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

94%

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

88%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.

A strong, actionable body with executable code, a clear validation-equipped workflow, and a verification checklist. Minor conciseness and progressive-disclosure gaps exist from repeated recalc guidance and inlined specialized financial-model standards.

Suggestions

Consolidate the recalc instructions into one section; the Common Workflow, 'Recalculating formulas' section, and Best Practices all restate the same scripts/recalc.py usage.

Move the financial-model color-coding and number-formatting standards into a separate reference file (e.g., references/financial-models.md) and link to it from the body to reduce inlined specialized content.

Trim basic library explanations (e.g., default pandas read_excel behavior) that Claude already knows to improve token efficiency.

Dimension	Reasoning	Score
Conciseness	Mostly efficient with executable code and actionable checklists, but the recalc step is restated across three sections and basic pandas/openpyxl usage is slightly over-explained for Claude's competence.	4 / 5
Actionability	Provides fully executable, copy-paste-ready code for pandas reading/writing, openpyxl creation and editing, and concrete recalc commands with JSON output schemas covering the common cases.	5 / 5
Workflow Clarity	The 6-step Common Workflow sequences tool choice through save, marks recalc as mandatory, and includes a validate-then-fix-then-recalculate feedback loop, supplemented by a dedicated Formula Verification Checklist.	5 / 5
Progressive Disclosure	Well-organized with clear section headers and a real scripts/recalc.py reference, but the specialized financial-model color-coding and number-formatting standards are inlined rather than split into a dedicated reference file.	4 / 5
	Total	18 / 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.

An exemplary description: concrete actions, comprehensive natural trigger terms including file extensions and casual phrasings, explicit when/what guidance, and clear negative boundaries to avoid conflicts. Third-person voice is maintained throughout.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions (open, read, edit, fix, add columns, compute formulas, format, chart, clean data, create, convert) across the spreadsheet domain with comprehensive coverage.	5 / 5
Completeness	Explicitly answers both 'what' (open/read/edit/fix/create/convert) and 'when' ('Use this skill any time a spreadsheet file is the primary input or output', 'Trigger especially when...'), plus explicit negative triggers.	5 / 5
Trigger Term Quality	Covers natural terms and synonyms including file extensions (.xlsx, .xlsm, .csv, .tsv), casual phrasings ('the xlsx in my downloads'), and messy-data descriptors (malformed rows, misplaced headers, junk).	5 / 5
Distinctiveness Conflict Risk	Clear niche (spreadsheet file as primary input/output) with explicit 'Do NOT trigger' boundaries for Word, HTML, Python scripts, database pipelines, and Google Sheets, minimizing overlap with related skills.	5 / 5
	Total	20 / 20 Passed

Validation

100%

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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: nextlevelbuilder/goclaw
Path: skills/xlsx/SKILL.md
Commit: 169e0ba

Reviewed: 2 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.