excel-author

Build auditable financial workbooks headless via openpyxl.

Quality

64%

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 ./optional-skills/finance/excel-author/SKILL.md

Quality

Content

75%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 a strong, convention-driven skill file: executable code throughout, genuine openpyxl quirks (merge-cell styling, no recalculation), explicit validation (Checks tab, recalc step, user checkpoints), and a correctly referenced working script. Weaker spots are the partially-illustrative sensitivity code, the distributed rather than unified workflow, and a single bundle reference where a references/ split would slim the main file.

Dimension	Reasoning	Score
Conciseness	The body is dense with conventions, quirks, and code, with essentially no padding about concepts Claude already knows (no 'what is Excel' prose). It is not a 5 because the ~230-line body has minor trim opportunities — the Checks-tab pattern appears in both the conventions and the skeleton, and the sensitivity code block partially duplicates the stated rules above it.	4 / 5
Actionability	Nearly all guidance is executable: setup command, font-color constants, DefinedName usage, Comment usage, a copy-paste skeleton, a merged-cell quirk fix, and a real recalc command plus a working scripts/recalc.py. It is not a 5 because the sensitivity block is explicitly 'simplified for illustration' with placeholder ranges (FCF_range, year_offset) rather than copy-paste-ready code; it is above 3 because that simplification is explicitly justified in-line.	4 / 5
Workflow Clarity	Sequencing and checkpoints are present: the layout-planning section enforces plan-headers-before-formulas, the Checks tab provides TRUE/FALSE validation, the recalc step handles computed values, and 'Verify step-by-step with the user' gives explicit per-stage checkpoints. It is not a 5 because the end-to-end workflow is distributed across sections rather than presented as one coherent ordered sequence with feedback loops.	4 / 5
Progressive Disclosure	The body is well-sectioned with clear headers, and its one bundle reference ('see scripts/recalc.py in this skill') points to a real, working file. It is not a 5 because everything else is inlined in SKILL.md — detailed sections like the sensitivity-table recipe would sit naturally in a references/ file for a leaner overview; it is above 3 because the inlined content is core conventions, not bulk reference material.	4 / 5
	Total	16 / 20 Passed

Description

53%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 short, accurate, and appropriately third-person, with a clear 'what' and a distinct niche. Its main weakness is the complete absence of 'when to use' guidance and of the natural trigger vocabulary (Excel, .xlsx, financial model, DCF) users would actually say. Per the rubric's cap rule, the missing trigger clause limits completeness to 3.

Suggestions

Add an explicit trigger clause, e.g. 'Use when building financial models (DCF, 3-statement, LBO, comps) as .xlsx files, when the user asks for an Excel financial model, or when auditable banker-grade workbooks are required.'

Include natural synonyms and file extensions users would say — 'Excel', '.xlsx', 'spreadsheet', 'financial model', 'sensitivity tables' — alongside 'openpyxl'.

Optionally enumerate the concrete capabilities the skill encodes (color-coded inputs vs formulas, named ranges, balance checks tab, sensitivity tables, formula recalculation) to lift specificity from one action to several.

Dimension	Reasoning	Score
Specificity	The description names the domain ('auditable financial workbooks') and one concrete action ('Build ... headless via openpyxl'), which matches the 'names domain and 1-2 concrete actions' anchor. It does not list several specific actions (no mention of models built, checks tabs, sensitivity tables, formatting conventions), so it is not a 4.	3 / 5
Completeness	The 'what' is clear (build auditable financial workbooks headless via openpyxl), but there is no 'Use when...' clause or equivalent trigger guidance anywhere in the description; 'headless' weakly implies a context at best. Per the judging guidelines, a missing explicit trigger clause caps completeness at 3.	3 / 5
Trigger Term Quality	Terms like 'financial workbooks', 'openpyxl', and 'headless' are relevant, but the natural phrases users would say — 'Excel', '.xlsx', 'financial model', 'DCF', 'spreadsheet' — are all missing. This fits 'some relevant keywords but missing common variations or synonyms' rather than the good-coverage anchor at 4.	3 / 5
Distinctiveness Conflict Risk	'auditable financial workbooks ... via openpyxl' carves out a fairly distinct niche that would not trigger for generic document or data skills. There is minor overlap risk with closely related siblings (e.g., an xlsx-author or dcf-model skill), which matches the 'mostly distinct; minor overlap risk' anchor rather than the minimal-conflict anchor at 5.	4 / 5
	Total	13 / 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: optional-skills/finance/excel-author/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.