xlsx

Create, read, edit Excel .xlsx workbooks and CSVs.

Quality

85%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

High

Do not use without reviewing

Quality

Content

100%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.

An exemplary script-based skill body: dense, executable, and pitfall-driven, with clear sequencing and a verification checklist for risky in-place operations. Detail is properly pushed to script --help output and a single well-signaled reference file.

Dimension	Reasoning	Score
Conciseness	Every section carries non-obvious information (script CLIs, spec schema keys, openpyxl gotchas like "openpyxl itself NEVER evaluates formulas" and "data_only=True then save silently discards all formulas") with no library tutorials or padding; it assumes Claude's competence throughout.	5 / 5
Actionability	The body provides copy-paste-ready argparse commands in "How to Run", a Quick Reference table covering ~20 concrete tasks with exact flags, and exact spec syntax ("--set \"A1==SUM(B:B)\"", "{\"value\": \"2026-01-31\", \"type\": \"date\"}"); everything is executable, not pseudocode.	5 / 5
Workflow Clarity	A numbered Procedure sequences create/read/edit/restructure/CSV with ordering semantics ("applies renames/copies first, then structural changes, then --set/--append"), and a dedicated Verification section gives explicit per-operation checkpoints (re-dump ranges, re-run --formulas, review the JSON report's not_shifted list), satisfying the feedback-loop requirement for destructive in-place edits.	5 / 5
Progressive Disclosure	The body is an overview over seven --help-documented CLI scripts, and the one deep-dive topic is clearly signaled twice as "references/restructuring.md" (verified to exist and match its description), keeping references one level deep and easy to navigate.	5 / 5
	Total	20 / 20 Passed

Description

70%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 tight, third-person description with concrete verbs and file extensions, but it answers only "what" and not "when". Adding an explicit trigger clause and the "spreadsheet" synonym would move it into the top examples.

Suggestions

Append a trigger clause, e.g. "Use when working with Excel spreadsheets, .xlsx workbooks, or CSV files, or when the user mentions Excel, sheets, or workbook data."

Include the synonym "spreadsheet" and the ".csv" extension alongside "Excel .xlsx workbooks and CSVs" to broaden natural trigger coverage.

Consider naming one more distinguishing capability (e.g. restructure sheets with reference rewriting, or headless recalculation) so the description reflects the skill's full scope.

Dimension	Reasoning	Score
Specificity	"Create, read, edit Excel .xlsx workbooks and CSVs" names the domain and three concrete actions with explicit formats, matching the several-specific-actions anchor; not 5 because broader capabilities (restructuring, recalculation, PDF conversion) are not surfaced, and not 3 because coverage of the core create/read/edit loop is explicit and concrete.	4 / 5
Completeness	The "what" is clear and concrete, but there is no "Use when..." clause or equivalent trigger guidance, which caps completeness at 3 per the judging guidelines; not 4 because the when is entirely absent rather than merely implicit.	3 / 5
Trigger Term Quality	Natural trigger terms are present ("Excel", ".xlsx", "workbooks", "CSVs") with the file extension included, but common synonyms like "spreadsheet" and ".csv" are missing, fitting the good-coverage-with-a-few-gaps anchor.	4 / 5
Distinctiveness Conflict Risk	Excel/.xlsx/CSV triggers form a clear niche distinct from sibling document skills (docx, pdf, powerpoint); "workbooks" and ".xlsx" are unambiguous triggers with minimal overlap risk.	5 / 5
	Total	16 / 20 Passed

Validation

81%

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 — 13 / 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
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	13 / 16 Passed

Repository: NousResearch/hermes-agent
Path: skills/productivity/xlsx/SKILL.md
Commit: 68fa7e9

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.