comparison.

Read-only EVM client: wallets, tokens, gas across 8 chains.

Unsloth: 2-5x faster LoRA/QLoRA fine-tuning, less VRAM.

Build and maintain a personal knowledge base (wiki) using LLMs. Instead of RAG-style retrieval, the LLM incrementally compiles, cross-references, and maintains a persistent structured wiki from raw sources. Use when user wants to create a knowledge base, build a personal wiki, organize research notes, ingest documents into a structured wiki, or maintain a living knowledge repository.

Builds and maintains a persistent, interlinked Obsidian knowledge base by incrementally ingesting sources, updating entity/concept pages, and keeping cross-references current.

Creates and manages Twitter/X agents with distinct personalities, storylines, and post-image libraries, including automated posting and multi-agent support.

Train a personalized identity model on a person's face for use in Higgsfield's image and video generation.

Quantize large language models to 8/4/3/2/1-bit precision without calibration data, using multiple optimized backends and integrations with HuggingFace Transformers, vLLM, and PEFT/LoRA.

Fine-tune large language models by training less than 1% of parameters using LoRA, QLoRA, and 25+ adapter methods, enabling efficient adaptation on limited GPU memory.

Configure an AI agent's personality using the AURA protocol based on the HEXACO model, adjusting traits like honesty, assertiveness, and autonomy to reduce sycophancy and tailor communication style.

Runs a multi-agent academic research pipeline covering systematic review, LaTeX paper writing, peer review, and end-to-end orchestration with integrity gates.

Generates YouTube videos from prompts, creates vertical Shorts from text, and converts long videos into Shorts using free tools like ffmpeg, edge-tts, and Pexels.

Structure a decision or design challenge through multiple perspectives before committing to action. Use as a synthesis step after scoping, mapping, and dilemma navigation when a group needs a wiser next step.

High-performance vector similarity search engine for RAG and semantic search. Use when building production RAG systems requiring fast nearest neighbor search, hybrid search with filtering, or scalable vector storage with Rust-powered performance.

High-performance vector similarity search engine for RAG and semantic search. Use when building production RAG systems requiring fast nearest neighbor search, hybrid search with filtering, or scalable vector storage with Rust-powered performance.

Persistent per-project memory for Claude Code. Auto-loads project context on session start, tracks sessions with git activity, and writes to native memory. Commands run deterministic Node.js scripts — behavior is consistent across model versions.

Persistent per-project memory for Claude Code. Auto-loads project context on session start, tracks sessions with git activity, and writes to native memory. Commands run deterministic Node.js scripts — behavior is consistent across model versions.

High-performance vector similarity search engine for RAG and semantic search. Use when building production RAG systems requiring fast nearest neighbor search, hybrid search with filtering, or scalable vector storage with Rust-powered performance.

Two-phase Apollo.io prospecting: free People Search to discover ICP-matching leads, then selective enrichment to reveal emails/phones (credits per contact). Deduplicates against CRM (Google Sheets). Supports Apollo API and MCP tools.

Add account state (P&L, win rate, drawdown) to RL observations + drawdown penalty in rewards. Trigger when: (1) model needs account awareness, (2) training should penalize drawdowns, (3) upgrading obs_dim 5300→5600.

CUDA kernel development, debugging, and performance optimization for Claude Code. Use when writing, debugging, or optimizing CUDA code, GPU kernels, or parallel algorithms. Covers non-interactive profiling with nsys/ncu, debugging with cuda-gdb/compute-sanitizer, binary inspection with cuobjdump, and performance analysis workflows. Triggers on CUDA, GPU programming, kernel optimization, nsys, ncu, cuda-gdb, compute-sanitizer, PTX, GPU profiling, parallel performance.

Optimizes MoE expert-parallel communication overlap in Megatron Bridge, covering dispatch/combine overlap, flex dispatcher backends, and expert wgrad scheduling.

Browse available agent personas and compose ad-hoc teams of up to 5 agents to work in parallel on a task, then synthesize their results.

Explains the advantages of building on Ethereum, including ERC-8004 identity, x402 payments, composability, and permissionless deployment, while correcting common misconceptions about gas costs and network status.

Train unsupervised machine learning models on genomic interval data from BED files, including region embeddings, single-cell ATAC-seq analysis, and consensus peak building.

Fine-tune large language models by training less than 1% of parameters using LoRA, QLoRA, and 25+ adapter methods, enabling efficient adaptation on consumer GPUs.

Persistent per-project memory for Claude Code. Auto-loads project context on session start, tracks sessions with git activity, and writes to native memory. Commands run deterministic Node.js scripts — behavior is consistent across model versions.