Use when the user asks to brainstorm personas, define target users, create user profiles, or plan cultural probes for design research. Generates persona clusters, persona hypothesis cards (name, goal statement, behavioral summary, constraints, design implications), and probe design briefs through a structured conversational workflow. Produces living hypotheses grounded in observed evidence rather than invented demographics. Trigger phrases: create personas, define target users, user profiles, who are my users, user research, cultural probes, research through design, persona discovery.
Use when the user wants to validate documentation quality, check for broken links, lint prose or Markdown, test code examples, verify setup instructions, or set up CI for documentation testing. Covers prose linting with Vale, Markdown/RST syntax checking (markdownlint, doc8), link validation (HTMLProofer, lychee, markdown-link-check), code example testing (pytest doctest, cargo test --doc), notebook validation (nbval), container-based instruction testing, and GitHub Actions CI integration for research software projects. Trigger phrases: check my docs, broken links, doc quality, documentation errors, spelling/grammar in docs, test documentation, validate README, link check, prose linting, doc CI.
Use this skill when users ask to "develop a download script", "debug data download", "fix download error", "create data pipeline template", "download template", "GAIA data pipeline", "download from S3", "access Zarr store", "cloud data access", or mention sources like CONUS404, HRRR, WRF, PRISM, Stage IV, USGS, ORNL, DEM, Synoptic, or IRIS. Generates CONFIG-at-top Python download scripts, validates source-specific configuration (auth, endpoint/path, date range, variables, AOI/CRS, and output format), and diagnoses common failures (403/auth, timeout/retry, CRS mismatch, missing binaries, and partial downloads).
Use when the user asks for a structured technical research approach, a spike/proof of concept, feasibility investigation, or research-driven implementation planning. Guides a six-phase workflow (Research, Plan, Iterate Plan, Experiment, Implement, Validate) that generates concrete artifacts: research questions and findings, phased implementation plans with success criteria, experiment reports, implementation logs, and validation reports.
Use when the user asks about Podman, rootless containers, Quadlet/systemd units, Podman Compose, or migrating Docker workflows to Podman. Creates and manages rootless Podman containers, maps Docker commands, configures podman run/build/compose flows, and sets up systemd-managed services.
Generates and configures open-source project files including README, CONTRIBUTING, LICENSE, CODE_OF_CONDUCT, SECURITY, and CITATION.cff, and sets up GitHub issue/PR templates following community best practices. Use when the user asks about setting up a new open-source project, creating README/CONTRIBUTING/LICENSE/CODE_OF_CONDUCT/SECURITY/CITATION.cff files, adding GitHub issue or PR templates, or improving repository community standards.
Create and publish distributable scientific Python packages following Scientific Python community best practices. Covers pyproject.toml, src layout, Hatchling, metadata, CLI entry points, and PyPI publishing. Use when the user wants to create a new Python package, set up pyproject.toml, configure Hatchling, publish to PyPI, or follow Scientific Python packaging standards.
Integrates Zarr with xarray and Dask for labeled, multi-dimensional scientific data workflows. Covers reading and writing Zarr stores with xarray, append and region-write operations, multi-file virtual datasets, Dask chunk alignment with Zarr chunks, encoding configuration, consolidated metadata, and performance optimization. Use when the user asks about reading or writing Zarr stores with xarray, aligning Dask chunks with Zarr arrays, or optimizing large-scale multi-dimensional data pipelines.