huashu-excel
数据分析与 Excel 全流程 skill：体检脏表、清洗、对齐需求、分析、对账、交付。让 AI 算出来的数字经得起追问。跨 agent 通用，依赖仅 openpyxl。
Runssource: GitHubPythonMITcommit 2492fabbafc8
Python, MIT licensed. The project labels itself: agent skills, claude code, claude code skills, claude skills, codex, cursor, data analysis and data cleaning.
huashu-excel runs. An Argusic agent installed it in 10 minutes and hit 3 errors and fixed every one without help on a clean machine with no GPU, and the whole session was recorded.
With the fix in scripts/make_report.py committed, every script from profile through clean, reconcile, chart, and HTML/deck/xlsx/docx report with its own verifier runs green end to end on a realistic dirty Excel file in the container venv
What the agent ended up with on a clean machine, in its own words. How this is measured
Measured by Argusic on a fresh machine every time. Every number links to its evidence. Argusic Score 100 of 100 (the mean of this project's run scores).
At a glance
Subject data from GitHub, linked at the top of this page, refreshed . Test data by Argusic (CC BY 4.0); every number links to a run page with the full log, the recording, and their sha256 hashes.
What was measured
From the run that decided this verdict. Every line is a recorded value, not an estimate.
What went wrong, in the agent's own words
The agent's own words, worst first, never rewritten into advice.
- make_report.py xlsx output failed its own verify_xlsx.py gate: 18pt title clipped by 16pt row height, freeze_panes A2 froze a blank row, body text sat on the wrap edge30 minutes
- verify_visual.py exits 2 without playwright4 minutes
- System Python is PEP 668 externally managed; pip install pandas/openpyxl refused2 minutes
- Install time
- 10 minutes
- Cold machine to finish
- 9 minutes
- Errors hit and fixed
- 3 hit, 3 fixed with no human help
- How the result was proved
- profile_table/clean_table/verify_numbers MASTER CHECK passed (claims 6000/9300 matched, exit 0); scan_traps exit 0; make_chart bar exit 0 and pie refusal exit 1; make_report all 4 formats exit 0; verify_visual html+deck exit 0 (no overflow, 0 console errors, 2 SVGs); verify_xlsx exit 0 fails []; verify_docx exit 0 fails [] (2 images); both --self-test suites exit 0; docx/xlsx zip integrity ok and embedded PNGs decoded by ffmpeg
- Model tokens used
- 835,072
- Exact commit tested
- 2492fabbafc8
- Container image
- sha256:cdd920bce783
What was not measured
The other half, so you can see exactly how far this evidence goes. A gap is printed as a gap and never filled in.
- Peak GPU memory
- this ran on a CPU machine, so there was no GPU to sample
- Behaviour over a long run
- each attempt uses the smallest documented settings and a fixed time budget, so this measures whether it runs, not how it holds up under load
The end of the recording
The last lines of the terminal session that decided this verdict, exactly as they were recorded.
- `huashu-excel` — a Python/agent-skill for Excel data analysis: profile → clean → reconcile → char… **Errors hit and fixes** 1. PEP 668 blocked system-wide `pip install` → created `/work/repo/venv`, installed `pandas 3.1.1` … 2. `make_report.py --format xlsx` output failed its own `verify_xlsx.py` gate (2 FAILs, 1 WARN): 18… 3. `verify_visual.py` skipped (exit 2) without playwright → installed `playwright 1.64.1` + headles… **Verified end-to-end (all exit 0 unless noted)** - Built `/tmp/demo.xlsx` (title rows, two-level header, subtotal row); `profile_table.py` found bot… - `verify_numbers.py --claim "1月 / 销售额(元):6000" --claim "2月 / 销售额(元):9300"` → exit 0, `MASTER CHECK… - `scan_traps.py` flagged the small-sample trap; `make_chart.py` bar chart saved; pie chart correct… - Reports: HTML + deck HTML + xlsx + docx generated; `verify_visual.py --json` html (svgCount 2, co… - Structure: `final.docx` — 2 embedded PNGs, image rels 2, `zip ok`; `final.xlsx` — 2 embedded char… Honest limitation: with no LibreOffice I could not render the OOXML files to images, and nothing he…
Replay the whole session, every command from a clean machine to this point.
How it was tested
One agent, one container, no human help. It installs the project the way its own documentation says to, runs it, and fixes what breaks. Everything below is recorded as it happened: the terminal session, the log and the exact commit. The full method.
Strengths and limits
Measured facts, not opinions. How this is written.
What went well
- Reached a running state on a clean machine, with the session recorded.
- Recovered from all 3 errors without a human stepping in, which says the failures are documented well enough to solve.
- Ran without a GPU, so it does not need one to start.
- Licensed MIT, as reported by its host.
What did not, or is not known
- Took 10 minutes to install, slower than the median of the 118 comparable projects Argusic has measured.
- Measured once so far. A single attempt shows it can run, not that it runs reliably.
Of the 119 agent-skills projects Argusic has installed and timed, huashu-excel was the 97th fastest to reach a running state, and 90 of 119 reached one at all.
What it is a reasonable choice for
- Trying it on a laptop or a small server: it reached a running state without a GPU.
- A quick evaluation: it was running 10 minutes after the clone.
Also tested, in the same area
Every one of these was installed and run by Argusic on a clean machine. Nothing appears here that was not tested.
Run history
Topics (from GitHub)
agent-skillsclaude-codeclaude-code-skillsclaude-skillscodexcursordata-analysisdata-cleaningdeepseek-harnessdsh-pluginexcelhuashu-skillsopenclawopenpyxlskillsspreadsheet
Embed the badge
Markdown for the project README. It links back here; terms on the terms page.
[](https://argusic.com/subject/huashu-excel)Questions
- Does huashu-excel run?
- Yes. huashu-excel runs. Argusic installed and launched it on a clean machine in 10 minutes, hitting 3 errors on the way, and recorded the session.
- How did Argusic test huashu-excel?
- On a fresh, disposable machine, with every command recorded and the repository pinned at commit 2492fabbafc8. One attempt is recorded, and the full method is on the methodology page.
- What did it cost to test huashu-excel?
- The run that produced this verdict cost $0.18: real compute and model cost, not a list price per million tokens. It is recorded on that run's page.
- How long does huashu-excel take to install?
- 10 minutes in the run that decided this verdict, from a clean machine to a running state. That is one measured attempt, not an average.
- Does huashu-excel need a GPU?
- Not to start. Argusic reached a running state on a machine with no GPU.
- What goes wrong when installing huashu-excel?
- 3 things broke in the recorded run, and 3 were fixed without human help. Each one, and the time it cost, is listed on this page.
- How does huashu-excel compare with the alternatives?
- Of the 119 agent-skills projects Argusic has installed and timed, huashu-excel was the 97th fastest to reach a running state, and 90 of 119 reached one at all.
- Where is the evidence for huashu-excel?
- The recorded run is on this page, each linking to its full log and terminal recording, stored with a sha256 fingerprint so it cannot be quietly altered.