Packs

9 packs

Task Execution Workflow

Load a plan, execute tasks with verification, and track progress via issues.

10 skills · pack

Route questions to domain experts instead of asking the current user

2 skills · pack

UX strategy skills: information architecture, content strategy, navigation patterns, user flows, task analysis, and competitive UX audits.

12 skills · pack

Build Multi-Agent System with CrewAI

Design and orchestrate multi-agent AI teams using the CrewAI framework with agent roles, task decomposition, and crew processes.

11 skills · pack

Bridges to pi (dev/pi), a minimal terminal coding harness. Delegates coding tasks to the pi CLI for execution with full file and git context.

3 skills · pack

Business Process

Business process skills (process-optimizer, sop-writer, workflow-mapper, weekly-review). Useful for operational documentation, SOP generation, and workflow analysis. NOT for: software engineering tasks — these target organizational processes, not code.

4 skills · pack

@pwdev-solucoes

Spec-driven development framework v2.3 — 8 real subagents (incl. advisor), per-task model routing, curated memory graph, opt-in parallel waves, external CLI delegation (Codex/OpenCode/Kimi/Gemini/Kiro), simplification pass, strict verify, audit hooks, 22 commands

2 skills · pack

Utility skills (decision-matrix, navigate, model-route, prompt-improver, grill-research, align-prompt). Useful for specialized one-off tasks like structured decisions, adversarial research grilling, or aligning a draft prompt to an Opus model. NOT for: daily development workflow — these are situational tools, not always-on skills.

4 skills · pack

@alirezarezvani

Multi-agent collaboration — spawn N parallel subagents that compete on code optimization, content drafts, research approaches, or any task that benefits from diverse solutions. 7 slash commands (/hub:init, /hub:spawn, /hub:status, /hub:eval, /hub:merge, /hub:board, /hub:run), agent templates, DAG-based orchestration, LLM judge mode, message board coordination.

8 skills · pack

Results for “task”

32 skills

orchestra-research

Merge multiple fine-tuned models using mergekit to combine capabilities without retraining, covering SLERP, TIES-Merging, DARE, Task Arithmetic, linear merging, and production deployment strategies.

10.4k · bundle

Benchmarks LLM agents fine-tuned with the Agent Data Protocol across software engineering, web browsing, OS/database tool use, and reasoning tasks, reporting unit test pass rates and task success rates.

Computes the Recall metric using torchmetrics, including configuration for binary, multiclass, and multilabel tasks.

Computes the LogAUC metric using the torchmetrics implementation for binary, multiclass, or multilabel classification tasks.

Computes the Receiver Operating Characteristic (ROC) metric using torchmetrics, supporting binary, multiclass, and multilabel tasks.

Scales Python ML workloads across clusters using Ray's distributed tasks, actors, data, and serving capabilities.

More results

nemo-evaluator-plugin

Run evaluation tasks against a NeMo Platform server using the Evaluator plugin CLI and Python SDK.

Computes the AUROC metric using torchmetrics, handling binary, multiclass, and multilabel tasks with configurable thresholds and averaging.

orchestra-research

grpo-rl-training

Expert guidance for implementing GRPO/RL fine-tuning with TRL for reasoning and task-specific model training.

10.4k · bundle

Performs time series machine learning tasks including classification, regression, clustering, forecasting, anomaly detection, segmentation, and similarity search using the aeon toolkit.

Compute the Equal Error Rate (EER) metric using torchmetrics for binary, multiclass, or multilabel classification tasks, with reference signatures and usage examples.

Runs time series machine learning tasks—classification, regression, clustering, forecasting, anomaly detection, segmentation, and similarity search—using the scikit-learn compatible aeon toolkit.

leandrobenjaminl

senior-orchestrator

Orquesta el ecosistema de agentes: decide qué modelo o tier usar, delega tareas a sub-agentes especializados y planifica arquitectura técnica.

Evaluates how well internal model representations (hidden states) predict token-level information importance in summarization tasks, using NDCG@10 and Spearman's rank correlation.

Trains LLMs with SimPO, a reference-free preference optimization method that outperforms DPO, using configurable hyperparameters and workflows for various models and tasks.

Benchmarks medical AI agents on synthetic EHR tasks, measuring success rates for data retrieval, temporal aggregation, and threshold-based conditional logic with exact-match scoring.

huggingface-best

Queries Hugging Face benchmark leaderboards to find the best AI models for a task, filters by device constraints, and returns a ranked comparison table with scores.

tao-train-oneformer

Train, evaluate, export, quantize, and run inference for a TAO OneFormer model that performs panoptic, instance, and semantic segmentation using task-conditioned queries.

Perform time series machine learning tasks including classification, regression, clustering, forecasting, anomaly detection, segmentation, and similarity search using a scikit-learn compatible Python toolkit.

30.2k · bundle

tao-finetune-cosmos-embed

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

Evaluates open-ended generation quality of multilingual LLMs across brainstorming, planning, and long-form tasks, using AYA and DOLLY datasets with qualitative fluency and quality scoring.

modal-serverless-gpu

Run ML workloads on Modal's serverless GPU cloud: deploy models as auto-scaling APIs, run batch jobs, and schedule tasks with pay-per-second GPU pricing.

Evaluates the throughput and resource allocation efficiency of RIS-aided mobile edge computing systems by measuring the total computation task bits successfully completed under varying network conditions.

Selects the right Gemma model for a task, recommends deployment tooling (Gradio, Transformers.js, Vertex AI, MLX), and applies optimizations like MTP and QAT.

Build clinical deep-learning pipelines with PyHealth: load EHR, signal, and imaging datasets, define prediction tasks, instantiate models, train with the PyHealth Trainer, and compute clinical metrics.

30.2k · bundle

Load pre-trained models from Hugging Face Hub, run pipeline inference, generate text, and fine-tune models on NLP, vision, audio, and multimodal tasks using the Transformers library.

30.2k · bundle

Replaces GIoU with Complete IoU (CIoU) loss in PyTorch object tracking or detection tasks, combining overlap area, center-point distance, and aspect-ratio similarity for improved bounding-box regression.

Benchmarks systems on the Abstraction and Reasoning Corpus (ARC) by requiring inference of abstract transformation rules from few input-output grid demonstrations and application to novel test cases, reporting the fraction of tasks solved.

Benchmarks long-context language models across 20 sub-tasks spanning 3k–200k tokens, covering retrieval, reasoning, summarization, and instruction understanding, with exact-match accuracy as the primary metric.

Benchmarks zero-shot in-context learning on BIG-Bench Hard multiple-choice tasks, comparing self-generated demonstrations against direct prompting and chain-of-thought baselines, and reports accuracy.

Measures the trade-off between computation time and energy consumption in mobile edge computing by computing a weighted sum of the two objectives, given system configuration parameters and per-user task characteristics.

Run cloud-native molecular modeling and drug-design workflows via a Python API, covering pKa prediction, docking, conformer and tautomer ensembles, molecular dynamics, and related small-molecule or protein tasks without local HPC infrastructure.