Name: xlsx-author
Rating: 65.60000000000001 (1 reviews)
Author: anthropics

xlsx-author

Produce a .xlsx file on disk (headless) instead of driving a live Excel workbook — for managed-agent sessions with no open Office app.

Quality

82%

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

The canonical home for this skill is xlsx-author in anthropics/financial-services

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.

The body is an exemplar of lean, actionable skill writing: a crisp output contract, runnable openpyxl code, and a conventions section that encodes domain rules without padding. The only real gaps are the missing verification step in the workflow and un-exemplified conventions like the Checks tab.

Suggestions

Add a verification checkpoint after saving (e.g. re-open the file or check it exists) and instruct to retry/fix on failure, which would lift workflow clarity to an explicit feedback loop.

Add a two-line code snippet for the Checks tab (e.g. a TRUE/FALSE tie-out formula) since it is a stated convention but never shown, and note openpyxl availability/installation for headless environments.

Dimension	Reasoning	Score
Conciseness	At roughly 37 lines, the body explains nothing Claude already knows; every section (output contract, build example, conventions, when-not-to-use) earns its place. Matches anchor 5 (lean, assumes competence); anchor 4 would require something to trim, and nothing qualifies.	5 / 5
Actionability	Provides an executable, copy-paste openpyxl snippet plus a concrete output contract ("Write to ./out/<name>.xlsx. Create ./out/ if it does not exist"). Not 5: minor gaps remain — no openpyxl availability/install note, and the Checks tab convention is stated without example code.	4 / 5
Workflow Clarity	The sequence is coherent and the contract explicit: write a Python script, run it with Bash, save to ./out/, and 'Return the relative path in your final message'. Not 5 because there is no verification checkpoint that the file was actually written; not 3 because steps and contract are explicit, not implicit.	4 / 5
Progressive Disclosure	A sub-50-line, single-purpose skill with well-organized sections and no external references needed; per the rubric's simple-skill guideline this matches anchor 5. No bundle files (references/, scripts/, assets/) exist, and no in-body file references are made, so there is nothing further to verify.	5 / 5
	Total	18 / 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.

The description is concise and clearly states what it does and the mode it applies to, with a helpful explicit contrast against live-workbook editing. It is held back by thin capability coverage (one action) and the absence of natural user trigger phrasing like "spreadsheet" or "create/build".

Suggestions

Enumerate the concrete capabilities (create workbooks, write formulas, apply blue/black/green formatting conventions, add a Checks tab) instead of the single 'Produce a .xlsx file' action.

Add natural trigger phrasing, e.g. 'Use when the user asks for a spreadsheet or Excel file in a headless/managed-agent session' to cover synonyms and lift trigger term quality and completeness.

Include the word "spreadsheet" as a synonym for Excel/xlsx to broaden natural keyword coverage.

Dimension	Reasoning	Score
Specificity	Names the domain (".xlsx", "Excel workbook") and one concrete action ("Produce a .xlsx file on disk"), but lists no other capabilities such as formulas, styling, or checks tabs. This matches anchor 3 (domain plus 1-2 concrete actions, not comprehensive), not anchor 4 which requires several specific actions.	3 / 5
Completeness	Both are present: what ("Produce a .xlsx file on disk (headless)") and when ("for managed-agent sessions with no open Office app"). Not 5 because the when-clause lacks natural user-facing trigger phrases, and not 3 because the when is explicit rather than merely implied.	4 / 5
Trigger Term Quality	Good keyword coverage including the file extension: ".xlsx", "Excel workbook", "Office app". Falls short of anchor 5 because common synonyms like "spreadsheet" and natural user verbs ("create/build an Excel file") are missing, but exceeds anchor 3's 'some relevant keywords'.	4 / 5
Distinctiveness Conflict Risk	The explicit contrast ("instead of driving a live Excel workbook") carves a mostly distinct niche with minor overlap risk against generic xlsx-creation skills. Not 5 because the distinguishing condition is session-state-based rather than request-based, so ".xlsx"/"Excel" triggers still overlap related skills.	4 / 5
	Total	15 / 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: anthropics/financial-services
Path: plugins/agent-plugins/valuation-reviewer/skills/xlsx-author/SKILL.md
Commit: 574ed36

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.