ML Ops
Machine learning operations
litellm
by Jamie-BitFlight
When calling LLM APIs from Python code. When connecting to llamafile or local LLM servers. When switching between OpenAI/Anthropic/local providers. When implementing retry/fallback logic for LLM calls. When code imports litellm or uses completion() patterns.
earnings-analyst-questions
by OctagonAI
Identify key themes and concerns raised by analysts during earnings calls, including specific analyst attribution and topic categorization.
ai-model-web
by TencentCloudBase
Use this skill when developing browser/Web applications (React/Vue/Angular, static websites, SPAs) that need AI capabilities. Features text generation (generateText) and streaming (streamText) via @cloudbase/js-sdk. Built-in models include Hunyuan (hunyuan-2.0-instruct-20251111 recommended) and DeepSeek (deepseek-v3.2 recommended). NOT for Node.js backend (use ai-model-nodejs), WeChat Mini Program (use ai-model-wechat), or image generation (Node SDK only).
ai-model-wechat
by TencentCloudBase
Use this skill when developing WeChat Mini Programs (小程序, 企业微信小程序, wx.cloud-based apps) that need AI capabilities. Features text generation (generateText) and streaming (streamText) with callback support (onText, onEvent, onFinish) via wx.cloud.extend.AI. Built-in models include Hunyuan (hunyuan-2.0-instruct-20251111 recommended) and DeepSeek (deepseek-v3.2 recommended). API differs from JS/Node SDK - streamText requires data wrapper, generateText returns raw response. NOT for browser/Web apps (use ai-model-web), Node.js backend (use ai-model-nodejs), or image generation (not supported).
ai-model-nodejs
by TencentCloudBase
Use this skill when developing Node.js backend services or CloudBase cloud functions (Express/Koa/NestJS, serverless, backend APIs) that need AI capabilities. Features text generation (generateText), streaming (streamText), AND image generation (generateImage) via @cloudbase/node-sdk ≥3.16.0. Built-in models include Hunyuan (hunyuan-2.0-instruct-20251111 recommended), DeepSeek (deepseek-v3.2 recommended), and hunyuan-image for images. This is the ONLY SDK that supports image generation. NOT for browser/Web apps (use ai-model-web) or WeChat Mini Program (use ai-model-wechat).
atdd
by 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.
jupyter-to-marimo
by marimo-team
Convert a Jupyter notebook (.ipynb) to a marimo notebook (.py).
anywidget-generator
by marimo-team
Generate anywidget components for marimo notebooks.
dspy-debugging-observability
by OmidZamani
This skill should be used when the user asks to "debug DSPy programs", "trace LLM calls", "monitor production DSPy", "use MLflow with DSPy", mentions "inspect_history", "custom callbacks", "observability", "production monitoring", "cost tracking", or needs to debug, trace, and monitor DSPy applications in development and production.
dtg-base
by unclecatvn
Complete reference for DTG Base module utilities and helpers. DTGBase is an abstract model providing common utility methods for date/time handling, barcode generation, timezone conversion, file operations, and more.
olore-codex-latest
by olorehq
Local Codex documentation reference (latest). Use when asked about Codex CLI features, configuration, skills, slash commands, AGENTS.md, MCP integration, or rules.
letta-development-guide
by letta-ai
Comprehensive guide for developing Letta agents, including architecture selection, memory design, model selection, and tool configuration. Use when building or troubleshooting Letta agents.
evolve
by evolving-machines-lab
"Evolve SDK development for TypeScript and Python. Use when building applications with Evolve to run AI agents (Claude, Codex, Gemini, Qwen, Kimi, OpenCode) in secure sandboxes. Triggers: (1) Creating Evolve applications, (2) Configuring agents with skills, Composio, MCP servers, (3) Using Swarm abstractions (map, filter, reduce, bestOf/best_of, verify), (4) Building Pipelines, (5) Structured output with schemas, (6) Session management, streaming, observability, (7) Checkpointing, storage & StorageClient, (8) Cost tracking (per-run and per-session spend), (9) Historical sessions & trace download via sessions() client."
fiftyone-dataset-inference
by voxel51
Run ML model inference (YOLO, YOLOv8, CLIP, SAM, Detectron2, etc.) on FiftyOne datasets. Use when running models, applying detection, classification, segmentation, embeddings, or any model prediction task. Also use for end-to-end workflows that include importing data then running inference.
fiftyone-model-evaluation
by voxel51
Evaluate model predictions against ground truth using COCO, Open Images, or custom protocols. Use when computing mAP, precision, recall, confusion matrices, or analyzing TP/FP/FN examples for detection, classification, segmentation, or regression tasks.
fiftyone-embeddings-visualization
by voxel51
Visualizes datasets in 2D using embeddings with UMAP or t-SNE dimensionality reduction. Use when exploring dataset structure, finding clusters, identifying outliers, or understanding data distribution.
ml-failfast-validation
by terrylica
POC validation patterns to catch issues before committing to long-running ML experiments. TRIGGERS - fail-fast, POC validation, preflight check, experiment validation, schema validation, gradient check, sanity check, smoke test.
create-squad
by VapiAI
Create multi-assistant squads in Vapi with handoffs between specialized voice agents. Use when building complex voice workflows that need multiple assistants with different roles, like triage-to-booking or sales-to-support handoffs.
training-data-curation
by sundial-org
Guidelines for creating high-quality datasets for LLM post-training (SFT/DPO/RLHF). Use when preparing data for fine-tuning, evaluating data quality, or designing data collection strategies.
megatron-memory-estimator
by yzlnew
Estimate GPU memory usage for Megatron-based MoE (Mixture of Experts) and dense models. Use when users need to (1) estimate memory from HuggingFace model configs (DeepSeek-V3, Qwen, etc.), (2) plan GPU resource allocation for training, (3) compare different parallelism strategies (TP/PP/EP/CP), (4) determine if a model fits in available GPU memory, or (5) optimize training configurations for memory efficiency.
slime-user
by yzlnew
Guide for using SLIME (LLM post-training framework for RL Scaling). Use when working with SLIME for reinforcement learning training of language models, including setup, configuration, training execution, multi-turn interactions, custom reward models, tool calling scenarios, or troubleshooting SLIME workflows. Covers GRPO, GSPO, PPO, Reinforce++, multi-agent RL, VLM training, FSDP/Megatron backends, SGLang integration, dynamic sampling, and custom generation functions.
Behavioral Modification
by pjt222
Agent Almanac — a curated reference of executable skills, specialist agents, and teams for AI-assisted development, with interactive visualization
Classification Modeling
by aj-geddes
Build binary and multiclass classification models using logistic regression, decision trees, and ensemble methods for categorical prediction and classification
data-jupyter-python
by Mindrally
Guidelines for data analysis and Jupyter Notebook development with pandas, matplotlib, seaborn, and numpy.