xlsx

Create, inspect, edit, restructure, recalculate, convert, and visually verify Excel .xlsx workbooks and CSV data.

Quality

78%

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

Fix and improve this skill with Tessl

tessl review fix ./packages/ekko-agent/skills/xlsx/SKILL.md

Quality

Content

86%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 well-structured, token-efficient skill body: concrete commands, a sequenced workflow with verification and visual-check steps, and correctly deferred detail in real bundle files. The only gaps are the unspecified JSON spec formats and the lack of an explicit failure-recovery loop.

Dimension	Reasoning	Score
Conciseness	The ~45-line body is lean and operational throughout — helper table, runnable command examples, a 6-step workflow, and hard integrity rules — with no explanation of concepts Claude already knows. Every section earns its place, matching the 'lean and efficient' anchor.	5 / 5
Actionability	Concrete, executable guidance: 'python3 -m pip install openpyxl' and four runnable helper invocations with argument shapes. Not 5 because the JSON spec formats (spec.json, edits.json) are delegated to '--help' rather than shown, leaving a minor gap for the most common creation/edit cases.	4 / 5
Workflow Clarity	The workflow is a clear 6-step sequence with explicit verification checkpoints ("Re-read formulas and values. Recalculate when the output depends on formula results", visual PDF verification). Not 5 because there is no explicit error-recovery feedback loop (what to do when validation or recalculation fails); not 3 because multiple checkpoints are present and well placed.	4 / 5
Progressive Disclosure	The body is a concise overview with a clearly signaled, one-level-deep reference ('read references/restructuring.md') and pointers to the seven real bundled scripts; restructuring detail is correctly deferred out of line. Scored against the actual bundle structure, all referenced files exist.	5 / 5
	Total	18 / 20 Passed

Description

71%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.

A strong, specific, third-person description that names the domain and enumerates concrete capabilities. Its main weakness is the complete absence of a 'when to use' trigger clause, which caps completeness, and thin synonym coverage (no 'spreadsheet' or 'tabular data').

Suggestions

Append a trigger clause such as: 'Use when working with Excel workbooks, spreadsheets, .xlsx files, CSV data, or tabular data, or when the user mentions formulas, pivot tables, or recalculation.'

Add natural synonyms users actually say — 'spreadsheet', 'tabular data', 'Excel files' — alongside the existing '.xlsx' and 'CSV' terms to improve trigger-term coverage.

Consider narrowing or qualifying the CSV claim (e.g., 'convert between Excel .xlsx and CSV') to reduce overlap with generic data-processing skills.

Dimension	Reasoning	Score
Specificity	The description lists seven concrete actions ("Create, inspect, edit, restructure, recalculate, convert, and visually verify") and names both target formats ("Excel .xlsx workbooks and CSV data"), matching the comprehensive multi-action anchor. Not 4 because coverage of the domain's core operations is complete rather than having minor gaps.	5 / 5
Completeness	The 'what' is explicit and concrete, but there is no 'Use when...' clause or equivalent trigger guidance — the judging guideline caps completeness at 3 in that case. Not 4 because 'when' is not even weakly implied by the action list.	3 / 5
Trigger Term Quality	It includes natural terms users say — "Excel", ".xlsx", "CSV data", "workbook" — but misses common synonyms like "spreadsheet" or "tabular data" that users often use instead of "workbook". Not 5 because the anchor requires comprehensive synonym coverage; not 3 because the extension and product name are present and natural.	4 / 5
Distinctiveness Conflict Risk	The Excel/.xlsx niche is clear and distinct, but "CSV data" is broad and overlaps with generic data-processing and conversion skills. Not 5 because the CSV half of the claim creates minor-to-moderate overlap risk with closely related data skills; not 3 because the .xlsx/Excel anchors keep it mostly distinct.	4 / 5
	Total	16 / 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
metadata_field	'metadata' should map string keys to string values	Warning

	Total	14 / 16 Passed

Repository: EKKOLearnAI/hermes-studio
Path: packages/ekko-agent/skills/xlsx/SKILL.md
Commit: 07ccb17

Reviewed: 5 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.