AI & ML

jmix-framework Skill

Create Liquibase changelogs that exactly match Jmix entity model changes, and register database changelogs supplied by Jmix add-ons that own persistent entities.

pixb Bundle

Guide for creating high-quality MCP (Model Context Protocol) servers that enable LLMs to interact with external services through well-designed tools. Use when building MCP servers to integrate external APIs or services, whether in Python (FastMCP) or Node/TypeScript (MCP SDK).

ai-analyst-lab Skill

Initialize session context, resolve the active dataset and context source, load resident instructions, and inventory the context available for question-specific selection. Run at the start of every session and again after /connect-data or /switch-dataset. Handles missing files gracefully, so running it when unsure is harmless.

panaversity Skill

Helps users discover and install agent skills when they ask questions like "how do I do X", "find a skill for X", "is there a skill that can...", or express interest in extending capabilities. This skill should be used when the user is looking for functionality that might exist as an installable skill.

pretend-to Skill

Expert guide for discovering, validating, and installing Agent Skills into MioChat. Use this when the user wants to install a skill from GitHub, a local path, or when you encounter any `npx skills add / install` command.

pretend-to Bundle

Expert tool for managing MioChat system configurations, LLM providers, and storage settings. Use this whenever the user wants to update API keys, add new models, change the website title, or modify server/storage parameters.

pretend-to Skill

SkillHub 商店 CLI 封装 — 浏览、搜索、安装来自 skillhub.club 社区的 80,000+ 个 Agent Skills。当用户说「去 SkillHub 找点技能」「搜一下 xxx skill」「装个 yyy」「SkillHub 上有什么好玩的」或者想从 SkillHub 市场获取技能时，一定要用这个 skill。也适用于用户想逛社区市场、看趋势、搜特定类目的技能。

pretend-to Bundle

Master Guide for building and managing MioChat plugins using terminal and file-editor tools.

pretend-to Skill

掌握 MioChat 后台条件哨兵（Sentinel）编写与部署技能。当用户需要对行情走势、价格突破、指标异常、系统状态、文件变更或外部事件进行后台自动巡逻并在条件达成时唤醒 Agent 时使用。

stanfish06 Skill

Distributed Python compute with Ray — @ray.remote tasks/actors for cluster-scale parallelism, Ray Data for large-batch preprocessing, Ray Train for distributed model training (DDP/FSDP/DeepSpeed), Ray Tune for scalable hyperparameter search, and Ray Serve for model serving. Use when scaling a Python workload (docking screens, million-cell atlas preprocessing, hyperparameter sweeps, multi-GPU training) from a laptop to a multi-node cluster with minimal code changes. Ray Tune can use optuna as a search algorithm; Ray Train wraps pytorch-lightning-style training loops.

stanfish06 Bundle

Lightweight WSI tile extraction and preprocessing. Use for basic slide processing, tissue detection, tile extraction, and stain normalization for H&E images. Best for simple pipelines, dataset preparation, and quick tile-based analysis. For advanced spatial proteomics, multiplexed imaging, or deep learning pipelines use pathml.

stanfish06 Bundle

Expert-thinking profile for Logician (proof theory / model theory / computability / set theory / formal verification (Lean, Coq, Z3)): Expert profile for logician — see AGENTS.md for field-specific methods and failure modes.

stanfish06 Bundle

Core agent-browser usage guide. Read this before running any agent-browser commands. Covers the snapshot-and-ref workflow, navigating pages, interacting with elements (click, fill, type, select), extracting text and data, taking screenshots, managing tabs, handling forms and auth, waiting for content, running multiple browser sessions in parallel, and troubleshooting common failures. Use when the user asks to interact with a website, fill a form, click something, extract data, take a screenshot, log into a site, test a web app, or automate any browser task.

stanfish06 Skill

DSPy declarative framework for automatic prompt optimization treating prompts as code with systematic evaluation and compilers

stanfish06 Bundle

Bayesian modeling with PyMC. Build hierarchical models, MCMC (NUTS), variational inference, LOO/WAIC comparison, posterior checks, for probabilistic programming and inference.

stanfish06 Bundle

Model interpretability and explainability using SHAP (SHapley Additive exPlanations). Use this skill when explaining machine learning model predictions, computing feature importance, generating SHAP plots (waterfall, beeswarm, bar, scatter, force, heatmap), debugging models, analyzing model bias or fairness, comparing models, or implementing explainable AI. Works with tree-based models (XGBoost, LightGBM, Random Forest), deep learning (TensorFlow, PyTorch), linear models, and any black-box model.

twells89 Bundle

Build, register, host, embed, and data-bind a bespoke Sigma custom plugin (@sigmacomputing/plugin) to recreate a source visualization for which Sigma has no native chart/KPI/table equivalent — a radial gauge, a custom heatmap, a sankey, or any bespoke viz kind outside Sigma's native element set. **Use when a source viz has no native Sigma equivalent and should be recreated as a bespoke plugin** — not when a native Sigma chart, KPI, or table kind already covers it (that's the `sigma-workbooks` skill). Covers the full lifecycle: writing the single-file plugin, registering it via `POST /v2/plugins`, hosting it, embedding it in a workbook spec bound to real data, and verifying value parity. Ships a worked example (a radial gauge / "value vs. target" plugin) and the `plugin_embed` emitter. Requires an SIGMA_API_TOKEN — obtain via the sigma-api skill first.

stanfish06 Skill

A Just-In-Time (JIT) compiler for Python that translates a subset of Python and NumPy code into fast machine code. Developed by Anaconda, Inc. Highly effective for accelerating loops, custom mathematical functions, and complex numerical algorithms. Use for @njit, @vectorize, prange, cuda.jit, numba.typed, JIT compilation, parallel loops, GPU acceleration with CUDA, Monte Carlo simulations, numerical algorithms, and high-performance Python computing.

stanfish06 Bundle

Observe the user's screen via screenpipe, detect repeated research workflows, match them against existing scientific-agent-skills, and draft new skills (or composition recipes that chain existing ones) for the patterns not yet covered. Use when the user asks to analyze their recent work and propose skills based on what they actually do. Requires the screenpipe daemon (https://github.com/screenpipe/screenpipe) running locally on port 3030 — the skill has no other data source and will refuse to run if screenpipe is unreachable. All detection runs locally; only redacted cluster summaries reach the LLM.

stanfish06 Bundle

Biology research tools reference. Always available inside agent containers.

stanfish06 Bundle

Vercel AI SDK expert guidance. Use when building AI-powered features — chat interfaces, text generation, structured output, tool calling, agents, MCP integration, streaming, embeddings, reranking, image generation, or working with any LLM provider.

stanfish06 Bundle

跨版本符号迁移与二进制差分。当你有旧版本的符号/逆向结果，需要快速迁移到新版本时使用。 适用场景：内核缺 PDB 用旧版符号推导、程序更新后批量迁移函数名、应用更新后快速定位新偏移。 核心方法：用 LLM 做结构化差异比对，程序化输入输出，成本极低（200 函数 ~1 元）。 触发关键词：符号迁移、bindiff、跨版本、PDB 缺失、函数偏移迁移、symbol migration、binary diff、版本对比。

stanfish06 Bundle

Expert-thinking profile for Statistician (applied inference / experimental design / Bayesian-frequentist / causal & survey methods / SAP-driven consulting): Reasons from estimands, generative-model assumptions, and a budgeted Type I/II error tradeoff through analysis plans (SAP, ICH E9(R1) estimands), mixed models, multiple imputation under MCAR/MAR/MNAR, and Benjamini-Hochberg FDR while treating naive post-selection SEs, unadjusted multiplicity, ignored clustering in...

stanfish06 Bundle

Use when Codex is already in the threat-modeling phase of a security scan, the user explicitly invokes $threat-model, or the user explicitly asks to create, update, or persist a repository threat model. Do not use as the primary trigger for full PR, commit, branch, patch, or repository scans.

stanfish06 Bundle

Expert-thinking profile for Agroecologist (field ecology / soil health / participatory on-farm trials / landscape GIS / agroecology transitions (FAO 10 Elements)): Reasons from socio-ecological farm systems, functional diversity, soil-biology-mediated fertility, and yield-service trade-offs through mother-baby and mixed-model trials, N/P/C mass balances, PLFA/amplicon and pollinator surveys, and NDVI/FRAGSTATS landscape analysis, while treating edge-effect and plot-size...

stanfish06 Bundle

Expert-thinking profile for AI Researcher (empirical ML / experiment design / evaluation methodology / reproducibility / LLM & RL / trustworthiness (robustness, fairness, safety)): Reasons from data generating processes, inductive biases, and compute-data-algorithm trade-offs through train/val/test discipline, seed sweeps, ablation ladders, and standards like NeurIPS reproducibility checklists, model cards, and lm-eval-harness, while treating data leakage (Kapoor & Narayanan taxonomy), benchmark...

stanfish06 Skill

LangGraph is a low-level orchestration framework for building stateful LLM agents and workflows as explicit graphs — typed state with reducers, nodes/edges/conditional routing, checkpointer-backed persistence and thread memory, human-in-the-loop interrupts, and streaming. Use when building an agent or multi-step LLM workflow that needs explicit control flow (branching, loops, parallel fan-out), durable/resumable execution, approval gates, or multi-agent handoffs — or when debugging StateGraph, checkpointer, interrupt, or create_react_agent-deprecation issues. Targets LangGraph 1.x.

stanfish06 Bundle

Local document and PDF parsing with spatial text and bounding boxes. Use for extracting text from PDFs, DOCX, Office files, and images; OCR on scans; layout-preserved JSON for RAG; batch-ingesting paper folders; or page screenshots for multimodal agents — even when the user does not name liteparse. Prefer over MarkItDown when you need bboxes, fast local parsing, or PNG page renders; prefer over the pdf skill for merge/split/forms.

stanfish06 Bundle

Expert-thinking profile for Cosmologist (theoretical / observational / computational cosmology): Reasons from Friedmann/ΛCDM, r_s and transfer functions, and multi-probe inference (Planck CMB, DESI BAO, lensing, Pantheon+ SNe) through CAMB/CLASS, Cobaya, and GetDist while treating photo-z–IA coupling, CMB foreground pipelines, H0/S8 tensions, and emulator extrapolation as first-class failure modes.

stanfish06 Bundle

Expert-thinking profile for Histologist (wet-lab / clinical & research histology): Reasons from fixation-through-stain pre-analytical chain (NBF, grossing, processing, embedding orientation, microtomy); validates H&E pH/QC, CAP IHC (90% concordance, predictive scoring systems), RNAscope controls, WSI (60-case validation), and treats floaters, autolysis, crush, ice-crystal, and decalcification...

stanfish06 Skill

Query NCBI GEO for gene expression datasets. Use when user asks about RNA-seq datasets, microarray data, expression data, GEO accessions, or finding public datasets. Triggers on "geo", "gene expression omnibus", "expression dataset", "RNA-seq dataset", "microarray dataset", "GSE", "GDS".

stanfish06 Bundle

Expert-thinking profile for Hydrologist (rainfall-runoff modeling / flood forecasting / watershed hydrology / cold-regions & ecohydrology / uncertainty quantification): Reasons from hydrologic-cycle closure (P = ET + Q + ΔS + I), runoff-generation mechanisms, and channel routing through HEC-HMS, HEC-RAS, the National Water Model, and split-sample KGE/NSE/PBIAS calibration, while treating post-flood rating-curve shifts, radar QPE bias, snow/rain misclassification, and non-stationarity...

stanfish06 Bundle

Debug LLM applications using the Phoenix CLI. Fetch traces, analyze errors, structure trace review with open coding and axial coding, inspect datasets, review experiments, query annotation configs, and use the GraphQL API. Use whenever the user is analyzing traces or spans, investigating LLM/agent failures, deciding what to do after instrumenting an app, building failure taxonomies, choosing what evals to write, or asking "what's going wrong", "what kinds of mistakes", or "where do I focus" — even without naming a technique.

stanfish06 Bundle

Vercel AI Gateway expert guidance. Use when configuring model routing, provider failover, cost tracking, or managing multiple AI providers through a unified API.

stanfish06 Bundle

Use when creating or configuring a persistent HeyGen avatar or digital twin for the agent, the user, or a named presenter, including prompt-based avatar creation, photo-based identity setup, voice selection, or passing an avatar identity to video generation. If a request combines avatar creation with video generation, use this before the video skill. Do not use for video generation alone, translation, TTS-only tasks, or streaming avatars.

stanfish06 Bundle

Generates an end-of-day wrap-up using the Superhuman Mail MCP server — identifies open loops, unanswered emails, and action items from your day so you can leave work with a clear head. Use this skill whenever someone asks to "wrap up my day", "what's still open in my inbox", "end of day summary", "what do I still need to do", "any emails I missed today", "open loops in my inbox", "summarize my day", "what didn't I respond to", "daily review", "close out my day", "what fell through the cracks", or any variation of wanting to know what's unfinished before signing off. Also trigger when someone says "before I log off", "anything I'm forgetting", "daily debrief", "what should I tackle tomorrow", or wants an accounting of their email activity for the day. if someone wants to review what happened and what's still pending at the end of their workday,