ML Ops
Machine learning operations
role-architect:system-design
by rnavarych
System design expertise including requirements analysis, C4 model diagrams, sequence diagrams, data flow diagrams, trade-off documentation, capacity estimation, distributed systems theory, load balancing algorithms, caching architectures, message-driven and stream processing architectures, data pipeline design, search architecture, and system design patterns for common internet-scale systems (URL shorteners, chat, news feed, rate limiters).
data_transform
by vuralserhat86
Transform raw data into analytical assets using ETL/ELT patterns, SQL (dbt), Python (pandas/polars/PySpark), and orchestration (Airflow). Use when building data pipelines, implementing incremental models, migrating from pandas to polars, or orchestrating multi-step transformations with testing and quality checks.
apple-foundation-models
by ios-agent
Use this skill when working with Apple's Foundation Models framework for on-device AI and LLM capabilities in iOS/macOS apps
pydantic-ai-agents
by Fuenfgeld
"Build and debug Pydantic AI agents using best practices for dependencies, dynamic system prompts, tools, and structured output validation. Use when the user wants to: (1) Create a new Pydantic AI agent, (2) Debug or fix an existing agent, (3) Add features like tools, validators, or dynamic prompts, (4) Integrate OpenRouter for multi-model access, (5) Add Logfire for debugging/observability, (6) Structure agent architecture with dependency injection."
advanced-evaluation
by xfstudio
This skill should be used when the user asks to "implement LLM-as-judge", "compare model outputs", "create evaluation rubrics", "mitigate evaluation bias", or mentions direct scoring, pairwise comparison, position bias, evaluation pipelines, or automated quality assessment.
swiftui
by ios-agent
SwiftUI framework for building user interfaces
video-understand
by jrusso1020
Video understanding and transcription with intelligent multi-provider fallback. Use when: (1) Transcribing video or audio content, (2) Understanding video content including visual elements and scenes, (3) Analyzing YouTube videos by URL, (4) Extracting information from local video files, (5) Getting timestamps, summaries, or answering questions about video content. Automatically selects the best available provider based on configured API keys - prefers full video understanding (Gemini/OpenRouter) over ASR-only providers. Supports model selection per provider.
model-thinking
by kcchien
Mental models toolkit for clearer thinking, better decisions, and problem-solving. Use when users face complex problems, need decision support, want to analyze situations from multiple angles, organize information, understand systems, predict outcomes, or learn about specific mental models. Triggers include phrases like "help me think through", "analyze this problem", "what models apply here", "how should I decide", "evaluate options", or direct model references (e.g., "use second-order thinking", "apply inversion"). 中文觸發：「思維模型」、「幫我分析」、「決策分析」、「多角度思考」、「怎麼判斷」、「幫我想清楚」、「系統思考」、「風險評估」。
optimize-prompt
by jbrukh
Optimize a prompt through a critique-compress pipeline with semantic equivalence verification at each stage. Applies think-critically to improve the prompt, then compress-prompt to reduce it, validating that behavior is preserved after each transformation.
ai-cost-optimizer
by YuniorGlez
"Master of LLM Economic Orchestration, specialized in Google GenAI (Gemini 3), Context Caching, and High-Fidelity Token Engineering."
write-article
by jbrukh
Write accessible, engaging op-ed-style articles in the Brukhman voice, authoritative but conversational, technically grounded, with progressive narrative structure.
movement-science-stats
by jjodx
Statistical quality checklist for movement science and neuroscience research. Auto-triggers when analyzing data, interpreting results, running statistics, writing results sections, or reviewing analysis code. Based on Makin & Orban de Xivry (2019, eLife).
multi-model-meta-analysis
by petekp
Synthesize outputs from multiple AI models into a comprehensive, verified assessment. Use when: (1) User pastes feedback/analysis from multiple LLMs (Claude, GPT, Gemini, etc.) about code or a project, (2) User wants to consolidate model outputs into a single reliable document, (3) User needs conflicting model claims resolved against actual source code. This skill verifies model claims against the codebase, resolves contradictions with evidence, and produces a more reliable assessment than any single model.
codex-review
by yelban
跨模型對抗式審查：用 Codex 審查 Claude 的計畫或程式碼產出。 異質模型產生真正的對抗張力，抓住同模型自審遺漏的問題。 自動 VERDICT 迴圈（最多 3 輪），產出結構化 issues 清單。 支援 --model 參數切換模型（預設 gpt-5.3-codex）。 觸發詞：/codex-review、cross-review、對抗審查
model-first-reasoning
by petekp
Apply Model-First Reasoning (MFR) to code generation tasks. Use when the user requests "model-first", "MFR", "formal modeling before coding", "model then implement", or when tasks involve complex logic, state machines, constraint systems, or any implementation requiring formal correctness guarantees. Enforces strict separation between modeling and implementation phases.
openrouter
by DimitriGilbert
Expert OpenRouter API assistant for AI agents. Use when making API calls to OpenRouter's unified API for 400+ AI models. Covers chat completions, streaming, tool calling, structured outputs, web search, embeddings, multimodal inputs, model selection, routing, and error handling.
x-algo-pipeline
by CloudAI-X
Explain the complete X recommendation algorithm pipeline. Use when users ask how posts are ranked, how the algorithm works, or want an overview of the recommendation system.
affiliate-onboarding
by dmend3z
This skill guides users in setting up a robust affiliate onboarding system. It covers welcome sequences, swipe file creation, training curriculum, compliance guidelines, resource library setup, first promotion guidance, and communication templates to transform new affiliates into high-performing partners.
dlt-extract
by dtsong
"Use this skill when building DLT pipelines for file-based or consulting data extraction. Covers Excel/CSV/SharePoint ingestion via DLT, destination swapping (DuckDB dev to warehouse prod), schema contracts for cleaning, and portable pipeline patterns. Common phrases: \"dlt pipeline for files\", \"extract Excel with dlt\", \"portable data pipeline\", \"dlt filesystem source\". Do NOT use for core DLT concepts like REST API or SQL database sources (use data-integration) or pipeline scheduling (use data-pipelines)."
bayesian-estimation
by James-Traina
Guide for Bayesian estimation and inference in quantitative social science. Use when the user is specifying priors, running MCMC, diagnosing chain convergence, or reporting posterior summaries — including hierarchical models, Bayesian structural models, and small-sample settings where priors regularize. Triggers on "Bayesian estimation", "Bayesian inference", "MCMC", "Markov chain Monte Carlo", "Stan", "PyMC", "NumPyro", "prior", "posterior", "credible interval", "Bayesian structural", "Bayesian BLP", "Bayesian DSGE", "hierarchical model", "random effects Bayesian", "posterior predictive check", "Bayes factor", "prior predictive check", "NUTS", "HMC", "Hamiltonian Monte Carlo", "R-hat", "rhat", "effective sample size", "ESS", "Bayesian calibration", "posterior distribution", "prior elicitation", "weakly informative prior", "brms", "rstanarm", "cmdstanpy", "pymc", "arviz".
config-management
by cklxx
配置管理 — 查询/修改 agent 配置参数（YAML 配置文件）。
compound-catalog
by James-Traina
Capture solved research problems as categorized documentation with YAML frontmatter for fast lookup. Use when a methodological, estimation, or data problem has been solved and should be documented for future reference. Triggers on "that worked", "it's fixed", "problem solved", "estimation converges now", "proof is complete", "pipeline runs", or when /workflows:compound invokes solution documentation. Also triggered by "document this solution", "save this fix", "log this resolution".
MLIP Simulation Skill
by fl-sean03
Phonopy: https://phonopy.github.io/phonopy/
scikit-survival
by kjgarza
Comprehensive toolkit for survival analysis and time-to-event modeling in Python using scikit-survival. Use this skill when working with censored survival data, performing time-to-event analysis, fitting Cox models, Random Survival Forests, Gradient Boosting models, or Survival SVMs, evaluating survival predictions with concordance index or Brier score, handling competing risks, or implementing any survival analysis workflow with the scikit-survival library.