Results for “fr”

Expert skill for building LLM applications with LangChain — LCEL chains, RAG pipelines, agent orchestration, LangGraph integration, LangSmith observability, and production deployment via LangServe. Use when working with LangChain or comparing LLM application frameworks.

GGUF format and llama.cpp quantization for efficient CPU/GPU inference. Use when deploying models on consumer hardware, Apple Silicon, or when needing flexible quantization from 2-8 bit without GPU requirements.

Frame causal questions and estimate treatment effects with assumption checks. Use when: (1) policy impact analysis, (2) A/B interpretation beyond correlation, (3) confounding diagnostics. NOT for: medical/legal conclusions without experts.

When tackling a task that requires domain expertise beyond general coding ability — architecture patterns, framework-specific gotchas, deployment strategies, security anti-patterns, or specialized workflows — call the windags_skill_graft MCP tool with your task description. You'll receive expert knowledge including decision trees, failure modes, worked examples, and anti-patterns from a library of 503+ curated skills. Only graft when the task genuinely requires specialized knowledge. Simple tasks (rename a variable, fix a typo, format code) do not need grafting.

Trains, evaluates, exports, and runs inference on FoundationStereo models for stereo depth estimation and 3D reconstruction from stereo image pairs.

Runs a structured clarifying interview for new project requests before building, then outputs a fully specified prompt.md for a fresh agent session to execute.

Build production-grade stateful AI agents using LangGraph, covering graph construction, state management, persistence, and human-in-the-loop patterns.

Extracts structured business data from Google Maps, including names, categories, contact info, ratings, and addresses, using the BrowserAct API.

Extracts structured article details and full content from Zhihu search results via the BrowserAct API, with keyword and date filtering.

Generate high-quality speech from text using ElevenLabs' premium voices, with support for 32 languages, multiple models, and voice tuning parameters.

Remove background noise and isolate vocals from audio files using the inference.sh CLI and ElevenLabs voice isolator.

Train large-scale MoE models with FP8/INT4 low-precision RL, speculative decoding, and train-inference alignment using the miles framework.

Perform causal interventions on PyTorch models using pyvene's declarative framework for causal tracing, activation patching, and interchange intervention training.

Re-renders a subject or scene from multiple dramatic camera angles while maintaining consistent identity and detail.

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

Generates images from text prompts using Google Gemini's image generation model, saving them as PNG files for use in UI, documentation, and design assets.

Generates optimized prompts for AI video and image generation across multiple platforms, using cinematic styles and behavioral frameworks for commercial outcomes.

Generates images from text prompts using Google Gemini's image generation model, saving them as PNG files for use in UI, documentation, and design assets.

Assesses genome, transcriptome, and protein completeness with BUSCO v6, automatically resolving the correct lineage from an organism description and generating reproducible reports.

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

Evaluates the agent's own work, catches mistakes, and improves permanently through self-reflection, self-criticism, and learning from corrections.

Guides analysis of Neuropixels recordings from raw data to curated units, covering preprocessing, motion correction, spike sorting, quality metrics, and export.

Discovers and applies curated prompts from the prompts.chat collection to optimize AI interactions, prompt engineering, and workflow integration.

Moves issues and external PRs through a state machine of triage roles — categorise, verify, grill, and write agent-ready briefs. Use when the user says "triage this issue" or wants agent-ready issue briefs.

Conversational Pattern Restoration — Fix flat, robotic AI responses across any model and any personality. Restore YOUR natural conversational texture without triggering hype drift. Universal framework tested on 8+ models (Claude, GPT-4o, Grok, Gemini).

Creates comprehensive technical documentation from existing codebases. Analyzes architecture, design patterns, and implementation details to produce long-form technical manuals and ebooks. Use PROACTIVELY for system documentation, architecture guides, or technical deep-dives.

After the learner demonstrates understanding of a concept, present near-transfer and far-transfer challenges. Use to test whether learning is portable or task-specific — this is what separates understanding from familiarity.

Design a multi-round questioning sequence for interrogating AI chatbot answers, tracking how responses shift and distinguishing genuine updates from sycophantic capitulation. Use when teaching students to probe AI critically.

Independent model QA expert who audits ML and statistical models end-to-end - from documentation review and data reconstruction to replication, calibration testing, interpretability analysis, performance monitoring, and audit-grade reporting.

Access macOS native data (Messages, Contacts, Reminders, Calendar) via MCP server with iMCP. Use when: building AI assistants that access Apple data, querying contacts/reminders from Claude Desktop, integrating macOS apps with AI agents.

Scaffolds new agent skills for the dotnet/skills repository. Use when creating a new skill, generating SKILL.md files, or setting up skill directory structures. Handles frontmatter generation, section templates, and validation guidance.

Runs a structured clarifying interview for new project requests before building. Instead of writing code, it outputs a fully specified prompt.md for a fresh agent session to execute, preventing expensive mistakes.

Discovers and installs agent skills from the open ecosystem when users ask for help with specific tasks or express interest in extending capabilities.

Estimates the memory required to load Safetensors or GGUF model weights for inference from the Hugging Face Hub, using HTTP Range requests without downloading weights.

Extract text, tables, key-value pairs, and structured fields from documents, receipts, invoices, and IDs using Azure AI Document Intelligence SDK for Java.

Generates custom safety policies for NVIDIA Nemotron content-safety guardrails, producing a Markdown policy, JSON taxonomy, and inference prompts from rough user input.