posit-dev

Launch Code OSS (VS Code from sources) into an isolated throwaway profile with unique debug ports so you can drive it with @playwright/cli AND attach a Node debugger via dap-cli in the same session. Use when working on VS Code itself and you want to interact…

This skill should be used when merging upstream changes from vscode-server into the Positron IDE repository. Invoke it when the git repository contains the conflicted changes from an upstream merge.

Use when writing, recording, updating, or troubleshooting the agent host end-to-end tests under src/vs/platform/agentHost/test/node/e2e (black-box tests that drive the whole agent host over the AHP protocol, using a CapiReplayProxy record/replay system for…

Analyze Agent Host debug log exports. Use when given an ah-logs or ahp-logs zip/folder, an Export Agent Host Debug Logs bundle, events.jsonl, AHP JSONL transport logs, Agent Host.log, remote-agenthost.log, or copilot-logs.

Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.

Classify and record explicit corrective feedback without turning skills or instructions into append-only knowledge dumps.

Use whenever adding, modifying, or reviewing any Copilot, agent, LLM, AI, tool, permission, sandbox, MCP, model, telemetry, feature-gate, setting, configuration, or enterprise control—especially anything an organization or administrator may need to manage.…

Core principles and workflow router for changes to the Agents Window under src/vs/sessions.

Creates a pull request from current changes, monitors GitHub CI, and debugs any failures until CI passes. Activate when the user says "create pr", "make a pr", "open pull request", "submit pr", "pr for these changes", or wants to get their current work into a…

Deploy or publish Python and R content to a Posit Connect server using rsconnect-python or the R rsconnect package. Handles interactive apps and dashboards, web APIs, rendered documents, and prepared bundles/manifests. Use whenever the user asks to deploy,…

Rigorously review code or pull requests for correctness, security, accessibility, maintainability, tests, and edge cases. Use when users request a critical code review, want a guided walkthrough of findings, need implementer-facing feedback, or want to…

Create and manage todo tracking documents for features, bugs, and multi-step tasks. Use when starting new work that benefits from a persistent record of decisions, progress, and context.

Set a tracking document as the source of truth for the current feature or task. Use when starting work on a feature, bug fix, or multi-step task that benefits from a persistent record of decisions, discoveries, and progress. Keeps the document updated as work…

Guidance for managing R package lifecycle according to tidyverse principles using the lifecycle package. Use when: (1) Setting up lifecycle infrastructure in a package, (2) Deprecating functions or arguments, (3) Renaming functions or arguments, (4)…

Address PR review feedback by systematically working through every unresolved PR review thread on the current branch's PR - analyze each comment, make the requested code changes (with tests where useful), commit, and optionally reply and resolve.

Bulk resolve unresolved PR review threads on the current branch’s PR — typically after threads have been addressed manually or via /pr-threads-address

Full quality pass over the site: structure via reader-review, then prose via writing-voice, then broken links and anchors, then a rebuild and the three checks. Fixes what is mechanical and reports what needs judgement. Needs credentials and takes 15 to 30…

Reviews whether this site's pages are structured for the reader rather than for the people who researched them: opening, scope, heading form, running order, enumeration, completeness, necessity and register. Judged against five R-community books and an…

Choosing and troubleshooting a connection from R to Databricks. Load this first for any R-to-Databricks work. Covers the five connection paths (odbc, brickster DBI, sparklyr, brickster REST, db_context), the ambient-credential model on Posit Workbench, and…

Finding and querying Unity Catalog data from R. Covers browsing catalogs, schemas and tables with brickster, writing dbplyr pipelines rather than SQL strings (including why spatial ST_ functions and the odbc BINARY bug are not reasons to drop to SQL, and why…

Choosing a parallel method for R work on Databricks, then running distributed R with sparklyr::spark_apply(). Covers the six candidate methods and when each fits, spark_apply mechanics and its hard prerequisites, and the limits of Databricks Connect. Load…

Use when adding, editing or reviewing a diagram on the R on Databricks guide. Covers the Graphviz-over-mermaid decision, the both-modes colour palette, the width budget, and how to preview a diagram with the dark mode toggle. Also use when deciding whether a…

Starting, stopping and inspecting Databricks clusters and SQL warehouses from R with brickster, without surprise billing. Covers the check-before-start rule, access modes and which ones permit R, cluster library installation, getting binary rather than source…

The brickster R package as a reference: authentication, the db_* function families, the builder DSL for clusters and jobs, the DatabricksSQL DBI backend for BINARY columns, and remote R execution via contexts. Load when you need brickster API detail; load…

Use LLMs to draft and edit Pointblank validation plans. Covers DraftValidation for generating plans from data, EditValidation for modifying existing plans with natural language, and the interactive assistant() chat interface. Supports Anthropic, OpenAI,…

Validate DataFrames and database tables with Pointblank. Covers the Validate workflow (plan, interrogate, report), column selectors, data backends (Polars, Pandas, DuckDB, databases via Ibis), threshold levels, actions, and result extraction. Use when…

Write data-validation plans with Pointblank. Covers choosing the right validation methods for each data quality concern, composing multi-step plans, setting thresholds and actions, using segments, conditional steps, handling nulls and missing values, and…

Define Pointblank validation plans in YAML instead of Python code. Covers the YAML schema, validate_yaml() for syntax checking, yaml_interrogate() for execution, yaml_to_python() for code generation, and data source configuration. Use when defining validation…

Profile and scan datasets with Pointblank before writing validation rules. Covers DataScan for column-level statistics, Schema inference with schema_from_tbl(), missing values analysis with missing_vals_tbl(), and table previewing. Use when exploring a new…

Generate synthetic datasets with Pointblank using Schema and field classes. Covers IntField, FloatField, StringField, BoolField, DateField, DatetimeField, and more. Supports presets (name, email, address, etc.), country-specific data, nullable columns, unique…

Define data contracts and pipeline validation with Pointblank. Covers Contract, Step, Schema, Pipeline, and PipelineResult for enforcing structural and semantic expectations at data boundaries. Use when setting up source/target contracts, pipeline validation,…

Generate documentation sites for Python packages with Great Docs. Covers init, build, preview, configuration (great-docs.yml), API reference, CLI docs, user guides, theming, deployment, and the llms.txt agent-context files. Use when creating, configuring,…

Configure a Great Docs documentation site through great-docs.yml. Covers theming (navbar gradients, content glow, dark mode), hero sections, logos, announcements, sidebar options, page tags, page status badges, SEO, analytics, and deployment settings. Use…

Write and maintain narrative user-guide pages for a Great Docs site. Covers page creation, QMD frontmatter, section grouping, sidebar ordering, callouts, executable code cells, cross-references, and content guidelines. Use when adding, reorganizing, or…

Review and improve Python docstrings for Great Docs API reference generation. Covers NumPy and Google style conventions, parameter documentation, return types, examples, cross-references, and Great Docs directives (%seealso, %nodoc). Use when auditing,…

Author, configure, and distribute Agent Skills for a Great Docs site. Covers the three scenarios: automatic skill generation, adding a single hand-written skill, and distributing multiple named skills with a switcher page. Use when creating, editing, or…

Walk through the full Shiny for Python release train interactively, phase by phase. Use when the user says "release", "start a release", "py-shiny release", "release train", or wants to publish new versions of py-shiny and its ecosystem packages…

Building, styling, testing, debugging, or observing a Shiny for Python (py-shiny) reactive web app - `from shiny import ...`, `shiny run app.py`. Index skill: read this, then open the linked reference for the task. Covers dashboard design and visual QA; card…

Manage GitHub sub-issues using the gh CLI (v2.94.0+). Use when the user asks to create, list, add, or remove sub-issues (child issues) from a parent issue.

Comprehensive guide for porting UI components from R's bslib package to py-shiny. Use this skill when: (1) User asks to "port this feature" or "port a component" and mentions bslib or links to a bslib PR (e.g., github.com/rstudio/bslib/pull/...), (2) Porting…

Capture screenshots and PDFs from raw HTML strings or local HTML files using nokap. Use when rendering HTML output from packages like Great Tables, Plotly, or custom report generators to images or PDFs.

Generate PDFs from web pages or HTML using nokap. Use when writing code that produces PDF output from URLs or HTML strings, configures paper sizes, margins, or creates element-bounded PDFs sized exactly to content.

Capture screenshots from live web pages using nokap. Use when writing code that screenshots URLs, configures viewports, handles page load timing, or captures specific page elements from remote sites.

Capture screenshots and PDFs from web pages using headless Chrome via CDP. Use when writing Python code that captures, screenshots, or renders web pages, local HTML files, or raw HTML strings to images or PDFs.

Validate blog post frontmatter and placement

Scaffold a new blog post with inferred frontmatter, branch, and optional environment setup

Review a blog post's content against its frontmatter and the authoring guide

Walks through the ship-day site update for a Positron patch release. Bumps versions, copies the new patch entry from next.md into release.md, resets next.md, refreshes _freeze, and opens the PR. Use when the user starts the ship-day PR for a patch (typically…

Walks through the monthly release-day site update for positron-website. Archives last month's notes, promotes next.md into release.md, bumps versions, refreshes _freeze, flags downstream doc updates, and opens the PR. Use when the user starts the monthly…

Guides authoring the in-product release notes in release-notes/next.md, including assembling the changelog by mining merged PRs forward from the version-bump anchor PR, and adding and iterating on images/GIFs with a local in-product preview loop before…

Build a Shiny app whose UI is a React client (the ui.tsx pattern) using shinyreact for Python or R. Use when the user asks to build, extend, or debug a Shiny app with a React front end, mentions shinyreact, set_react_page(), page_react(), reactive_output, or…

Convert an existing Shiny app (R or Python) to the shinyreact ui.tsx pattern — inspect the source, drive the running app in a browser, describe it in plain English, then port it against that description. Use when the user asks to port, convert, migrate,…

Audit FEATURES.md against the shinyreact source — confirm, contradict, or flag every leaf, and find behavior in the code that the tree never claims. Use when the user says "audit features", "/audit-shinyreact-features", "is FEATURES.md still true", or after a…

Use when adding Playwright tests that verify a component's example apps under components/ actually run and behave — covers the shared components/conftest.py smoke_test fixture, create_example_fixture, per-component test_<name>.py layout, and py-shiny…

Use when adding or editing a component documentation page under components/ in py-shiny-site (inputs, outputs, display-messages, layout) — covers the directory layout, index.qmd front matter, app-*.py preview/example files, shinylive link generation, and…

Update the packages of the gallery's own renv library, in R/renv.lock. Use when R/check.R or R/capture.R fails on a package version, when a package the tooling needs is absent from the lockfile, or when the lockfile is old enough to be worth refreshing. Not…

Capture or replace the thumbnail of a Shiny app for the gallery. Use when a tile in apps.yml or packages.yml still shows the placeholder image, or when an existing thumbnail is out of date. Opens each app in a browser that the user controls. Captures the…