xlsx

Use this skill any time a spreadsheet file is the primary input or output. This means any task where the user wants to: open, read, edit, or fix an existing .xlsx, .xlsm, .csv, or .tsv file (e.g., adding columns, computing formulas, formatting, charting, cleaning messy data); create a new spreadsheet from scratch or from other data sources; or convert between tabular file formats. Trigger especially when the user references a spreadsheet file by name or path — even casually (like "the xlsx in my downloads") — and wants something done to it or produced from it. Also trigger for cleaning or restructuring messy tabular data files (malformed rows, misplaced headers, junk data) into proper spreadsheets. The deliverable must be a spreadsheet file. Do NOT trigger when the primary deliverable is a Word document, HTML report, standalone Python script, database pipeline, or Google Sheets API integration, even if tabular data is involved.

Quality

88%

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

77%

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

The body is highly actionable with strong validation workflows and verified bundle references, but is somewhat verbose and presents most detailed domain standards inline rather than via progressive disclosure into separate files.

Suggestions

Tighten conciseness by collapsing the three repeated hardcoded-vs-formula examples into a single before/after pair and removing the duplicate error-code definitions that appear in both the workflow and best-practices sections.

Split the financial-modeling standards (color-coding RGB values, number-format rules, hardcoding source documentation) into a separate references/ file (e.g. FINANCIAL_MODELING.md) and link to it one level deep, raising progressive disclosure toward level 3.

Consider moving the full scripts/recalc.py JSON output schema and the detailed formula-checklist into a reference file, keeping SKILL.md as a concise overview with well-signaled pointers.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient executable guidance, but the hardcoded-vs-formulas section repeats the same lesson three times and error-code meanings (#REF!, #DIV/0!) are restated in multiple places; it could be tightened and assumes less. It is above level 1 (no padded conceptual explanation) but below level 3 because not every token earns its place.	2 / 3
Actionability	Provides copy-paste-ready openpyxl/pandas code, exact commands ('python scripts/recalc.py output.xlsx 30'), specific RGB color codes and format strings ($#,##0;($#,##0);-), and the JSON output schema, matching the fully-executable anchor.	3 / 3
Workflow Clarity	The numbered '通用工作流' explicitly sequences the required recalc step and includes a validation feedback loop (run recalc -> if status is errors_found -> fix and re-run), supported by a formula-verification checklist, matching the anchor for clear sequence with explicit validation and error-recovery loops.	3 / 3
Progressive Disclosure	Sections are well-organized and the body correctly references real bundle files (scripts/recalc.py and scripts/office/soffice.py, both verified to exist), but the SKILL.md is a fairly long monolithic wall keeping domain standards (color codes, number-format rules, formula-construction guidance) inline rather than splitting them into separate reference files; it is above level 1 but lacks one-level-deep reference splitting of level 3.	2 / 3
	Total	10 / 12 Passed

Description

100%

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 precise, action-rich, and unambiguous about both capabilities and triggering contexts, with explicit negative examples that sharply delimit the skill's scope.

Dimension	Reasoning	Score
Specificity	Lists many concrete actions such as 'open, read, edit or repair existing .xlsx, .xlsm, .csv or .tsv files (e.g. adding columns, calculating formulas, formatting, charting, cleaning messy data)' plus 'create new spreadsheets from scratch' and 'convert between tabular file formats', matching the anchor for listing multiple specific concrete actions.	3 / 3
Completeness	It explicitly answers both 'what' (the enumerated actions) and 'when' via the explicit 'Use this skill when...' trigger clauses and 'Particularly triggered when...', plus explicit non-triggers, satisfying the anchor for clearly answering both what and when.	3 / 3
Trigger Term Quality	Covers natural user terms including the file extensions (.xlsx, .xlsm, .csv, .tsv), 'spreadsheet file', and a casual example ('the xlsx in my downloads folder'), giving good coverage of phrases a user would actually say.	3 / 3
Distinctiveness Conflict Risk	A clear spreadsheet niche is bounded by explicit exclusions ('Does not trigger when the primary deliverable is a Word document, HTML report, standalone Python script, database pipeline, or Google Sheets API integration'), making conflict with other skills unlikely.	3 / 3
	Total	12 / 12 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-en/SKILL.md
Commit: 734c8b9

Reviewed: 3 days 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.