brendancol/xarray-spatial-skills
Command Claude Code
This file is NOT a runnable command. It defines the shared machinery every /sweep- command uses: module discovery, standard flags, module groups, CUDA probing, the state-CSV contract, the severity rubric, the repro gate, and the agent contract. Each sweep file references the sections below by name instead of repeating…
brendancol/xarray-spatial-skills
Command Claude Code
Verify that all implemented backends produce consistent results for a given function or set of functions. The prompt is: $ARGUMENTS.
brendancol/xarray-spatial-skills
Command Claude Code
Run ASV benchmarks for the current branch against main and report regressions and improvements. The prompt is: $ARGUMENTS.
brendancol/xarray-spatial-skills
Command Claude Code
Create a Jupyter notebook that sets up a Dask distributed LocalCluster and walks through an ETL (Extract, Transform, Load) workflow. The prompt is: $ARGUMENTS.
brendancol/xarray-spatial-skills
Command Claude Code
Pick one xrspatial module and dispatch every /sweep- command at it in parallel. Each sub-sweep follows the audit template embedded in its own .claude/commands/sweep-.md file, runs /rockout for HIGH/MEDIUM findings when the sweep specifies it, and updates its own .claude/sweep-{type}-state.csv row for the target module.
brendancol/xarray-spatial-skills
Command Claude Code
Analyze source code for performance anti-patterns specific to the NumPy / CuPy / Dask / Numba stack. The prompt is: $ARGUMENTS.
brendancol/xarray-spatial-skills
Command Claude Code
Audit the README feature matrix, identify gaps and opportunities, and file GitHub issues for the best candidates. The prompt is: $ARGUMENTS.
brendancol/xarray-spatial-skills
Command Claude Code
Scan the open pull requests and report the ones that are ready to merge. A PR is ready when it has been reviewed, its review blockers are resolved, it has no merge conflict with main, and CI is green. A failing Read the Docs build is tolerated, because RTD flakes under rate limiting and that failure does not reflect…
brendancol/xarray-spatial-skills
Command Claude Code
Cut a major release (X.Y.Z -> X+1.0.0). Follow every step below in order.
brendancol/xarray-spatial-skills
Command Claude Code
Cut a minor release (X.Y.Z -> X.Y+1.0). Follow every step below in order.
brendancol/xarray-spatial-skills
Command Claude Code
Cut a patch release (X.Y.Z -> X.Y.Z+1). Follow every step below in order.
brendancol/xarray-spatial-skills
Command Claude Code
Prescreen a pull request from an outside contributor for two things the domain-aware reviews do not look for: prompt injection aimed at the LLM agents that will later read the PR, and unsafe outside code (exfiltration, arbitrary execution, build/install hooks, CI tampering). The output is a safety verdict that gates…
brendancol/xarray-spatial-skills
Command Claude Code
Review a pull request with checks specific to a geospatial raster library built on NumPy, Dask, CuPy, and Numba. The prompt is: $ARGUMENTS.
brendancol/xarray-spatial-skills
Command Claude Code
Take the user's prompt describing an enhancement, bug, or suggestion and drive it through all ten steps below. The prompt is: $ARGUMENTS.
brendancol/xarray-spatial-skills
Command Claude Code
Audit xrspatial modules for numerical accuracy issues: floating point precision loss, incorrect NaN propagation, off-by-one errors in neighborhood operations, missing or wrong Earth curvature corrections, backend inconsistencies (numpy vs cupy vs dask results differ), and divergence from reference implementations.…
brendancol/xarray-spatial-skills
Command Claude Code
Audit xrspatial modules for API consistency issues across analogous public functions: parameter naming drift (cellsize vs cellsize vs res, agg vs raster vs data), inconsistent return-type shapes, missing or mismatched type hints, docstring/signature divergence. Cheap to find; makes the library feel polished and…
brendancol/xarray-spatial-skills
Command Claude Code
Audit xrspatial modules for benchmark coverage gaps in the asv suite under benchmarks/benchmarks/: public functions with no benchmark at all, benchmarks that only exercise the numpy backend, inputs too small to reflect real workloads, and benchmarks that are broken or silently skipped. Without benchmark coverage, the…
brendancol/xarray-spatial-skills
Command Claude Code
Deep-sweep scope: library-wide — /deep-sweep skips this sweep.
brendancol/xarray-spatial-skills
Command Claude Code
Audit xrspatial modules for documentation gaps and quality issues: missing or incomplete docstrings, docstring/signature drift, broken or outdated runnable examples, public functions absent from the API reference, and documentation that misstates behavior (wrong dtype/shape or backend-support claims). Subagents fix…
brendancol/xarray-spatial-skills
Command Claude Code
Audit xrspatial modules for the failure-path user experience: public functions that skip input validation, errors raised far from their cause with unactionable messages, bad input that yields garbage output instead of an exception, inconsistent exception types across sibling functions, and over-broad exception…
brendancol/xarray-spatial-skills
Command Claude Code
Audit xrspatial modules for metadata propagation bugs: attrs (especially res, crs, transform, nodatavals, FillValue), coords (x/y values and dims), and dim names. Spatial libs lose CRS/transform silently and the result looks correct but is wrong. The skyviewfactor cellsize bug (#1407) was exactly this class of issue.…
brendancol/xarray-spatial-skills
Command Claude Code
Audit xrspatial modules for performance bottlenecks, OOM risk under 30TB dask workloads, and backend-specific anti-patterns. Subagents fix HIGH and MEDIUM-severity findings via /rockout in the same agent that did the audit, in parallel.
brendancol/xarray-spatial-skills
Command Claude Code
Validate xrspatial algorithms against independent reference implementations — gdaldem for terrain, scipy.ndimage for focal/convolution/morphology, richdem / WhiteboxTools for curvature and hydrology — on shared synthetic inputs. This is the strongest correctness signal a spatial algorithm library can have: not "the…
brendancol/xarray-spatial-skills
Command Claude Code
Audit xrspatial modules for security issues specific to numeric/GPU raster libraries: unbounded allocations, integer overflow, NaN logic bombs, GPU kernel bounds, file path injection, and dtype confusion. Subagents fix CRITICAL, HIGH, and MEDIUM severity issues via /rockout.