excel-author

Build auditable Excel workbooks headless with openpyxl — blue/black/green cell conventions, formulas over hardcodes, named ranges, balance checks, sensitivity tables. Use for financial models, audit outputs, reconciliations.

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

92%

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

A high-quality, highly actionable skill body: executable code, clear sequencing, and explicit validation/feedback loops for a complex domain. The main weakness is progressive disclosure — most material lives inline in SKILL.md with only one externalized bundle file.

Suggestions

Move the full skeleton and/or sensitivity-table code into reference files (e.g. references/skeleton.py, references/sensitivity.py) and link to them from a concise overview, so SKILL.md stays a navigable hub.

Consider extracting the blue/black/green convention detail or the checkpoint pattern into a references/ doc to deepen progressive disclosure beyond the single recalc.py helper.

Dimension	Reasoning	Score
Conciseness	The body is lean for its scope: nearly every section delivers a concrete convention or executable code block, and it avoids explaining basics Claude already knows (no 'what is Excel' padding); rationale sentences are domain-specific and earn their place.	3 / 3
Actionability	Provides fully executable, copy-paste-ready guidance throughout — pip install, a complete openpyxl skeleton, named-range/Checks/comment code, sensitivity-table loops, and a LibreOffice recalc command — with the referenced scripts/recalc.py verified to exist.	3 / 3
Workflow Clarity	Multi-step work is explicitly sequenced (the numbered 'Model layout planning' steps) with validation checkpoints (Checks tab TRUE/FALSE, recalc-before-delivery) and a feedback-loop checkpoint pattern for confirming intermediate artifacts with the user.	3 / 3
Progressive Disclosure	Sections are well-organized and the single scripts/recalc.py reference is clearly signaled and real, but the body is largely monolithic — long inline skeleton and sensitivity-table code blocks that could be externalized into reference files — so content that could be separate stays inline.	2 / 3
	Total	11 / 12 Passed

Description

85%

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, concrete description that states a specific action, enumerates the modeling conventions it enforces, and gives an explicit 'Use for' trigger. Its only gap is trigger-term breadth — it omits common user shorthand like '.xlsx' and 'spreadsheet'.

Suggestions

Add common file-extension and shorthand trigger terms (e.g. '.xlsx', 'spreadsheet', 'Excel model') so the description matches how users actually phrase the request.

Consider an explicit 'Use when the user mentions...' phrasing that mirrors the finance trigger terms to strengthen the when-clause further.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete techniques — 'blue/black/green cell conventions, formulas over hardcodes, named ranges, balance checks, sensitivity tables' — alongside the named tool openpyxl, matching the anchor that lists multiple specific concrete actions rather than a single vague verb.	3 / 3
Completeness	Explicitly answers what ('Build auditable Excel workbooks headless with openpyxl — ...') and when ('Use for financial models, audit outputs, reconciliations.'), with an explicit 'Use for' trigger clause matching the top anchor.	3 / 3
Trigger Term Quality	Includes natural terms like 'Excel workbooks' and 'financial models' but misses common variations users would say such as '.xlsx', 'spreadsheet', or 'model', matching the anchor for some relevant keywords missing common variations.	2 / 3
Distinctiveness Conflict Risk	The 'auditable ... headless with openpyxl' framing plus finance-specific triggers ('financial models, audit outputs, reconciliations') carve a clear niche distinct from a generic xlsx skill, making wrong-skill triggering unlikely.	3 / 3
	Total	11 / 12 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: optional-skills/finance/excel-author/SKILL.md
Commit: 4c9628e

Reviewed: about 15 hours 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.