Results for “macro-f1”

Fine-tune, evaluate, run inference, and export Cosmos-Embed1 video-text embedding models for tasks like text-to-video retrieval and semantic deduplication.

Compute the F1Score metric using torchmetrics when predictions and ground-truth labels are available.

VIXEN v1.0 — Dual-mode emerging movers scanner. Built from FOX v1.6 live trading data (+34.5% ROI). Two entry modes: STALKER (steady accumulation, score 6+, catches the SM buildup BEFORE the explosion) and STRIKER (violent FIRST_JUMP, score 9+, with raw volume confirmation to filter blow-off tops). 2-hour per-asset cooldown after Phase 1 exits. DSL High Water Mode mandatory.

Use when annotating VCF files with flanking sequence information (INFO/FS tag) or masking regions/variants in flanking sequences.

Generates and edits images and videos via fal.ai's queue-based API, supporting models like Flux, Gemini image, and Kling video-to-video, with automatic polling.

SA-1B: Segment Anything 1 Billion Masks Dataset

Generate text-to-video with HappyHorse 1.0 on RunComfy. Documents HappyHorse 1.0's strengths (#1 on Artificial Analysis Video Arena, native 1080p with in-pass synchronized audio, multi-shot character consistency, 6-language prompt support), the duration / aspect-ratio / resolution schema, and when to route to Wan 2.7 / Seedance 2 / LTX 2 instead. Calls `runcomfy run happyhorse/happyhorse-1-0/text-to-video` through the local RunComfy CLI. Triggers on "happyhorse", "happy horse", "happyhorse 1.0", "happyhorse video", or any explicit ask to generate video with this model.

Use to audit canned responses, macros, templates and saved replies for staleness, contradictions, overuse and gaps. Trigger for "audit our macros", "are our canned responses up to date", "which templates do agents actually use", macro sprawl, template cleanup, conflicting saved replies, or before migrating macros to a new helpdesk.

Flamingo: A Visual Language Model for Few-Shot Learning

Guides cost-effective image generation by iterating at low resolution before producing final high-resolution output.

JACKAL — First Jump pyramider. FOX v1.6's exact five-layer entry gauntlet combined with RHINO's pyramiding mechanic. Enter at 30% on a qualifying First Jump, add 40% at +10% ROE and final 30% at +20% ROE — but only after re-validating 4h trend, SM alignment, and volume. Failed scouts cost $15 instead of FOX's $50. Full pyramids capture the same upside. DSL High Water Mode (mandatory).

Phi-1: Textbooks Are All You Need

N+1 Query Detection and Resolution

Generate text-to-video with HappyHorse 1.0 on RunComfy. Documents HappyHorse 1.0's strengths (#1 on Artificial Analysis Video Arena, native 1080p with in-pass synchronized audio, multi-shot character consistency, 6-language prompt support), the duration / aspect-ratio / resolution schema, and when to route to Wan 2.7 / Seedance 2 / LTX 2 instead. Calls `runcomfy run happyhorse/happyhorse-1-0/text-to-video` through the local RunComfy CLI. Triggers on "happyhorse", "happy horse", "happyhorse 1.0", "happyhorse video", or any explicit ask to generate video with this model.

KOMODO v1.0 — Momentum Event Consensus. Uses leaderboard_get_momentum_events (real-time threshold crossings) to detect when 2+ quality SM traders cross momentum thresholds on the same asset/direction within 60 minutes. Confirmed by market concentration + volume. Enters with the momentum. Replaces MANTIS v1.0 and SCORPION v1.1 (both used stale position data).

Organizes Flutter code by business features instead of technical layers, with self-contained folders for UI, logic, and data, plus a recommended project structure and dependencies.

Fine-tune Cosmos Reason video QA models using supervised fine-tuning with FSDP parallelism, including dataset preparation, spec construction, and AutoML support.

Orchestrate token-heavy research, coding, and testing by delegating bounded tasks to cheaper subagents while reserving Claude Fable for architecture, synthesis, and final review.

Enables Megatron Fully Sharded Data Parallel in Megatron-Bridge with configuration overrides, code anchors, pitfalls, and verification steps.

Edit images with Flux 1 Kontext Pro (Black Forest Labs' precise local image-edit model) on RunComfy — bundled with the model's documented prompting patterns so the skill gets sharper output than naive prompting against the same model. Documents Flux Kontext's strengths (single-reference precise local edits, strong prompt control, consistent high-fidelity outputs), the schema (single image + prompt), and when to route to Nano Banana Edit / GPT Image 2 edit / Flux 2 Klein instead. Calls `runcomfy run blackforestlabs/flux-1-kontext/pro/edit` through the local RunComfy CLI. Triggers on "flux kontext", "flux-kontext", "flux 1 kontext", "kontext", "BFL kontext", or any explicit ask to edit with this model.

Edit images with Flux 1 Kontext Pro (Black Forest Labs' precise local image-edit model) on RunComfy — bundled with the model's documented prompting patterns so the skill gets sharper output than naive prompting against the same model. Documents Flux Kontext's strengths (single-reference precise local edits, strong prompt control, consistent high-fidelity outputs), the schema (single image + prompt), and when to route to Nano Banana Edit / GPT Image 2 edit / Flux 2 Klein instead. Calls `runcomfy run blackforestlabs/flux-1-kontext/pro/edit` through the local RunComfy CLI. Triggers on "flux kontext", "flux-kontext", "flux 1 kontext", "kontext", "BFL kontext", or any explicit ask to edit with this model.

Generate images using Google Gemini 3.1 Flash Image Preview via the inference.sh CLI, with support for text-to-image, image editing, multi-image input, and Google Search grounding.

Generate text-to-video with HappyHorse 1.0 on RunComfy. Documents HappyHorse 1.0's strengths (#1 on Artificial Analysis Video Arena, native 1080p with in-pass synchronized audio, multi-shot character consistency, 6-language prompt support), the duration / aspect-ratio / resolution schema, and when to route to Wan 2.7 / Seedance 2 / LTX 2 instead. Calls `runcomfy run happyhorse/happyhorse-1-0/text-to-video` through the local RunComfy CLI. Triggers on "happyhorse", "happy horse", "happyhorse 1.0", "happyhorse video", or any explicit ask to generate video with this model.

Crie e gerencie arquivos de planejamento markdown persistentes para execução estruturada de tarefas. Use quando o usuário pedir para "criar um plano", "acompanhar progresso", "iniciar um projeto de pesquisa", ou quando uma tarefa exigir mais de 5 chamadas de ferramenta e precisar de rastreamento de fases estruturado para manter o foco e evitar desvio de objetivo.

Decompose an unknown quantity into 3-5 estimable factors and produce a defensible order-of-magnitude answer without needing precise data. Load when the user needs to size something without data — market size, resource requirements, effort estimates, user numbers, costs — or when a decision is blocked by "we don't know the numbers". Also triggers on "ballpark this", "rough estimate", "how big is this market", "how long would this take", "how many users", or when deep-thinking diagnoses a sizing/estimation frame. The goal is not precision — it is a defensible answer that enables a decision to be made. Based on Enrico Fermi's estimation method.

Extracts and analyzes malicious VBA macros, XLM macros, DDE, and remote template injections in Microsoft Office documents using olevba, oledump, and deobfuscation techniques to identify download cradles, payload execution, and persistence mechanisms.

Generates premium React/Next.js frontend code with deterministic typography, calibrated color palettes, and motion physics, enforcing anti-cliché design rules and performance guardrails.

LoRA: Low-Rank Adaptation of Large Language Models

Generates images, videos, and audio using fal.ai models via MCP, covering text-to-image, text/image-to-video, text-to-speech, and video-to-audio.

Provides a general step-by-step procedure for handling requests related to end, size, and fs, with placeholders for specifics.

Detect structural macro regime transitions (1-2 year horizon) using cross-asset ratio analysis, analyzing RSP/SPY concentration, yield curve, credit conditions, size factor, equity-bond relationship, and sector rotation to identify regime shifts.

Generates at most one token recommendation and one prediction-market pick per run, each with a falsifiable thesis, entry, sizing, and kill criterion. Returns NO_PICK when no candidate meets the bar.

COCO: Microsoft COCO: Common Objects in Context

Create a structured H2/H3 outline with BLUF openers and MECE coverage, bound by the research dossier's beat spec. Triggered after /research and /brand-reference.

AutoAugment: Learning Augmentation Strategies from Data