analyst
Exhaustively profile a dataset and list ALL possible analyses — distributions, correlations, rankings, trends, group comparisons, anomalies. Reads detective.json for context. Runs after the Detective/Scout, before the Editor. Outputs analyst.json with ana_xx IDs and chart-ready data_tables.
npx skills add QinghongLin/data2story-skill --skill analyst --agent claude-code
Same command for any agent — swap --agent for codex, cursor, copilot.
Weekly change comes from our own snapshots, not the repository page — it measures attention, not adoption.
# Analyst Your job is **completeness**, not curation. List every analysis this dataset can support, grounded in the context the Detective found. You are not deciding what story to tell — that is the Editor's job. You are cataloguing what the data contains. ## Setup - `DATA_DIR` = first argument - `PROJECT_DIR` = second argument - Read `PROJECT_DIR/detective.json` before starting — it tells you what matters in this domain - Also read `PROJECT_DIR/scout.json` if present — surface any `live_status[]` entries as **display-only** context (cite the dated source; **never** feed live status to a forecasting/training model) - Outputs: `PROJECT_DIR/code/*.py` (analysis scripts), `PROJECT_DIR/analyst.json` ## Steps ### 1. Dataset Profile Run code to compute: - File(s), format, row count, column count - What one row represents - Time range, geographic scope - Missing value counts per column - Cardinality of categorical columns ### 2. Field Inventory For every column: - Name, inferred meaning, data type - Sample values - Noteworthy distributions or quirks ### 3. All Possible Analyses Run actual code (Python/Bash) for every applicable category below. Record the **actual numbers** — not descripti
- Setup
- Steps
- 1. Dataset Profile
- 2. Field Inventory
- 3. All Possible Analyses
- 4. Save all code to code/
- 5. Write analyst.json
- Output
- Scientific Paper Mode
- Team coordination — Analyst team
What does the analyst skill do?
Exhaustively profile a dataset and list ALL possible analyses — distributions, correlations, rankings, trends, group comparisons, anomalies. Reads detective.json for context. Runs after the Detective/Scout, before the Editor. Outputs analyst.json with ana_xx IDs and chart-ready data_tables.
How do I install it?
Run `npx skills add QinghongLin/data2story-skill --skill analyst --agent claude-code` — it drops the skill into your project so the agent can pick it up. Swap the --agent value for codex, cursor or copilot if you use one of those.
Where does this skill come from?
From QinghongLin/data2story-skill, a repository with 149 stars. We read it straight from the repository tree rather than a submitted listing, so what you see here is what is actually published.
Is a popular skill a good skill?
Not necessarily. Stars measure attention, not adoption — a repository can trend for a week and be abandoned. That is why we show the weekly change from our own snapshots next to the total, instead of a single flattering number.