all publishers

brojonat

@brojonat source repo

58 published skills

  1. ▌
    Regression 2 · brojonat bundle
    Build a production-ready regression model on tabular data using XGBoost with conformalized quantile regression for prediction intervals. Use when the user needs to predict a continuous target from tabular features (price, sales, demand, time-to-event, score) and report uncertainty alongside the point estimate. Default to this for any tabular regression task.
    1 repo stars
  2. ▌
    Tabular Eda 2 · brojonat bundle
    Profile a new tabular dataset before modeling. Find target leakage, missing data patterns, high-cardinality categoricals, near-constant features, redundant pairs, and non-linear relationships that Pearson correlation misses. Use whenever the user hands you a CSV or parquet and asks "what should I do with this?" Always run this skill before training any model on data you haven't seen before.
    1 repo stars
  3. ▌
    Unsupervised 2 · brojonat bundle
    Find structure in unlabeled tabular data — clustering with KMeans / GMM / DBSCAN and proper K selection, IsolationForest anomaly detection, and PCA dimensionality reduction. Use when the user has tabular data without a target column and wants to discover segments, find anomalies, or reduce dimensions. Always run tabular-eda first to profile the data.
    1 repo stars
  4. ▌
    LLM Finetuning 2 · brojonat bundle
    Fine-tune small open-weight LLMs locally with Unsloth + QLoRA for text tasks (classification, extraction, translation). Use when input is raw text (not tabular features), user has labeled examples, and wants model ownership without API costs. Default to Gemma-4 E2B; scale up based on VRAM. Always compare zero-shot vs fine-tuned, log every run to MLflow, export to GGUF for llama.cpp.
    1 repo stars
  5. ▌
    Data Labeling QA 2 · brojonat bundle
    Audit an untrusted labeled training set before fine-tuning. Find mislabeled examples with four complementary techniques — provenance/integrity checks (off-by-one, schema drift), cleanlab confident learning (random noise), high-loss monitoring (hard cases), and LLM-as-judge on the flagged subset (systematic confusion). Use before spending GPU on any fine-tune where you don't fully trust the labelers. Works with any classification dataset reshaped to `data` and `untrustworthy_label` columns.
    1 repo stars
  6. ▌
    Binary Classification 2 · brojonat bundle
    Build a production-ready binary classifier on tabular data using XGBoost. Use when the user needs to predict a binary outcome from tabular features (churn, fraud, conversion, default, click). Covers class imbalance, threshold tuning, calibration verification, and SHAP feature importance. Default to this for any binary classification task on tabular data.
    1 repo stars
  7. ▌
    Multiclass Classification 2 · brojonat bundle
    Build a production-ready multiclass classifier on tabular data using XGBoost. Use when the user needs to predict one of several discrete classes from tabular features (product category, sentiment level, customer segment, intent, fault type). Covers per-class metrics, confusion matrix analysis, sample weighting for imbalance, top-K accuracy, and SHAP. Default to this for any tabular multiclass problem.
    1 repo stars
  8. ▌
    Multilabel Classification 2 · brojonat bundle
    Build a production-ready multilabel classifier on tabular data using XGBoost wrapped in MultiOutputClassifier. Use when each row can have multiple labels simultaneously (tags, attributes, gene functions, content moderation categories, multi-disease detection). Covers hamming loss, per-label metrics, label co-occurrence, MultiOutputClassifier vs ClassifierChain, and per-label SHAP. Default to this for any tabular multilabel problem.
    1 repo stars
  9. ▌
    Sklearn Pipeline Template 2 · brojonat bundle
    Build a tabular ML project with scikit-learn Pipelines, MLflow tracking, model artifacts, and a marimo demo notebook. Use when starting any new tabular classification or regression bundle so all bundles share the same plumbing.
    1 repo stars
  10. ▌
    Sqlite 2 · brojonat
    Extend SQLite with application-defined functions and loadable extensions in Python. Use when you need custom SQL logic (transforms, scoring, aggregations) in-process, or need to load/build C extensions for reusable SQLite plugins. Assumes Python stdlib sqlite3. Go equivalents exist (zombiezen/go-sqlite, mattn/go-sqlite3) — look up their APIs at runtime.
    1 repo stars
  11. ▌
    Ibis Data 2 · brojonat
    Use Ibis for database-agnostic data access in Python. Use when writing data queries, connecting to databases (DuckDB, PostgreSQL, SQLite), or building portable data pipelines that should work across backends.
    1 repo stars
  12. ▌
    Go Service 2 · brojonat
    Build Go microservices with stdlib HTTP handlers, sqlc, urfave/cli, and slog. Use when creating or modifying a Go HTTP server, adding routes, middleware, database queries, or CLI commands.
    1 repo stars
  13. ▌
    Scikit Learn 2 · brojonat
    Build ML pipelines with scikit-learn, including preprocessing, cross-validation, hyperparameter tuning, evaluation, and MLflow tracking. Use when training models, building pipelines, or running ML experiments.
    1 repo stars
  14. ▌
    K8S Deployment 2 · brojonat
    Deploy services to Kubernetes with Docker multi-stage builds, kustomize overlays, and Makefile automation. Use when creating Dockerfiles, writing k8s manifests, or setting up deployment pipelines.
    1 repo stars
  15. ▌
    Fastapi Service 2 · brojonat
    Build FastAPI services with JWT auth, structlog, and Prometheus metrics. Use when creating or modifying a Python HTTP server, adding authentication, structured logging, or instrumentation to a FastAPI app.
    1 repo stars
  16. ▌
    Temporal Python 2 · brojonat
    Build Temporal applications in Python using the temporalio SDK. Use when creating workflows, activities, workers, clients, signals, queries, updates, child workflows, timers, retry policies, saga/compensation patterns, testing, or any durable execution pattern in Python.
    1 repo stars
  17. ▌
    Sqlite · brojonat bundle
    Extend SQLite with application-defined functions and loadable extensions in Python. Use when you need custom SQL logic (transforms, scoring, aggregations) in-process, or need to load/build C extensions for reusable SQLite plugins. Assumes Python stdlib sqlite3. Go equivalents exist (zombiezen/go-sqlite, mattn/go-sqlite3) — look up their APIs at runtime.
    1 repo stars
  18. ▌
    Ibis Data · brojonat bundle
    Use Ibis for database-agnostic data access in Python. Use when writing data queries, connecting to databases (DuckDB, PostgreSQL, SQLite), or building portable data pipelines that should work across backends.
    1 repo stars
  19. ▌
    Go Service · brojonat bundle
    Build Go microservices with stdlib HTTP handlers, sqlc, urfave/cli, and slog. Use when creating or modifying a Go HTTP server, adding routes, middleware, database queries, or CLI commands.
    1 repo stars
  20. ▌
    Scikit Learn · brojonat bundle
    Build ML pipelines with scikit-learn, including preprocessing, cross-validation, hyperparameter tuning, evaluation, and MLflow tracking. Use when training models, building pipelines, or running ML experiments.
    1 repo stars
  21. ▌
    K8S Deployment · brojonat bundle
    Deploy services to Kubernetes with Docker multi-stage builds, kustomize overlays, and Makefile automation. Use when creating Dockerfiles, writing k8s manifests, or setting up deployment pipelines.
    1 repo stars
  22. ▌
    Fastapi Service · brojonat bundle
    Build FastAPI services with JWT auth, structlog, and Prometheus metrics. Use when creating or modifying a Python HTTP server, adding authentication, structured logging, or instrumentation to a FastAPI app.
    1 repo stars
  23. ▌
    Temporal Python · brojonat bundle
    Build Temporal applications in Python using the temporalio SDK. Use when creating workflows, activities, workers, clients, signals, queries, updates, child workflows, timers, retry policies, saga/compensation patterns, testing, or any durable execution pattern in Python.
    1 repo stars
  24. ▌
    Sklearn Pipeline Template · brojonat bundle
    Build a tabular ML project with scikit-learn Pipelines, MLflow tracking, model artifacts, and a marimo demo notebook. Use when starting any new tabular classification or regression bundle so all bundles share the same plumbing.
    1 repo stars
  25. ▌
    Building Bundles · brojonat
    How to design, build, validate, and ship a new ManagerPack skill bundle. Use when starting any new bundle in the studio. Captures the workflow from picking a model family through to a published, marimo-validated, MLflow-tracked deliverable.
    1 repo stars
  26. ▌
    Pymc Inference Template · brojonat bundle
    Build a Bayesian inference project with PyMC, NUTS sampling, ArviZ diagnostics, MLflow tracking, idata persistence, and a marimo demo notebook. Use when starting any new Bayesian bundle so all bundles share the same plumbing.
    1 repo stars
  27. ▌
    Air Go · brojonat
    Hot-reload Go apps with cosmtrek/air during development. Use when setting up dev workflows for Go HTTP servers, configuring .air.toml, or debugging hot-reload issues with SQLite, port binding, or file watchers.
    1 repo stars
  28. ▌
    Honker · brojonat
    Add cross-process pub/sub, durable task queues, event streams, and scheduled jobs to a SQLite database using the honker extension. Use when you need Postgres NOTIFY/LISTEN semantics, background job processing, or event-driven architecture without leaving SQLite. Supports Python, Node, Go, Rust, Ruby, Bun, and Elixir via language bindings, or raw SQL via the loadable extension.
    1 repo stars
  29. ▌
    Datastar · brojonat
    Build real-time hypermedia web apps with Datastar — the backend owns state and pushes HTML down one long-lived SSE stream while writes are short-lived requests that render nothing. Use when working with `data-*` attributes, `datastar-patch-elements` / `datastar-patch-signals` SSE events, signals, `@get`/`@post` actions, or the `datastar-py` / `datastar-go` SDKs. Also use when a task calls for live-updating or multiplayer UI without a SPA.
    1 repo stars
  30. ▌
    Ducklake · brojonat
    Work with DuckLake, an open lakehouse format built on DuckDB. Use when creating or querying DuckLake tables, managing snapshots, time travel, schema evolution, partitioning, or lakehouse maintenance operations.
    1 repo stars
  31. ▌
    Bubbletea · brojonat
    Build terminal user interfaces (TUIs) in Go with the Charm Bubble Tea framework (Elm-style Model/Update/View). Use when creating or modifying interactive CLI apps, dashboards, wizards, pickers, progress UIs, pagers, or any Go program that uses github.com/charmbracelet/bubbletea, github.com/charmbracelet/bubbles, or github.com/charmbracelet/lipgloss. Triggers on tasks involving tea.Model, tea.Cmd, tea.Msg, tea.KeyMsg, spinners, text inputs, lists, tables, viewports, progress bars, paginators, or styling terminal output.
    1 repo stars
  32. ▌
    Python CLI · brojonat
    Build Python CLIs with Click using subcommand groups. Use when creating or modifying a Python command-line interface, adding subcommands, or structuring a CLI package.
    1 repo stars
  33. ▌
    Redfin API · brojonat
    Interact with Redfin's unofficial stingray API for property search, listing data, AVM estimates, and property history. Use when writing code to search listings, fetch property details, parse Redfin responses, or build GISCSV queries.
    1 repo stars
  34. ▌
    Regression · brojonat bundle
    Build a production-ready regression model on tabular data using XGBoost with conformalized quantile regression for prediction intervals. Use when the user needs to predict a continuous target from tabular features (price, sales, demand, time-to-event, score) and report uncertainty alongside the point estimate. Default to this for any tabular regression task.
    1 repo stars
  35. ▌
    Urfave CLI · brojonat
    Build Go command-line applications with urfave/cli v3 — commands, subcommands, flags, env var binding, Before/After hooks, shell completion, and testing. Use when creating or modifying a Go CLI entry point (main.go), adding subcommands, wiring flags to environment variables, customizing help output, or testing CLI behavior. Covers the cli.Command declarative API, flag types (StringFlag, IntFlag, BoolFlag, DurationFlag, StringSliceFlag, TimestampFlag, etc.), cli.Exit exit codes, and context.Context propagation into actions.
    1 repo stars
  36. ▌
    Tabular Eda · brojonat bundle
    Profile a new tabular dataset before modeling. Find target leakage, missing data patterns, high-cardinality categoricals, near-constant features, redundant pairs, and non-linear relationships that Pearson correlation misses. Use whenever the user hands you a CSV or parquet and asks "what should I do with this?" Always run this skill before training any model on data you haven't seen before.
    1 repo stars
  37. ▌
    Temporal Go · brojonat
    Build Temporal workflow applications in Go. Use when creating or modifying Temporal workflows, activities, workers, clients, signals, queries, updates, retry policies, saga patterns, or writing Temporal tests.
    1 repo stars
  38. ▌
    Pg Messaging · brojonat
    Build pub/sub and task queue services using PostgreSQL as the backend. Use when implementing messaging primitives, log-based consumer groups, job queues with SKIP LOCKED, or replacing external message brokers (Kafka, RabbitMQ, SQS) with Postgres.
    1 repo stars
  39. ▌
    Resend Email · brojonat
    Send transactional emails via Resend using SMTP or HTTP API. Use when integrating Resend for magic links, scheduled emails, cancellation, or listing sent emails. Covers API keys, SMTP config, scheduled_at, and Go integration patterns.
    1 repo stars
  40. ▌
    Unsupervised · brojonat bundle
    Find structure in unlabeled tabular data — clustering with KMeans / GMM / DBSCAN and proper K selection, IsolationForest anomaly detection, and PCA dimensionality reduction. Use when the user has tabular data without a target column and wants to discover segments, find anomalies, or reduce dimensions. Always run tabular-eda first to profile the data.
    1 repo stars
  41. ▌
    Data Flywheel · brojonat
    Build a data flywheel service that ingests labeled data into SQLite, triggers async model training via honker queues after every N records, and hot-swaps the active model for inference. Use when you need a self-improving ML service backed by a single SQLite database with no external broker or scheduler.
    1 repo stars
  42. ▌
    Openai Agents · brojonat
    Build multi-agent systems with the OpenAI Agents SDK, including tool definitions, handoffs, context management, and webhook validation. Use when creating OpenAI agent flows, defining tools, or handling agent handoffs in Python or Go.
    1 repo stars
  43. ▌
    Litestream K8S · brojonat
    Run SQLite with Litestream replication to S3-compatible storage (Cloudflare R2, etc.) on Kubernetes. Use when adding persistent SQLite to a containerized app, setting up Litestream, or doing point-in-time database recovery.
    1 repo stars
  44. ▌
    LLM Finetuning · brojonat bundle
    Fine-tune small open-weight LLMs locally with Unsloth + QLoRA for text tasks (classification, extraction, translation). Use when input is raw text (not tabular features), user has labeled examples, and wants model ownership without API costs. Default to Gemma-4 E2B; scale up based on VRAM. Always compare zero-shot vs fine-tuned, log every run to MLflow, export to GGUF for llama.cpp.
    1 repo stars
  45. ▌
    Playwright E2e · brojonat
    Write Playwright end-to-end tests for web apps. Use when setting up e2e tests, testing auth flows, or writing browser automation scripts. Covers project setup, test patterns, auth bypass for dev mode, and integration with Go/backend servers.
    1 repo stars
  46. ▌
    Marimo Notebook · brojonat
    Author marimo notebooks with conventions for interactive scatter exploration. Use when creating a new marimo notebook, choosing how to run marimo locally, or wiring up jscatter scatter plots with lasso selection feeding a table below the plot.
    1 repo stars
  47. ▌
    Bayesian Bandits · brojonat bundle
    Implement Thompson sampling for multi-armed and contextual bandits. Use when the user wants to adaptively allocate traffic across variants (ads, recommendations, content, pricing) to minimize regret instead of running a fixed-allocation A/B test. Covers Bernoulli bandits, contextual bandits, regret analysis, and comparison with epsilon-greedy and UCB.
    1 repo stars
  48. ▌
    Data Labeling QA · brojonat bundle
    Audit an untrusted labeled training set before fine-tuning. Find mislabeled examples with four complementary techniques — provenance/integrity checks (off-by-one, schema drift), cleanlab confident learning (random noise), high-loss monitoring (hard cases), and LLM-as-judge on the flagged subset (systematic confusion). Use before spending GPU on any fine-tune where you don't fully trust the labelers. Works with any classification dataset reshaped to `data` and `untrustworthy_label` columns.
    1 repo stars
  49. ▌
    Parquet Analysis · brojonat bundle
    Analyze parquet files using Python and Ibis. Use when the user wants to explore, transform, or analyze parquet data files, perform aggregations, joins, or export results. Works with local parquet files and provides database-agnostic data operations.
    1 repo stars
  50. ▌
    Pyproject Config · brojonat
    Configure Python projects with pyproject.toml including build system, console scripts, ruff linting, and pytest. Use when setting up a new Python project, configuring tooling, or adding entry points.
    1 repo stars
  51. ▌
    Bayesian Ab Testing · brojonat bundle
    Run a Bayesian A/B test on conversion data using PyMC. Use when the user wants to compare two variants (landing pages, emails, pricing, UI changes) and decide which to ship using posterior probabilities and expected loss instead of p-values. Covers Beta-Binomial model, ROPE, expected loss, sample-size guidance, and ArviZ diagnostics.
    1 repo stars
  52. ▌
    Bayesian Regression · brojonat bundle
    Fit Bayesian regression models with PyMC using the Hogg approach — start simple, diagnose problems, upgrade the likelihood. Use when the user needs regression with proper uncertainty quantification, heteroscedastic errors, outlier robustness, or model comparison. Covers Normal, Student-t, and GLM likelihoods with ArviZ diagnostics and LOO-CV.
    1 repo stars
  53. ▌
    Binary Classification · brojonat bundle
    Build a production-ready binary classifier on tabular data using XGBoost. Use when the user needs to predict a binary outcome from tabular features (churn, fraud, conversion, default, click). Covers class imbalance, threshold tuning, calibration verification, and SHAP feature importance. Default to this for any binary classification task on tabular data.
    1 repo stars
  54. ▌
    Bayesian Mixture Models · brojonat bundle
    Fit Bayesian Gaussian mixture models with PyMC for soft clustering with full uncertainty. Use when the user needs probabilistic cluster assignments, latent heterogeneity modeling, zero-inflated data, or principled model selection for number of clusters. Covers Dirichlet priors, label switching, LOO-CV model comparison, and applications beyond clustering.
    1 repo stars
  55. ▌
    Multiclass Classification · brojonat bundle
    Build a production-ready multiclass classifier on tabular data using XGBoost. Use when the user needs to predict one of several discrete classes from tabular features (product category, sentiment level, customer segment, intent, fault type). Covers per-class metrics, confusion matrix analysis, sample weighting for imbalance, top-K accuracy, and SHAP. Default to this for any tabular multiclass problem.
    1 repo stars
  56. ▌
    Multilabel Classification · brojonat bundle
    Build a production-ready multilabel classifier on tabular data using XGBoost wrapped in MultiOutputClassifier. Use when each row can have multiple labels simultaneously (tags, attributes, gene functions, content moderation categories, multi-disease detection). Covers hamming loss, per-label metrics, label co-occurrence, MultiOutputClassifier vs ClassifierChain, and per-label SHAP. Default to this for any tabular multilabel problem.
    1 repo stars
  57. ▌
    Bayesian Decision Analysis · brojonat bundle
    Turn posterior distributions into optimal actions using loss functions, expected value of information, and the newsvendor framework. Use when the user has a Bayesian model and needs to make a decision under uncertainty — pricing, inventory, ship-or-wait, resource allocation. Covers EVPI, EVSI, custom loss functions, and asymmetric cost structures.
    1 repo stars
  58. ▌
    Statistical Process Control · brojonat bundle
    Monitor a metric over time with process behaviour charts (XmR / control charts) to separate routine variation from real process change. Use whenever the user wants to know "is this number unusual?", set alerting thresholds on a KPI or operational metric, detect anomalies or regressions in a time series of measurements, build a control chart, or replace ad-hoc "it looks high this week" judgments with something principled. Default to this for metric monitoring and threshold-setting tasks — even when the user doesn't say "SPC" or "control chart" — including dashboards, SLO/error-rate watching, manufacturing quality data, and weekly business reviews.
    1 repo stars