MLOps

codex

skills-directory

Use when the user asks to run Codex CLI (codex exec, codex resume) or references OpenAI Codex for code analysis, refactoring, or automated editing

building-with-llms

RefoundAI

Help users build effective AI applications. Use when someone is building with LLMs, writing prompts, designing AI features, implementing RAG, creating agents, running evals, or trying to improve AI output quality.

ai-evals

RefoundAI

Help users create and run AI evaluations. Use when someone is building evals for LLM products, measuring model quality, creating test cases, designing rubrics, or trying to systematically measure AI output quality.

openai-image-gen

openclaw

Batch-generate images via OpenAI Images API. Random prompt sampler + index.html gallery.

local-llm-router

hoodini

Route AI coding queries to local LLMs in air-gapped networks. Integrates Serena MCP for semantic code understanding. Use when working offline, with local models (Ollama, LM Studio, Jan, OpenWebUI), or in secure/closed environments. Triggers on local LLM, Ollama, LM Studio, Jan, air-gapped, offline AI, Serena, local inference, closed network, model routing, defense network, secure coding.

aws-strands

hoodini

Build AI agents with Strands Agents SDK. Use when developing model-agnostic agents, implementing ReAct patterns, creating multi-agent systems, or building production agents on AWS. Triggers on Strands, Strands SDK, model-agnostic agent, ReAct agent.

ln-1000-pipeline-orchestrator

levnikolaevich

"Meta-orchestrator (L0): reads kanban board, drives Stories through pipeline 300->310->400->500 in parallel via TeamCreate. Max 3 concurrent Stories. Auto squash-merge to develop on quality gate PASS."

context-fundamentals

shipshitdev

Understand the components, mechanics, and constraints of context in agent systems. Use when designing agent architectures, debugging context-related failures, or optimizing context usage.

cold-call-scripts

sachacoldiq

1-minute cold call script (5 steps) and no-show phone script. Use when training SDRs on calls, building call frameworks, or handling common phone scenarios.

numerai-model-implementation

numerai

Add a new Numerai model type to the agents training pipeline. Use when you need to register a model in agents/code/modeling/utils/model_factory.py, handle fit/predict quirks in agents/code/modeling/utils/numerai_cv.py, and update configs so the model can run via python -m agents.code.modeling.

organizational-transformation

RefoundAI

Help users transform organizations toward modern product practices. Use when someone is trying to shift from feature teams to product teams, introduce empowered teams, modernize legacy processes, or drive cultural change in how product is built.

pymc-bayesian-modeling

jaechang-hits

"Bayesian modeling with PyMC 5. 8-step workflow: define model, set priors, define likelihood, sample (NUTS/ADVI), diagnose (R-hat, ESS, divergences), interpret posteriors, compare models (LOO/WAIC), predict. Hierarchical, logistic, GP model variants. Prior/posterior predictive checks."

geniml

jaechang-hits

"Geniml is a Python library for genomic interval machine learning. Train and apply region2vec embeddings to convert BED file regions into numeric vectors, load and index genomic interval datasets for ML pipelines, search embedding spaces with BEDSpace, and evaluate embedding quality. Use for chromatin accessibility clustering, regulatory element classification, cross-sample region comparison, and building ML models on genomic intervals."

scikit-survival-analysis

jaechang-hits

"Survival analysis and time-to-event modeling with scikit-survival. Cox proportional hazards (standard/elastic net), Random Survival Forests, Gradient Boosting, SVMs for censored data. C-index (Harrell/Uno), Brier score, time-dependent AUC evaluation. Kaplan-Meier, Nelson-Aalen, competing risks. scikit-learn Pipeline/GridSearchCV compatible. For frequentist regression use statsmodels; for Bayesian survival use pymc; for simpler parametric models use lifelines."

summarize

openclaw

Summarize or extract text/transcripts from URLs, podcasts, and local files (great fallback for “transcribe this YouTube/video”).

3d-cv-labeling-2026

curiositech

Expert in 3D computer vision labeling tools, workflows, and AI-assisted annotation for LiDAR, point clouds, and sensor fusion. Covers SAM4D/Point-SAM, human-in-the-loop architectures, and vertical-specific training strategies. Activate on '3D labeling', 'point cloud annotation', 'LiDAR labeling', 'SAM 3D', 'SAM4D', 'sensor fusion annotation', '3D bounding box', 'semantic segmentation point cloud'. NOT for 2D image labeling (use clip-aware-embeddings), general ML training (use ml-engineer), video annotation without 3D (use computer-vision-pipeline), or VLM prompt engineering (use prompt-engineer).

atdd

swingerman

This skill should be used when the user asks to "build a feature", "implement a feature", "add functionality", "start development", "write acceptance tests", "write specs", "use ATDD", "use TDD with acceptance tests", or begins any feature implementation work. Also triggered by the /atdd command. Enforces the Acceptance Test Driven Development workflow: write Given/When/Then specs before code, generate a project-specific test pipeline, and maintain two test streams.

lmms-eval-guide

EvolvingLMMs-Lab

Guides AI coding agents through the lmms-eval codebase - a unified evaluation framework for Large Multimodal Models (LMMs). Use when integrating new models, adding evaluation tasks/benchmarks, using the HTTP eval server, or navigating the evaluation pipeline architecture.

leela-ai

SimHacker

"Manufacturing Intelligence — Leela AI develops MOOLLM for practical use and industrial exploration"

llm-integration

yonatangross

LLM integration patterns for function calling, streaming responses, local inference with Ollama, and fine-tuning customization. Use when implementing tool use, SSE streaming, local model deployment, LoRA/QLoRA fine-tuning, or multi-provider LLM APIs.

rag

sjtu-sai-agents

Retrieval-Augmented Generation (RAG) system for semantic search and knowledge retrieval. Use when implementing knowledge-grounded AI, building document Q&A systems, or integrating LLMs with external knowledge bases. Supports vector-based similarity search using FAISS and transformer embeddings.

Ai Image Generation

omer-metin

ultrawork

Yeachan-Heo

Parallel execution engine for high-throughput task completion

ecomode

Yeachan-Heo

Token-efficient model routing modifier