Results for “e-e-a-t”

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.

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.

Extends effective context capacity through strategic compression, masking, caching, and partitioning techniques.

Master Python 3.12+ with modern features, async programming, performance optimization, and production-ready practices. Expert in the latest Python ecosystem including uv, ruff, pydantic, and FastAPI.

Model complex UI behavior as finite state machines with states, events, and transitions to eliminate impossible states and make behavior predictable.

Generates structured VGL JSON prompts for Bria's FIBO image generation models, covering text-to-image, editing, inpainting, outpainting, and captioning with a deterministic schema.

Automate V0 operations through Composio's V0 toolkit via Rube MCP, including tool discovery, connection management, and execution.

Automate Getform form operations through Composio's toolkit via Rube MCP, including tool discovery, connection management, and execution.

Automate Browseai operations through Composio's Browseai toolkit via Rube MCP, including tool discovery, connection management, and execution.

Automate Formsite operations through Composio's Formsite toolkit via Rube MCP, including tool discovery, connection management, and execution.

Automates Recallai operations through Composio's Recallai toolkit via Rube MCP, including tool discovery, connection management, and execution.

Automate Formbricks operations through Composio's Formbricks toolkit via Rube MCP, including tool discovery, connection management, and execution.

Animate any still image on RunComfy — this skill is a smart router that matches the user's intent to the right i2v model in the RunComfy catalog. Picks HappyHorse 1.0 I2V (Arena #1, native audio, identity preservation) for general animations, Wan 2.7 with `audio_url` for custom-voiceover lip-sync, or Seedance 2.0 Pro for multi-modal animation from image + reference video + reference audio. Bundles each model's documented prompting patterns so the caller gets sharper output without burning iterations on the wrong model. Calls `runcomfy run <vendor>/<model>/image-to-video` (or endpoint variant) through the local RunComfy CLI. Triggers on "image to video", "image-to-video", "i2v", "animate image", "make this move", or any explicit ask to turn a still into video.

Anthropic Claude API patterns for Python and TypeScript. Covers Messages API, streaming, tool use, vision, extended thinking, batches, prompt caching, and Claude Agent SDK. Use when building applications with the Claude API or Anthropic SDKs.

Start, query, and stop a TAO inference microservice for a specific network architecture by delegating container execution to the appropriate platform skill.

Orchestrates multi-agent teams using the ClawTeam CLI, enabling task management, inter-agent messaging, git context integration, runtime profiles, and monitoring dashboards.

Store and query embeddings with metadata, vector and full-text search, and filtering. Integrates with LangChain and LlamaIndex for RAG and semantic search applications.

Drive a Genie change test-first through the genie MCP tools, working entirely from the live image (no files). Use when adding behavior or fixing a bug in the image — anything where a test should lead.

Automate D2L Brightspace operations through Composio's toolkit via Rube MCP, including tool discovery, connection management, and task execution.

Master systematic debugging techniques, profiling tools, and root cause analysis to efficiently track down bugs across any codebase or technology stack. Use when investigating bugs, performance issues, or unexpected behavior.

Automate Strava operations like fetching activities, managing connections, and executing bulk tasks through Composio's Strava toolkit via Rube MCP.

Resto tech — POS, menu digital, livraison, Uber Eats DZ, facturation restaurants

Retail tech — magasin connecté, stock, caisse, fidélisation, e-commerce omnicanal DZ

Coordinate multiple subagents/worktrees for parallel workstreams. Decomposes larger tasks into independent sub-tasks, dispatches each to a dedicated agent.

Research-before-coding workflow. Search for existing tools, libraries, and patterns before writing custom code. Invokes the researcher agent.

Simulator.Company digital-twin & actor-agent specialist — talk to an agent AS an agent and delegate work to it. An agent is ANY actor whose `description` holds an "# Agent" competency profile (what it does, what it knows, whether it fits a task). The common case is a person: every workspace user has a 1:1 twin actor (`systemObjType="user"`) carrying that profile. But any actor can be an agent — a service/bot twin, a team or department, an organization, a process. This skill discovers the agent (`findAgent`), loads its profile (`getAgent`), adopts it as the persona, then either does the task, finds a better-suited agent, or hands the decision to the user (for a person: a task or a p2p message; for a non-person: propose another executor or run/trigger it as an actor). It is the actor-analog of `simulator-skills` (the `Skills`-form registry), but the registry is the workspace's agent actors. Use when the user wants to "delegate", "assign this to <someone/something>", "can <X> do this", "who/what should do this",

This skill should be used when the user asks to "/do-agent", asks for "Execute complex tasks using multi-agent architecture with context protection", or needs the workflow previously provided by the /do-agent slash command.

Deliberative consultation with another Claude model via Task tool. Opus consults Sonnet, Sonnet consults Opus. Ask, evaluate, critique, iterate until workable agreement.

Compiled CLI covering all 52 endpoints of the Anytype local API — objects, properties, tags, search, chat, files — one binary, no MCP server needed.

Use when working from the local Biomni repository to run agent-style biomedical tasks or inspect Biomni's biomedical tool modules and examples.

Compiled CLI covering all 52 endpoints of the Anytype local API — objects, properties, tags, search, chat, files — one binary, no MCP server needed.

Compiled CLI covering all 52 endpoints of the Anytype local API — objects, properties, tags, search, chat, files — one binary, no MCP server needed.

Anthropic Claude API patterns for Python and TypeScript. Covers Messages API, streaming, tool use, vision, extended thinking, batches, prompt caching, and Claude Agent SDK. Use when building applications with the Claude API or Anthropic SDKs.