Cecil data analysis with xarray-sql — skill + tutorial#5
Merged
Conversation
Structural restructure of #4 (jayendra13/add-cecil-data-analysis-xql-skill). The original PR is a single skill containing 4 runnable Python scripts and 3 reference documents (~1,200 LOC). That shape is closer to a tutorial than a skill — skills are short, focused text loaded into an agent's context at inference time, not multi-file CLI projects. Splitting into two artifacts: - skills/cecil-data-analysis-xql/SKILL.md (~135 lines) Just what an agent needs in-context: the subscription gate (wallet safety), the golden-rule output format, the SQL idioms, the PascalCase quoting rule, vector-vs-raster routing, and failure modes. Links out to the tutorial for everything else. - tutorials/cecil-data-analysis-xql/ ├── README.md full Step 0–5 walkthrough + worked example ├── references/ datasets.md, sdk.md, xarray_sql.md (Jayendra's) └── scripts/ _env.py, list_subscriptions.py, inspect_dataset.py, run_analysis.py (Jayendra's, with three small fixes) Three review fixes applied to the script: 1. run_analysis.py: added --vector flag using load_dataframe + XarrayContext.from_pandas. Previously the runner unconditionally called load_xarray, which would fail on IBAT vector datasets the description says are in scope ("threatened species ranges intersect this AOI"). 2. run_analysis.py: replaced fig.autofmt_xdate() in the bar-chart branch with rotation of categorical xticks. autofmt_xdate is a date-axis helper applied to a non-date axis. 3. README.md: pinned xarray-sql to a sub-0.1 range (pre-1.0 package; the XarrayContext().from_dataset() API is the kind that drifts in 0.x). Also dropped the bash-specific `set -a && source .env && set +a` syntax from the prerequisites — fish/zsh-without-posix users would hit it. If this merges, #4 should close as superseded. Co-Authored-By: jayendra13 <jayendra0parmar@gmail.com> Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Splitting into two artifacts:
skills/cecil-data-analysis-xql/SKILL.md (~135 lines) - Links out to the tutorial for everything else.
tutorials/cecil-data-analysis-xql/
├── README.md full Step 0–5 walkthrough + worked example
├── references/ datasets.md, sdk.md, xarray_sql.md (Jayendra's)
└── scripts/ _env.py, list_subscriptions.py, inspect_dataset.py,
run_analysis.py (Jayendra's, with three small fixes)
Three review fixes applied to the script:
Also dropped the bash-specific
set -a && source .env && set +asyntax from the prerequisites — fish/zsh-without-posix users would hit it.