pandas-data-wrangling
Skill4 starsChanged 57 days agoNo licenceView on GitHub
Use when cleaning, typing, filtering, deduplicating, joining, aggregating, reshaping, or time-aligning tabular data with pandas, or debugging row loss, join fan-out, null handling, index alignment, schema drift, and wrangling memory use. Produces explicit data contracts, reproducible transformations, reject accounting, and invariant checks. Data wrangling only, not exploratory analysis, modelling, feature engineering, visualisation, or orchestration.
We split this skill into the rules it gives an agent
7 rules. About 0 are common, 4 are distinctive, and 3 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈4
Distinctive · estimate
This author's own choices. Worth a look.
3
Very specific
Tied to their project's names, files or tools. Probably skip.
No licence file, so all rights are reserved — read it at the source. We count its rules but don't quote them. Read them on GitHub.
≈ “Common” is an estimate: at least 1 in 5 of the 308,232 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
In this repository249 other files it gives its agents.
- .github/copilot-instructions.mdCopilot instructions
- asset-frontmatter-checkSkill
- asset-self-containment-checkSkill
- markdown-link-auditorSkill
- agent-governance-patternsSkill
- agentic-evalSkill
- agent-owasp-complianceSkill
- agent-supply-chainSkill
- ai-readySkill
- copilot-cli-quickstartSkill
- first-askSkill
- generate-custom-instructions-from-codebaseSkill
- github-copilot-starterSkill
- nano-banana-pro-openrouterSkill
- noob-modeSkill
- prompt-builderSkill
- remember-interactive-programmingSkill
- rememberSkill
- tldr-promptSkill
- what-context-neededSkill
- acceptance-test-planSkill
- architecture-auditSkill
- gap-analysisSkill
- miro-boardSkill
- process-mapSkill
- requirements-documentSkill
- risk-analysisSkill
- stakeholder-mapSkill
- tradeoff-analysisSkill
- use-caseSkill
- write-epicSkill
- write-user-storySkill
- architecture-models-4plus1Skill
- create-architectural-decision-recordSkill
- technology-stack-blueprint-generatorSkill
- dashboard-beautifySkill
- dashSkill
- daskSkill
- data-validation-and-schema-contractsSkill
- experiment-tracking-and-reproducibilitySkill
- exploratory-data-analysisSkill
- feature-engineering-and-leakage-checksSkill
- forecastic-evaluationSkill
- gradient-boostongSkill
- hypothesis-testing-and-ab-evaluationSkill
- imbalanced-classificationSkill
- matplotlibSkill
- mlflowSkill
- model-recommendationSkill
- model-selections-and-cross-validationSkill
- networkxSkill
- numpy-scipy-statisticsSkill
- opencvSkill
- plotlySkill
- polarsSkill
- powerbi-modellingSkill
- pymcSkill
- scikit-learn-pipelines-and-column-transformersSkill
- scikit-learnSkill
- seabornSkill
- The first 60 shown.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
Reviews can't be read right now.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.