MLOps

django-model

jprokay-counterpart

Creating Django models following Counterpart's patterns. Use when building new models, working with audit fields, implementing relationships, or using PydanticJSONEncoder. Triggers: 'create model', 'new database table', 'audit fields', 'BaseModel inheritance', 'add foreign key', 'JSON field validation'

Data Loader Throughput + Sequence Packing

sovr610

This skill should be used when the user asks to "audit dataloader throughput", "measure data pipeline stalls", "implement sequence packing", "reduce padding waste in training", "add cu_seqlens packing for SFT", "boundary-aware packing FlashAttention", "DataCollatorWithFlattening", "configure DataLoader num_workers prefetch_factor", "tune DataLoader settings", "streaming dataset pipeline", "WebDataset tar shards", "memmap pretraining dataset", "HF datasets streaming IterableDataset", "deterministic sharding per rank", "DistributedSampler set_epoch", "padding ratio metrics", "effective tokens per second", "pretraining block builder", "data stall ratio measurement", "persistent_workers pin_memory tuning", "shard cache policy", "packed sequences with position_ids reset", "varlen_attn cu_seqlens", or needs guidance on turning the input pipeline into a first-class performance target with measurement, streaming I/O, packing, and deterministic distributed sharding.

decision-heuristics

kangarooking

当用户在重大选择上纠结（换工作/买房/搬城/合伙/结婚）、列了利弊表还是拿不定主意时调用。 核心理念: 无法决定就答否; 三个重大决定(住哪/和谁/做什么)值得花一两年; 两个均等选择选短期更痛苦的路。 不适用于: 日常琐碎选择（晚饭吃什么）、信息查询。 Triggers: 纠结/拿不定主意/要不要/该不该/利弊/decision/hesitate/should I

bg-remover

yemyat

Remove backgrounds from images using FAL.ai's BiRefNet model. Use when users ask to remove background, make transparent PNG, extract subject from image, or create cutouts. Trigger phrases include "remove background", "transparent background", "cut out", "extract subject", or any background removal request.

hytopia-entities

Abstrucked

Helps create and manage entities in HYTOPIA SDK games. Use when users need to create game objects, NPCs, items, or any interactive objects. Covers Entity class, spawn/despawn, components, animations, and lifecycle management.

ml-research

Pranav-Karra-3301

Comprehensive skill for ML/AI research experiments and finetuning. Use when: (1) Setting up new ML research project ("create ML project", "init experiment") (2) Finetuning models ("finetune LLM", "adapt pretrained model", "LoRA", "QLoRA") (3) Training from scratch ("train model", "run experiment") (4) Debugging ML issues ("model not converging", "loss exploding", "GPU OOM") (5) Setting up experiment tracking ("add W&B", "setup MLflow") (6) Optimizing GPU usage ("batch size tuning", "memory optimization") (7) Creating visualizations ("plot training curves", "confusion matrix") (8) Auditing ML code ("check reproducibility", "review experiment") Triggers: "ML", "machine learning", "deep learning", "training", "finetuning", "PyTorch", "TensorFlow", "experiment", "GPU", "CUDA", "model", "neural network", "W&B", "MLflow", "reproducibility", "learning rate", "checkpoint", "epoch"

minimax-h3-max

RobZombAI

Baseline high-fidelity guide and execution toolkit for MiniMax H3-Max video generation, SGLang miles RL + LoRA SFT training, PDD 6-step/8-step high-fidelity inference, and Apple Silicon Metal 4 NAX native acceleration. Activate whenever the user mentions MiniMax H3, H3-Max, Hailuo 3, SGLang miles, or asks for high-fidelity 6-step/8-step cinematic video generation with synchronized 48 kHz audio.

pricing-analyzer

ferdiboxman

Analyze and optimize your SaaS pricing strategy

ocr-disruptivo

rogermaiocchi

Pipeline production-grade de OCR jurídico com 8 engines, privacy-gate, roteamento automático, preservação de tabelas e FAIR-compliance. Unifica transcrever-pdf + ocr-juridico.

gptq

majiayu000

Post-training 4-bit quantization for LLMs with minimal accuracy loss. Use for deploying large models (70B, 405B) on consumer GPUs, when you need 4× memory reduction with <2% perplexity degradation, or for faster inference (3-4× speedup) vs FP16. Integrates with transformers and PEFT for QLoRA fine-tuning.

sirv-ai-studio

IgorVaryvoda

Guide for using Sirv AI Studio (www.sirv.studio), an AI-powered image and video processing platform. Use when working with product images, background removal, image upscaling, AI generation, video creation, batch processing, or e-commerce image workflows. Triggers on mentions of Sirv AI Studio, product photography, background removal, image upscaling, AI image generation, batch image processing, or marketplace optimization. IMPORTANT - If sirv-ai MCP tools are available (sirv_remove_background, sirv_upscale, sirv_generate, etc.), USE THEM directly for image processing tasks instead of telling user to visit the website.

galaxy-db-migration

arash77

Galaxy database migration with Alembic - create schema changes (add table/column), upgrade/downgrade database versions, check migration status, troubleshoot errors. Use for: SQLAlchemy model changes, database schema modifications, Alembic revisions, migration version conflicts, lib/galaxy/model changes.

build

pmco23

Use after /plan to execute the build. Opus leads and coordinates; Sonnets implement. Supports --parallel (independent agent per task group, own context) or --sequential (one task group at a time in current session). Invokes drift-verifier agent post-build. Writes .pipeline/build.complete on pass.

learned-index

WakeUp-Jin

学习记录索引与使用说明

conclave

mdm-sfo

"Multi-model AI deliberation with anti-sycophancy controls. Convenes a tribunal of AI models to independently solve a task, debate with evidence (position stability tracking, advisor framing, affective/epistemic convergence analysis per Kelley & Riedl 2026), and produce a consensus output validated by impartial judges on The Bench and a Fresh Eyes reviewer. Supports QUICK through NUCLEAR depth tiers. Trigger: /conclave or 'council'."

codex

VisualxIntelligence

Use when the user asks to run Codex CLI (codex exec, codex resume) or references OpenAI Codex for code analysis, refactoring, or automated editing. Uses GPT-5.2 by default for state-of-the-art software engineering.

zhin-database-orm

zhinjs

Guides database usage in Zhin including model definitions, CRUD queries, transactions, migrations, and lifecycle hooks. Covers the built-in ORM based on @zhin.js/database with SQLite support. Use when working with data persistence in Zhin plugins.

chai1

HughYau

Structure prediction for protein, nucleic-acid, and small-molecule complexes with the Chai-1 foundation model (Chai Discovery 2024, github.com/chaidiscovery/chai-lab). Reach for this skill to predict an antibody-antigen or protein-ligand complex from a single FASTA, to re-fold designed binders as an AlphaFold-multimer alternative, or to drive co-folding from Python for batched campaigns on a GPU.

clawpilot

CryptoManiaques

Discord voice channel integration for OpenClaw. Talk to your AI agent through Discord voice - say its name anywhere in a sentence or use wake words. Choose between free (local) or paid (cloud) STT/TTS providers. Streams responses sentence-by-sentence for fast voice interaction.

media-understand

maxgent-ai

AI-powered media understanding and analysis for images, videos, and audio. Use when users ask to describe, analyze, summarize, or extract text (OCR) from media files.

rails-active-record

shivamsinghchahar

Master Active Record for model associations, querying, validations, and advanced patterns in Rails applications

hf-job-ops-playbook

Haruk1y

Operate Hugging Face Jobs reliably for training and evaluation in this repository, with reproducible submission records, monitoring, and retry flow. Use when submitting, monitoring, or triaging HF Jobs.

z-cheatsheet

AutoFor

dotfiles に定義されたショートカット・コマンドを日本語キーワードで検索する。

智能食谱推荐系统

z12a