Results for “f1”

Evaluates automated metrics and vision-language models on identifying granular errors in detailed image descriptions and ranking paired descriptions against human judgments, using macro F1, pairwise accuracy, Spearman rank ρ, and Kendall's τ.

Legal-specific Argument Ranking Engine. Hodnotí právní argumenty 17-sloupcovým scoringem (síla, bezpečnost, dopad, riziko + 10 legal-specific kritérií: Compliance s novelou 2026, Evidence backing, Time-sensitivity, per-document mapping, R-static/R-reversal split, Tom-weight bonus, C-XX/M-XX/N-XX/D-XX integrace). Output: priorizovaný seznam argumentů s kategoriemi CORE/SUPPORT/CONTEXT/EXCLUDED/SUMMARY a per-document bundles (PR/§909/40_06/195). Použití: pre-prioritizace argumentů před F11.x review, Phase 2 Verify input, DÁVKA 3, výživné L04, AT podání. VŽDY použij tento skill, když Tom (nebo legal/strat) zmíní: /lare, lare, argument ranking, ARE matrix, score arguments, prioritize arguments, argument bundle, CORE/SUPPORT/CONTEXT/EXCLUDED, ARE_F11, LARE_F11, legal argument evaluation, argument scoring, compliance scoring, Tom-weight.

贺炜（体育解说）认知与表达框架（压缩蒸馏）：文学比喻嵌入赛况、克制激情、终场金句… 触发：足球诗人解说 等。非煽动球迷对立

Dolphins: Multimodal Language Model for Driving

Documents Ferrari's brand design system including color palette, typography, spacing, and layout tokens for use in marketing materials.

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

Finetunes the NV-Generate-CTMR MR-brain diffusion UNet from user-supplied NIfTI training volumes using a wrapper that stages configs and delegates to upstream scripts.

Submit TAO jobs to Lepton managed GPU compute on DGX Cloud, with run/status/cancel interface and multi-node distributed training support.

Import HD Map or OpenDRIVE files into a RoadRunner scene using MATLAB. Use when loading driving scenes in RoadRunner or RoadRunner Scene Builder, importing RRHD, OpenDRIVE, or other RoadRunner-supported formats for simulation, or verifying Lanelet2-to-RRHD conversion results visually. Requires rrApp handle from roadrunner-core.

Route Firebase AI feature work into either direct app/client Firebase AI Logic SDK integration or a server-owned Genkit workflow. Use when a web, mobile, backend, or full-stack feature needs model calls, typed outputs, reusable flows, tools, retrieval, prompt files, evals, observability, or deployment. Choose client-ai-logic, flow-foundation, tool-and-agent, retrieval-and-prompt, evaluation-and-observability, deployment-runtime, or comparison-or-fallback; route Firebase platform/operator work to `firebase-cli` and broad framework comparisons to `survey`.

Use when a manager, dispatcher, or safety director needs to have a coaching conversation with a driver — about a safety event (harsh brake, hard turn, distraction), an HOS violation, a customer complaint, a missed delivery, repeated minor incidents, or to deliver positive recognition. Covers conversation structure, language, documentation, and escalation.

Fetches real-time London transit data from the TfL API, including Tube and bus arrivals, line status, disruptions, journey planning, and route information.

nuScenes: A Multimodal Dataset for Autonomous Driving

Kinetics-400: A Large Video Understanding 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.

Generate AI videos on RunComfy via the `runcomfy` CLI — a smart router across the full video-model catalog: HappyHorse 1.0 (Arena #1, native in-pass audio), Wan-AI Wan 2-7 (open weights, audio-driven lip-sync), ByteDance Seedance v2 / 1-5 / 1-0 (multi-modal cinematic), Kling 3.0 / 2-6, Google Veo 3-1, MiniMax Hailuo 2-3, ByteDance Dreamina 3-0. Covers text-to-video (t2v), image-to-video (i2v), and Veo's video-extend endpoint. The skill picks the right model for the user's intent (Arena-#1 quality, multi-shot character identity, in-pass audio, cinematic motion, fastest path, sub-15s clip, longest duration) and ships each model's documented prompting patterns plus the minimal `runcomfy run` invoke. Triggers on "generate video", "make a video", "text to video", "t2v", "image to video", "i2v", "animate", "AI video", "make X move", "video from prompt", "video from image", or any explicit ask to produce a video clip from prompt or still.

Generate and edit videos using Alibaba HappyHorse 1.0 models via the inference.sh CLI, supporting text-to-video, image-to-video, reference-to-video, and video editing with natural language.

Extract violation details, fine amounts, vehicle information, and payment deadlines from traffic fine notices.

v4.1.0 reward function redesign to fix overtrading and DSR dominance

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.

Create, list, remove, and rename Gameplay Tags with runtime registration (GameplayTagService). Use when the user asks to add or register gameplay tags, list/query existing tags, or rename/remove tags (e.g. Ability.Attack.Melee, State.Stunned).

Trains large language models (2B-462B parameters) using NVIDIA Megatron-Core with advanced parallelism strategies. Use when training models >1B parameters, need maximum GPU efficiency (47% MFU on H100), or require tensor/pipeline/sequence/context/expert parallelism. Production-ready framework used for Nemotron, LLaMA, DeepSeek.

Auto-review pipeline — reads the full CEO, design, eng, and DX review skills from disk and runs them sequentially with auto-decisions using 6 decision principles. (gstack)

DriveLM: Driving with Graph Visual Question Answering

Integrates Firebase services into a Flutter app, covering authentication, Firestore, storage, messaging, analytics, crash reporting, and remote configuration with Provider state management.

Monitor a live model for data quality, input and prediction drift, performance decay, and fire retraining triggers.

Imported skill daytona from langchain

Execute the full AgentHub competition lifecycle in a single command: initialize, capture baseline, spawn agents, evaluate results, and merge the winner.

PHOENIX v2.0 — Contribution Velocity Scanner (Hardened). Same battle-tested signal. Fixed trade counter. DSL plugin exits.

Cancel any active OMC mode (autopilot, ralph, ultrawork, ultraqa, swarm, ultrapilot, pipeline, team)

Financial runway & unit economics tracker — burn rate, revenue trajectory, runway in months, scenario modeling

Evaluates the faithfulness of abstractive summaries by verifying if factual claims (masked as cloze questions) in the reference summary can be correctly answered using only the generated summary, compared against a gold-standard answer derived from the source context.