원클릭으로
session-wrapup
How to gather everything for future learnings
Codex 또는 Claude로 설치 이 Prompt를 복사해 Codex, Claude 또는 다른 어시스턴트에 붙여 넣으면 Skill 페이지를 검토하고 설치를 진행할 수 있습니다.
메뉴
How to gather everything for future learnings
Codex 또는 Claude로 설치 이 Prompt를 복사해 Codex, Claude 또는 다른 어시스턴트에 붙여 넣으면 Skill 페이지를 검토하고 설치를 진행할 수 있습니다.
SOC 직업 분류 기준
How to use the CARTO CLI to interact with the platform
How to write, validate, and upload CARTO Workflows
How to enrich component notes and input type documentation served by the local workflows-api
Builds Geographically Weighted Regression (GWR) workflows in CARTO. Triggers when the user mentions GWR, geographically weighted regression, spatially varying relationships, local regression, local coefficients, spatial regression, "what drives X in different areas", "why do prices vary spatially", "local factors affecting Y", varying coefficients, coefficient maps, spatial non-stationarity, or wants to model how the relationship between a dependent variable and predictors changes across geography. Produces per-cell regression coefficients that reveal how predictor importance shifts from place to place.
Builds Getis-Ord Gi* hotspot analysis workflows in CARTO. Triggers when the user mentions hotspots, coldspots, spatial clusters, Getis-Ord, Gi*, cluster detection, concentration areas, "where do X cluster", spacetime hotspot, temporal clusters, time-varying patterns, hotspot trends, emerging hotspots, Mann-Kendall, or wants to find statistically significant spatial or spatiotemporal patterns in point or grid data.
Builds Moran's I spatial autocorrelation workflows in CARTO. Triggers when the user mentions spatial autocorrelation, Moran's I, spatial dependency, spatial correlation, spatial outliers, HH HL LH LL quadrants, high-high clusters, low-low clusters, spatial weight matrix, "is there clustering", "are values spatially correlated", local indicators of spatial association, LISA, spatial randomness test, or wants to determine whether a variable exhibits spatial clustering, dispersion, or randomness across a gridded dataset. Also relevant when the user needs to classify locations into cluster types (HH, HL, LH, LL) rather than just identifying hotspots and coldspots.
| name | session-wrapup |
| description | How to gather everything for future learnings |
Load this skill when:
This skill covers three types of documentation:
Location: ./session-reports/YYYY-MM-DD-brief-topic.md
Create after every session to document what happened.
# Session Report: <Brief Description>
**Date**: YYYY-MM-DD
**Workflow**: <workflow filename or "N/A">
**Outcome**: Completed | Partially Completed | Blocked
## Errors Encountered
| Error | Cause | Resolution |
|-------|-------|------------|
| <error message> | <why it happened> | <how fixed or "unresolved"> |
## Limitations & Workarounds
| Limitation | Workaround | Ideal Solution |
|------------|------------|----------------|
| <what was missing> | <how you worked around it> | <what would be better> |
## New Learnings
| Learning | Source | Should Document? |
|----------|--------|------------------|
| <what you learned> | <how discovered> | Yes/No |
## Improvement Suggestions
- Documentation: <missing/unclear docs>
- Components: <useful new components>
- CLI: <missing features, better errors>
- Agent: <process refinements>
Location: ./bug-reports/YYYY-MM-DD-brief-description.md
Create when you encounter unexpected engine errors (not user errors).
Create a bug report when:
Do NOT create for:
carto auth login to fix)# Bug Report: [Brief Description]
## Summary
[One paragraph describing the issue]
## Reproduction Steps
1. [Step 1]
2. [Step 2]
## Expected Behavior
[What should have happened]
## Actual Behavior
[What actually happened, including error messages]
## Environment
- Connection: [name]
- Provider: [bigquery/snowflake/etc]
- CLI version: [output of `carto --version`]
## Attachments
- workflow.json: [path or inline]
Location: ./model-feedback/YYYY-MM-DD-short-topic.md
Create when you encounter inefficiencies that could be improved.
# Feedback: [Topic]
**Date**: YYYY-MM-DD
**Task**: [What you were trying to do]
**Time Lost**: [Estimate]
## What Happened
[Describe the struggle]
## Root Cause
[Why - missing tool, unclear docs, bad error message, etc.]
## What Would Have Helped
- [Improvement #1]
- [Improvement #2]
## Priority
[Low/Medium/High]