loading
loading
Profile a dataset for completeness, duplicates, outliers, and schema issues before anything uses it.
Catches the business-critical nulls and duplicate keys before a report depends on them — concrete column-level issues, no hand-wavy causal claims.
Listed for review
No verified public repo for this skill yet, so this page does not give you an install command. Skills with a verified source install in one command — or fully manual: copy the skill folder into .claude/skills/ and your agent picks it up.
Boostor Quality Score
84/100 · B
Data Quality Profiler reads a dataset against your schema expectations and the business meaning of each column, then returns a profile: completeness, uniqueness, outliers, schema mismatches, and recommended fixes. It reports concrete column-level issues — the business-critical nulls and duplicate keys that break reports later — and avoids unsupported causal claims, so problems surface before a report or automation already depends on the data.
Audit product analytics for missing events, vague names, and payload gaps tied to real funnel questions.
Ties every event to a decision question and flags PII in payloads — so your analytics answers funnel questions instead of just piling up.
Transparent + deterministic: every point above is computed from this skill's real fields plus a prompt-injection safety scan. No black box, no pay-to-rank.
Write an A/B test readout that separates significant results from directional signals from noise.
Separates a significant result from a directional signal from noise — and surfaces the sample-size and seasonality caveats before you ship a win.
Wire up a retrieval-augmented generation pipeline from docs to answers.
Skips the where-do-I-start of RAG: ingestion, chunking, and upsert in one config, plus a relevance check so junk chunks never reach the prompt.