跳至正文
OpenAgentSkill
浏览已开放 · 目录记录日期 2026-11-21 · 自动更新和账户服务暂时关闭。
数据与分析

ada

Compute and check numbers from CSV or Excel tables with ADA (the automated-data-analyst Python package). It computes every number in pandas, SciPy and statsmodels with the calculation and rows behind it, checks a number stated about a table (verified, or unverified with a reason), maps a folder of related files and how they join, or refuses with a reason instead of guessing. Use when someone wants a number from a data file, wants a number in a report or an answer checked against the data, wants to know what is in a file or folder, compare groups, test a relationship or a trend,.

saineshnakra · 已有静态检查记录

安装与使用

运行命令前先阅读来源与依赖说明。复制命令不会自动安装或执行。

npx skills add saineshnakra/automated-data-analyst --skill ada

技能说明


name: ada description: Compute and check numbers from CSV or Excel tables with ADA (the automated-data-analyst Python package). It computes every number in pandas, SciPy and statsmodels with the calculation and rows behind it, checks a number stated about a table (verified, or unverified with a reason), maps a folder of related files and how they join, or refuses with a reason instead of guessing. Use when someone wants a number from a data file, wants a number in a report or an answer checked against the data, wants to know what is in a file or folder, compare groups, test a relationship or a trend,. license: MIT compatibility: Needs Python 3.11 or newer and pip install automated-data-analyst 0.7.0 or later. metadata: homepage: https://github.com/saineshnakra/automated-data-analyst docs: https://github.com/saineshnakra/automated-data-analyst/blob/main/docs/README.md

ADA: data analysis with every number computed

ADA computes numbers from CSV and Excel tables and checks numbers stated about them. Every number comes from pandas, SciPy or statsmodels, with the calculation and the rows behind it; when ADA can't compute something honestly it refuses with the reason.

Let ADA do the arithmetic. Report the numbers it computed, with the test or calculation it names, rather than computing or estimating them yourself; when it refuses, pass the reason on. That way everything you report can be checked against ADA's output and the data.

Pick the mode from what the person wants:

  • A number, or a check of one ("what is the average delay?", "is it true that 32% survived?", or any number you are about to write about a data file): "Computing and checking numbers" below.
  • A folder of related files: ada scan data/ first and ask its questions, then ada ask and ada claim on the folder or a file.
  • Just what is in a file: ada analyze data.csv, or in Python ada.analyze("data.csv"). See "First look" at the end.
pip install automated-data-analyst
ada --version

A paper's tables, figures and methods draft from a study, or a prediction for a Kaggle-style folder, are in ADA Lab (pip install ada-lab; see https://github.com/saineshnakra/ada-lab).

Arithmetic on numbers you already have

Do not add, multiply, divide or take percentages in your head. Write the expression and let ADA compute it exactly:

ada compute "0.15 * (1200 - 300)"      # 135, with each step
ada compute "1/3 + 1/6" --json         # value 0.5, fraction 1/2, exact: true
ada compute "x + y = 10; x - y = 2"    # x = 6, y = 4, with each step and a check

Fractions stay exact, each step is shown, and the conventions used are listed (-2^2 is -4). An expression that reads two ways (6/2(1+2), 17 % 5, log(8)) is refused with both readings: write the parentheses or the function you mean. Report the value with its steps, and say "approximately" when exact is false.

To solve equations, write them with one-letter unknowns and give them to the same command: it solves linear equations and systems, polynomial equations in one unknown, and systems of polynomial equations (x*y = 6; x + y = 5), exactly; rules out values that divide by zero; and ends with a check. "No solution" and "every value works" are answers, not errors. A root marked ≈ has no exact form: report it as approximate. To solve a formula for one letter, name it: ada compute "solve h = v*t - g*t^2/2 for t". Report the conditions with the answer (g ≠ 0, the number under a root not negative).

Computing and checking numbers

Compute with ada ask, and check every number you state about the data with ada claim, including numbers you computed yourself or read in a report.

ada ask flights.csv "average dep_delay by origin" --json
ada claim flights.csv "The average departure delay was about 13 minutes."
ada claim flights.csv --question "average dep_delay" --value 12.64 --json
ada claim data/ "The average order_total is 154.10."     # a folder: checked against the file it fits

ada claim prints verified or unverified with one of six reasons, and exits 0 (verified), 1 (the data give a different number, or a check on the analysis failed), 2 (the file could not be read) or 3 (unverified for another reason). With --json it gives the claim's interval ("about 13" is 12 to 14), the plan that ran, the calculation, the rows read, used and left out with a reason for each, the file's sha256, the assumptions, the warnings, and a clarification: the one question that would let the check go ahead.

When you report numbers:

  • Say which numbers ADA verified, and give each with its calculation and the rows it used ("12.64, mean(dep_delay) over the 328,521 flights with a departure delay recorded").
  • Say which are unverified and why, in ADA's words. Unverified is not false: only failed_check with agreement: "mismatch" means the data give a different number.
  • Never call a whole answer verified because one number in it was. A check covers one number, as read; it says nothing about the wording around it.
  • When the reason is missing_context or ambiguous_intent, ask the person ADA's clarification (for example "Which column is meant: dep_delay or arr_delay?") instead of picking a reading yourself.
  • Pass on the assumptions and warnings that matter: rows left out, a scale or unit that was not given, a correlation that runs the other way within groups, repeated rows from one subject.
  • Read decisions on every answer and check: the choices ADA took, such as leaving World and region rows out of an average. Each has a question, its options and ADA's default. When the person's goal settles one ("compare countries" leaves World out), pass that option with --decide KEY=OPTION, such as --decide aggregate_rows=keep, and say you did. When it does not, ask the person the decision's question. With no one to ask, keep the default and say which it was. (--decide needs a
阅读完整来源 ↗