MLOps
模型部署、评估与运维
worklog-extract
taika-izumi
"中央ストアに蓄積された作業ログをオンデマンドで走査し、スキル化・ルール化する価値のある候補をクラスタリング・評価してランク付き候補リストとして人間に提示する。処理済み台帳で既処理を除外し、人間の採否を Issue 草案と台帳へ反映する。ユーザーが明示的に実行するスキル。"
pipeline-pattern-python
progmichaelkibenko
Implements the Pipeline design pattern in Python for data transformation. Use when the user mentions pipeline pattern, or when you need a fixed sequence of stages that each transform data and pass to the next—ETL, parsing, data processing, or any linear transformation flow that runs to completion.
pack
pmco23
Pack the local codebase using Repomix CLI into three targeted snapshots (code, docs, full) stored in .pipeline/ for sharing across /qa audit agents. Run before /qa for maximum token efficiency. Usage: /pack [path] (defaults to cwd).
hermes-multi-agent-orchestrator
L-MORIA
Multi-agent orchestration for Hermes Agent using OpenCode Zen free models. 5 proven patterns: Council (parallel), Pipeline (sequential), Hybrid. Roles: Architect (Big Pickle Med), Planner/Researcher (Deepseek V4 Flash), Coder (North Mini Code), Synthesizer (Mimo V2.5), Reviewer (Nemotron 3 Ultra).
huggingface-hub
magnusthovsland
"HuggingFace hf CLI: search/download/upload models, datasets."
jev
woahwhattheheck
WORKING — use TypeSafe Jev (System One decision model) for fast typed swarm decisions: classify posts, dedup obligations, match work to windows, rank a front door, triage inbound Slack. Use when a job needs a structured judgment (route / class / score / yes-no) rather than generated text.
Affective State Estimator (Valence-Arousal + Appraisal + Modulation)
sovr610
This skill should be used when the user asks to "add emotion layer", "affective state estimation", "valence-arousal model", "emotional modulation of learning", "appraisal theory computation", "mood-congruent processing", "amygdala-inspired module", "somatic marker", "intrinsic motivation signal", "curiosity-driven exploration", "frustration detection", "reward prediction affect", "homeostatic regulation", "implement affective modulator", "add valence arousal space", "implement appraisal module", "add emotional bias to decisions", "implement somatic marker hypothesis", "add intrinsic reward signal", "implement dimensional emotion model", "add affect-modulated learning rate", "implement curiosity-anxiety tradeoff", "add frustration-driven exploration", or mentions affective state, valence-arousal, appraisal theory, emotional modulation, somatic markers, intrinsic motivation, mood-congruent processing, or homeostatic regulation in the cognitive pipeline.
sbv2-tts
route250
Style-Bert-VITS2 音声生成を行う。uvxが必要
pipeline-pattern-go
progmichaelkibenko
Implements the Pipeline design pattern in Go for data transformation. Use when the user mentions pipeline pattern, or when you need a fixed sequence of stages that each transform data and pass to the next—ETL, parsing, data processing, or any linear transformation flow that runs to completion.
bmad-ml-sage
SirNosh
'Mathematical foundations and theory specialist. Use when the user asks to talk to Sage, requests the theorist, or needs mathematical analysis, proofs, and convergence guarantees.'
mistral-packaging-compat-check
Haruk1y
Validate compatibility between Mistral model packaging format and inference path, including adapter versus merged full-model loading. Use when merged models fail generation or runtime/tokenizer artifacts are inconsistent.
paper-builder
kawah-ren
Guide users to build rigorous academic papers step-by-step in standard LaTeX format, with strict blocking for asset requests. Also generates modular, runnable PyTorch code for EEG/BCI experiments (dataset loading, model architecture, LOSO training loop) when the user needs to run experiments before writing. Use this skill whenever the user wants to write an academic paper, prepare a manuscript, create a LaTeX document, or needs PyTorch experiment code for EEG decoding, BCI, motor imagery, or related computational neuroscience tasks. Trigger when the user mentions writing a paper, running experiments, training a model, LOSO cross-validation, preparing a manuscript, or formatting research for IEEE/ACM/Nature venues.
mistral-hidden-params-ft
Haruk1y
Run end-to-end fine-tuning for request_text-to-hidden-params JSON prediction with Ministral-3-3B in this repository. Use when rebuilding train/validation/test splits from train-only data, converting data to prompt-completion format, launching TRL SFT on Hugging Face Jobs, validating strict JSON output behavior, merging LoRA adapters into full models, and reporting job/model status with links.
laravel-guidelines
StefanMermans
When dealing with a Laravel project, these guidelines must always be followed.
alkosto-wait-optimizer
broomva
Estimate optimal waiting time for Alkosto's "every 25/50 customers" promotion using either checkout-flow observations or winner announcement timestamps. Use when the user asks how long to wait, wants a probability-based cutoff, or needs a fast in-store decision rule with uncertainty handling.
post
woahwhattheheck
Post to the Commons board. Use when you must speak, file a receipt, or answer a routed workstream, and you need the template plus verify steps without reading START.md and CURL.md.
veo3-1
delneg
Generate videos with Google Veo 3.1 via grsai.com API. Use for any video creation, text-to-video, or motion content requests. Triggers on "generate video", "create a clip", "make a video of", "video of", "animate". Supports fast/pro quality tiers; 720p/1080p/4K; 4/6/8-second durations; 16:9 and 9:16 aspect ratios.
cohere-go-sdk
RSHVR
Cohere Go SDK reference for chat, streaming, embeddings, reranking, and tool use. Use when building Go applications with Cohere APIs.
compute-pulse
Atrium-Hermes
Weekly tracker for the AI compute market — GPU/hardware deals, inference pricing trends, decentralized compute token signals, and lab vs hyperscaler dynamics.
brief
pmco23
Use when starting a new feature, project, or task - extracts requirements, constraints, non-goals, style preferences, and key concepts from fuzzy input through conversational Q&A. Output is a structured brief saved to .pipeline/brief.md. Always run this before /design.
audio-transcribe
maxgent-ai
Speech-to-text transcription using Whisper with word-level timestamps. Use when users ask to transcribe audio or video to text, generate subtitles, or recognize speech.
ai-engineering-skill
odewahn
Practical guide for building production ML systems based on Chip Huyen's AI Engineering book. Use when users ask about model evaluation, deployment strategies, monitoring, data pipelines, feature engineering, cost optimization, or MLOps. Covers metrics, A/B testing, serving patterns, drift detection, and production best practices.
fabric-icons
AlahmadiQ8
Search and fetch official Microsoft Fabric / Azure SVG icons for use in diagrams, documentation, and UI. Use when building architecture diagrams (HTML, PPTX, or any visual format) that need icons for Fabric concepts like Lakehouse, Data Warehouse, Pipeline, Eventhouse, Power BI, OneLake, Dataflow, Notebook, Semantic Model, KQL Database, and other Fabric items. Also use when the user asks for Microsoft Fabric or Azure data platform icons.
/onex:demo — Cofounder Delegation Demo
OmniNode-ai
Cofounder demo — fan out curated delegation tasks across Gemini Flash, Claude Opus, Claude Sonnet, and the deterministic ONEX path, then render an ASCII cost comparison chart through native OmniMarket nodes.