comps-analysis

Build comparable company analysis in Excel — operating metrics, valuation multiples, statistical benchmarking vs peer sets. Pairs with excel-author. Use for public-company valuation, IPO pricing, sector benchmarking, or outlier detection.

Quality

73%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./optional-skills/finance/comps-analysis/SKILL.md

Quality

Content

47%

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

The content is highly actionable with a clear, well-validated workflow, but it is far too verbose and repetitive for a skill body — restating known concepts and duplicating sections — and uses a monolithic structure with references to bundle files that do not exist.

Suggestions

Cut roughly half the body: remove the explanations of known concepts (EBITDA/quartile definitions, the generic Excel formula reference) and consolidate the industry-specific metric lists and duplicate "Section 6" into a single section.

Replace placeholder formula examples (=[Enterprise Value]/[LTM Revenue]) with concrete cell-reference examples consistent with the =E7/C7 style used elsewhere.

Either create the referenced bundle files (examples/comps_example.xlsx, the excel-author recalc script) or move large reference material (formulas guide, industry add-ons) into separate one-level-deep reference files rather than a monolithic SKILL.md.

Dimension	Reasoning	Score
Conciseness	The ~650-line body is verbose and padded: it explains concepts Claude already knows (what EBITDA/quartiles are, "75th percentile = Premium companies", a full Excel formula reference of =AVERAGE/=MEDIAN) and repeats content across sections (industry metric lists appear in Sections 5, 6, and 9; two sections are both numbered "Section 6").	1 / 3
Actionability	Provides concrete executable guidance ("cell.value = \"=E7/C7\"", "=QUARTILE(B7:B9,3)", exact hex colors, ASCII layout), but some core examples use placeholders ("EV/Revenue: =[Enterprise Value]/[LTM Revenue]") instead of real cell references, leaving key details incomplete.	2 / 3
Workflow Clarity	Section 7 gives a clearly sequenced step-by-step build process with time estimates, and the "Formulas Over Hardcodes + Step-by-Step Verification" section provides explicit verification checkpoints (show headers before filling data, confirm inputs before formulas, sanity-check before statistics) plus an output checklist.	3 / 3
Progressive Disclosure	No bundle files exist (references/, scripts/, assets/ are absent) and the content is a monolithic single-file wall of text; it references examples/comps_example.xlsx and excel-author/scripts/recalc.py that are not present in the bundle, though section-level organization is reasonable.	2 / 3
	Total	8 / 12 Passed

Description

100%

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, concrete, and fully answers both what the skill does and when to use it with natural trigger terms and third-person voice. It is a strong, well-scoped skill description with no notable weaknesses.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — "Build comparable company analysis in Excel", "operating metrics, valuation multiples, statistical benchmarking vs peer sets" — rather than vague language.	3 / 3
Completeness	Explicitly answers both what (build comps with operating metrics, multiples, benchmarking) and when ("Use for public-company valuation, IPO pricing, sector benchmarking, or outlier detection").	3 / 3
Trigger Term Quality	Covers natural user-facing terms — "public-company valuation, IPO pricing, sector benchmarking", "outlier detection", "comparable company analysis", "Excel" — that a user would actually say.	3 / 3
Distinctiveness Conflict Risk	Has a clear niche (comps/valuation analysis) with distinct triggers and explicit pairing with excel-author, making conflicts with other skills unlikely.	3 / 3
	Total	12 / 12 Passed

Validation

75%

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 — 12 / 16 Passed

Validation for skill structure

Criteria	Description	Result
skill_md_line_count	SKILL.md is long (663 lines); consider splitting into references/ and linking	Warning
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	12 / 16 Passed

Repository: NousResearch/hermes-agent
Path: optional-skills/finance/comps-analysis/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.