xlsx

当电子表格文件是主要输入或输出时使用此技能。这意味着用户想要：打开、读取、编辑或修复现有的 .xlsx、.xlsm、.csv 或 .tsv 文件（例如添加列、计算公式、格式化、制图、清理混乱数据）；从头创建新的电子表格或从其他数据源创建；或在表格文件格式之间进行转换。当用户通过名称或路径引用电子表格文件时特别触发——即使是随意提及（如"我下载目录里的 xlsx"）——并且想对其进行操作或从中生成内容。也适用于将混乱的表格数据文件（格式错误的行、错位的表头、垃圾数据）清理或重构为规范的电子表格。交付物必须是电子表格文件。当主要交付物是 Word 文档、HTML 报告、独立 Python 脚本、数据库管道或 Google Sheets API 集成时不触发，即使涉及表格数据也不触发。

Quality

90%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Quality

Content

81%Weight 40%Scale 1-5

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The content is highly actionable with executable code and a clear validated workflow, and it makes good use of a scripts bundle for the heavy machinery. Its main weakness is redundancy—recalc.py instructions and the anti-hardcoding examples are repeated—modestly inflating token use.

Suggestions

Consolidate the recalc.py instructions into one section and have other steps reference it, instead of restating the invocation and its behavior in 通用工作流, 重新计算公式, and 重要要求.

Reduce the three near-identical '错误做法' formula examples to one and rely on a single contrasting correct example to make the same point more concisely.

Move the financial-modeling color-coding, number-format, and source-citation standards into a references/ file (e.g. FINANCIAL_MODELS.md) and link from the overview, since they are a specialized sub-domain not every xlsx task needs.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient and free of concepts Claude already knows, but the recalc.py usage is restated across the 通用工作流, 重新计算公式, and 重要要求 sections, and the use-formulas-not-hardcoded point illustrates three near-identical '错误做法' examples—more than minor trimming would remove.	3 / 5
Actionability	Provides copy-paste-ready pandas and openpyxl code, a concrete recalc.py invocation with arguments and timeout, the JSON output schema for interpreting results, and explicit error-code guidance covering the common cases.	5 / 5
Workflow Clarity	The numbered 通用工作流 sequences load → modify → save → recalc → validate/fix with an explicit feedback loop (if status is errors_found, fix and re-run), reinforced by a formula-validation checklist with checkpoints.	5 / 5
Progressive Disclosure	The body is well sectioned and points to real, clearly-signaled bundle files (scripts/recalc.py and scripts/office/soffice.py, both confirmed present), though some inlined standards (color coding, number formats, source-citation examples) could live in reference files to slim the overview.	4 / 5
	Total	17 / 20 Passed

Description

100%Weight 40%Scale 1-5

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

The description is a strong, third-person trigger description that comprehensively states capabilities, uses natural trigger terms including file extensions, answers both 'what' and 'when' explicitly, and sharply distinguishes itself from adjacent skills via negative triggers.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions—open/read/edit/repair .xlsx/.xlsm/.csv/.tsv, add columns, compute formulas, format, chart, clean messy data, create from scratch or other sources, and convert between formats—giving comprehensive coverage.	5 / 5
Completeness	Explicitly answers what it does (create/edit/convert spreadsheet files) and when to use it (user references a spreadsheet by name or path, even casually; cleaning messy tabular data), with an explicit 'Use when...' framing and concrete negative triggers.	5 / 5
Trigger Term Quality	Covers natural terms and synonyms users would say ('xlsx', '.xlsx/.xlsm/.csv/.tsv', 'spreadsheet', plus the example '我下载目录里的 xlsx') including file extensions.	5 / 5
Distinctiveness Conflict Risk	Clear niche (spreadsheet files as primary deliverable) with explicit negative triggers excluding Word docs, HTML reports, standalone Python scripts, database pipelines, and Google Sheets API integrations, minimizing conflict risk.	5 / 5
	Total	20 / 20 Passed

Validation

87%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 14 / 16 Passed

Validation for skill structure

Criteria	Description	Result
metadata_version	'metadata.version' is missing	Warning
referenced_paths_exist	Referenced path issues: 1 deeper-than-1-level	Warning

	Total	14 / 16 Passed

Repository: agentscope-ai/QwenPaw
Path: src/qwenpaw/agents/skills/xlsx-zh/SKILL.md
Commit: 1a4f4d8

Reviewed: 7 minutes ago

Table of Contents

Discovery Implementation Validation

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.