emily2040/data-science-agent-skills

1

ai-data-readiness-triage Assess whether a dataset or data domain is ready for AI, analytics, or modeling before a project commits time and bud…

emily2040/data-science-agent-skills

3

2

baseline-ablation-lab Design honest baselines and ablations before complex models are accepted. Use when an agent needs a judgment-heavy da…

emily2040/data-science-agent-skills

3

3

causal-assumption-scout Clarify when a data science request needs causal reasoning, what assumptions are required, and what evidence is missi…

emily2040/data-science-agent-skills

3

4

cost-aware-compute-planner Plan compute use so data science experiments, model training, and inference stay within budget and latency constraint…

emily2040/data-science-agent-skills

3

5

data-question-framing Turn ambiguous business, product, policy, or research asks into decision-ready data science problem statements. Use w…

emily2040/data-science-agent-skills

3

6

data-science-incident-rca Run root-cause analysis for broken models, metrics, dashboards, pipelines, and data science decisions. Use when an ag…

emily2040/data-science-agent-skills

3

7

dataset-contract-forensics Infer practical data contracts, schema expectations, and validation tests from messy real datasets. Use when an agent…

emily2040/data-science-agent-skills

3

8

domain-expert-collaboration-loop Structure collaboration between data scientists, AI agents, and domain experts when domain judgment is required. Use …

emily2040/data-science-agent-skills

3

9

drift-monitor-designer Design drift monitoring for production models and data products across data, concept, performance, and operational si…

emily2040/data-science-agent-skills

3

10

evaluation-reality-check Design evaluation strategies that match task type, deployment setting, time, groups, and decision risk. Use when an a…

emily2040/data-science-agent-skills

3

11

experiment-provenance-ledger Preserve experiment provenance across code, data, environment, parameters, metrics, artifacts, and human decisions. U…

emily2040/data-science-agent-skills

3

12

feature-store-readiness Decide whether a feature store is needed and design features to avoid training-serving skew, staleness, and reuse con…

emily2040/data-science-agent-skills

3

13

leakage-adversary Actively search ML datasets and pipelines for target, temporal, group, split, join, and preprocessing leakage. Use wh…

emily2040/data-science-agent-skills

3

14

messy-data-cleanroom Design transparent, reversible cleaning plans for messy datasets without silently mutating evidence. Use when an agen…

emily2040/data-science-agent-skills

3

15

metric-design-review-board Review whether a chosen data science metric actually supports the decision, user outcome, risk, and cost tradeoff. Us…

emily2040/data-science-agent-skills

3

16

missingness-mechanism-investigator Diagnose missing-data mechanisms and design imputation, exclusion, or sensitivity plans. Use when an agent needs a ju…

emily2040/data-science-agent-skills

3

17

model-risk-compliance-memo Create concise model risk and compliance memos for review, audit, launch, or executive approval. Use when an agent ne…

emily2040/data-science-agent-skills

3

18

notebook-repro-packager Package notebooks so another machine or teammate can reproduce their results with known data, environment, seeds, and…

emily2040/data-science-agent-skills

3

19

notebook-to-pipeline-surgeon Convert exploratory notebooks into modular, parameterized scripts or orchestrated pipeline tasks. Use when an agent n…

emily2040/data-science-agent-skills

3

20

oss-ds-supply-chain-auditor Audit open-source packages, notebooks, model weights, datasets, licenses, and provenance used in data science work. U…

emily2040/data-science-agent-skills

3

21

privacy-preserving-ds Guide data science work on sensitive data using minimization, local-first analysis, de-identification, synthetic data…

emily2040/data-science-agent-skills

3

22

production-ml-handoff Convert data science prototypes into engineering-ready ML handoffs with contracts, artifacts, SLOs, monitoring, and o…

emily2040/data-science-agent-skills

3

23

semantic-lineage-mapper Reconstruct practical lineage across SQL, notebooks, scripts, dashboards, model artifacts, and pipeline configs. Use …

emily2040/data-science-agent-skills

3

24

small-data-power-planner Help teams decide what can be learned responsibly from small, imbalanced, expensive, or scarce datasets. Use when an …

emily2040/data-science-agent-skills

3

25

stakeholder-insight-storyteller Convert analysis into stakeholder-ready insight narratives that state decisions, evidence, uncertainty, and recommend…

emily2040/data-science-agent-skills

3