XLSX Parsing

What it does

When your agent uses it

• Reference document is an .xlsx file rather than JSON/CSV
• Tasks that involve Excel spreadsheets
• Tasks that involve DataFrames

Example prompts

• “/xlsx-parsing”

Requirements

• Python 3

Workflow steps

3 steps, taken from the first numbered list in SKILL.md.

1. 1Multiple sheets, only one of which is the data you actually want.
2. 2Sparse cells — a row that uses a column may sit next to a row that doesn't, leaving None cells. Empty is meaningful (the rule does not…
3. 3Composite cells — a single cell that contains a comma-separated list, a JSON blob, or a sentence rather than an atomic value.

What it can do on your machine

Read from SKILL.md and the folder at commit 9a1f4dd. It shows what the files ask for, not the result of running them.

• Tool permissions

  Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

  From allowed-tools in the SKILL.md frontmatter.

• Runs code

  No scripts in the folder and no shell commands in SKILL.md (its code samples are python).

  From the folder's file list and the shell code blocks in SKILL.md.

• Network

  No URLs in SKILL.md.

  From URLs in SKILL.md, links to its own repository left out.

• Credentials

  Names no API keys, tokens, secrets or passwords.

  From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

XLSX Parsing loads about 1.4k tokens when it runs. Until then it costs about 87 tokens; SKILL.md has 529 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it

~87

When it runs · the whole SKILL.md, loaded when a task matches

~1.4k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from benchflow-ai/skillsbench at commit 9a1f4dd, republished under its Apache-2.0 licence (© benchflow-ai). 529 words, ~1,388 tokens.

name

xlsx-parsing

description

Read Microsoft Excel (.xlsx) files robustly with `openpyxl` (or `pandas`). Covers multi-sheet workbooks, header rows, empty cells, merged cells, comma-separated list cells, and converting a sheet to a list-of-dicts the rest of your code can consume. Use when a task input or reference document is an `.xlsx` file rather than JSON/CSV.

import openpyxl

wb = openpyxl.load_workbook("workbook.xlsx", data_only=True, read_only=True)
print(wb.sheetnames)            # e.g., ['Metadata', 'Definitions', 'Rules']

ws = wb["Rules"]
rows = ws.iter_rows(values_only=True)
header = [str(c).strip() if c else "" for c in next(rows)]
records = [dict(zip(header, row)) for row in rows if any(cell is not None for cell in row)]

import pandas as pd

# Multi-sheet read returns a dict of DataFrames
sheets = pd.read_excel("workbook.xlsx", sheet_name=None, dtype=object)
rules_df = sheets["Rules"]

# Drop fully-empty rows; keep partial rows
rules_df = rules_df.dropna(how="all")

# Iterate as dicts; NaN becomes None
records = rules_df.where(rules_df.notna(), None).to_dict(orient="records")

def get(rec, key, default=None):
    val = rec.get(key)
    return default if val is None or (isinstance(val, str) and not val.strip()) else val

def split_list_cell(value):
    if value is None:
        return []
    return [item.strip() for item in str(value).split(",") if item.strip()]

last = None
for row in records:
    if row["section"] is None:
        row["section"] = last
    else:
        last = row["section"]

import openpyxl

def load_sheet_as_records(wb, sheet_name):
    ws = wb[sheet_name]
    rows = ws.iter_rows(values_only=True)
    header = [str(c).strip() if c else "" for c in next(rows)]
    return [
        dict(zip(header, row))
        for row in rows
        if any(cell is not None for cell in row)
    ]

wb = openpyxl.load_workbook("workbook.xlsx", data_only=True, read_only=True)
metadata = {row[0]: row[1] for row in wb["Metadata"].iter_rows(min_row=2, values_only=True)}
defs  = load_sheet_as_records(wb, "Definitions")
rules = load_sheet_as_records(wb, "Rules")

© benchflow-ai, Apache-2.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in tasks-extra/nda-playbook-review/environment/skills/xlsx-parsing of benchflow-ai/skillsbench.

Open the folder on GitHubat commit 9a1f4dd