Index of every page on this site: llms.txt
All skills
bytedance avatar

/data-analysis

@40ef4f6
by Bytedance Inc.bytedance/deer-flow86k stars
12,065
Run it yourself

Use this skill when the user uploads Excel (.xlsx/.xls) or CSV files and wants to perform data analysis, generate statistics, create summaries, pivot tables, SQL queries, or any form of structured data exploration. Supports multi-sheet Excel workbooks, aggregation, filtering, joins, and exporting results to CSV/JSON/Markdown.

Use this Skill: https://skilld.dev/gh/bytedance/deer-flow/data-analysis

Nothing lands on disk. Nothing to clean up.

Fork this Skill

Edit a local copy. It keeps the author and licence.

AGENTS.md

≈639 tokens on demand. Your agent reads this file only when SKILL.md points to it.

Data analysis skill (skills/public/data-analysis/)

python -m pytest tests/skills -q -k "data_analysis"

Tests use real DuckDB. Default tests never download the spatial extension. XLSX integration tests run only with an installed copy named by DEERFLOW_TEST_SPATIAL_DIRECTORY. Legacy XLS and CSV analysis do not need it; the XLS CLI regression uses an empty local extension repository in a fresh process. Legacy XLS keeps compatible columns typed and stores incompatible mixes as text, preserving nulls. Change the XLS cache key when this materialization changes.

Table names and SQL

  • Lookup aliases and SQL table names are allocated together, for CSV files and Excel sheets. Neither may shadow an existing name, compared without case. Reserve a name only after its table was created.
  • Bind file paths and sheet names as SQL values, and quote generated identifiers.
  • User SQL is never rewritten with regular expressions. Original names resolve through connection-local temporary views over the canonical tables, also on a read-only cache hit. Normal CTE shadowing keeps working.

Cache

  • Cache identity covers input order, file names and content digests. Moving the directory does not change it. Bump the namespace version when the table-mapping semantics change.
  • Publish through open_analysis_cache(). Build in a private directory, close the writer, reopen read-only, then atomically replace one manifest. Metadata is never published while a writer owns the database.
  • Validate the manifest and the physical tables before reuse. An invalid entry is rebuilt.
  • Keep a generation when publication may have happened. Another process may be reading it. Concurrent cold builders can repeat work, and they never share a writable database.
  • There is no automatic garbage collection and no power-loss guarantee.

Environment and exports

  • Missing DuckDB or openpyxl prints setup instructions. The skill does not start an installer.
  • Export paths resolve against the caller's working directory, also for a bare file name.
  • Markdown export escapes headers and values the same way, and turns line breaks into <br>, so one result row stays one table row.
  • JSON export rejects duplicate column names before it opens the output file, and tells the caller to add SQL aliases. CSV and Markdown keep duplicates.
  • At the CLI boundary a ValueError becomes a short stderr message and a non-zero exit. The connection closes in finally.

Source: SKILL.md on GitHub

skilld matched fixed text patterns in SKILL.md and file names. Patterns miss obfuscated code.

skilld run checks every file with the same patterns. It asks for approval before it loads a Skill with a behavior marked Needs approval.

2 warnings4d5 checks · Risk SAFE
  • Gen Agent Trust Hub4d

    A data analysis skill using DuckDB that enables SQL queries and statistical summaries of uploaded files. It provides significant utility but introduces attack surfaces for file reading and writing if the agent is manipulated into using sensitive paths in SQL or output parameters.

  • Socket4d

    No alerts

  • Snyk4d

    Risk: MEDIUM · 1 issue

  • Runlayer9mo

    2/2 files flagged

  • ZeroLeaks7mo

    Score: 93/100 · 2 sections analyzed

Signed by skilld at 40ef4f6. This ties the file your Agent reads to that commit on GitHub. It does not review the instructions.

Last checked against GitHub 3 hours ago.

Activeupdated last week
  • Python
  • duckdb
  • data-analysis
  • sql
  • excel
  • csv
  • statistics
  • aggregation
  • pivot-tables

README badge

README badge for bytedance/deer-flow/data-analysis

Analyzes Excel and CSV files using DuckDB, supporting SQL queries, statistical summaries, multi-sheet workbooks, and result export to CSV/JSON/Markdown. Useful for exploring tabular data, computing aggregations, performing cross-file joins, and generating pivot tables without manual data manipulation.

Generated from the current SKILL.md.

What file formats does this skill support?
Excel (.xlsx/.xls) files and CSV files. Each sheet in an Excel workbook becomes a separate table, and multi-file analysis with joins is supported.
Can I run SQL queries across multiple files at once?
Yes. Pass multiple file paths to the `--files` parameter and write SQL joins across tables from different files in the same query.
What output formats can I export results to?
CSV, JSON, and Markdown. Specify the format by the file extension in the `--output-file` parameter.
How does caching work?
Files are automatically cached after first load in a DuckDB database under `/mnt/user-data/workspace/.data-analysis-cache/`. Subsequent queries on the same files use the cache for near-instant startup.
Does this skill handle large files efficiently?
Yes. DuckDB uses a columnar engine and handles files 100MB+ without loading everything into memory at once.

Generated from the current SKILL.md. These answers refresh after source changes.