CtrlK
BlogDocsLog inGet started
Tessl Logo

comps-analysis

Build comparable-company valuation workbooks in Excel.

48

Quality

55%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

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

Quality

Content

56%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 delivers genuinely strong, concrete finance-modeling instruction with explicit per-stage verification and quality checks, but it is a bloated monolith: it repeats itself across redundant sections, explains Excel basics Claude already knows, and keeps everything inline instead of splitting reference material into bundle files (which the bundle doesn't even contain). Trimming duplication and moving the reference-guide material out would substantially cut its token footprint without losing instruction.

Suggestions

Deduplicate the industry-specific metric guidance (Sections 5, 6-Advanced, and 9 all cover the same ground) and collapse the two "Section 6" sections into one — this alone would remove well over 100 lines.

Delete the "Essential Excel Formulas" guide (=AVERAGE, =MEDIAN, =MAX, =MIN, STDEV.P) and definitions Claude already knows (what EBITDA/P/E stand for); keep only the domain-specific patterns.

Split reference material (formulas reference, industry additions, formatting checklist) into files under references/ and either add the referenced examples/comps_example.xlsx or remove the dangling reference to it.

DimensionReasoningScore

Conciseness

The ~650-line body is noticeably verbose: it re-teaches Excel basics Claude already knows (=MEDIAN, =MAX, =AVERAGE, STDEV.P, what EBITDA stands for), repeats industry-specific metric lists three times (Sections 5, 6-Advanced, and 9), restates the statistics-block formatting rule in at least four places, and even contains two different sections both numbered "Section 6". Several padded "Why this matters" commentary blocks add tokens without adding instruction.

2 / 5

Actionability

Guidance is mostly executable: exact cell formulas ("Gross Margin (F7): =E7/C7", "=QUARTILE(B7:B9,3)"), a concrete header block, an ASCII template layout, explicit color hexes, and a recalc command. Minor gaps: placeholder formulas like "=[FCF]/[Revenue]" instead of cell references, and the referenced examples/comps_example.xlsx does not exist in the bundle.

4 / 5

Workflow Clarity

Section 7 lays out a clearly sequenced 6-step process, the "Formulas Over Hardcodes" section mandates per-stage user-verification checkpoints (show header layout, confirm inputs, sanity-check margins), and QC includes error auditing (#DIV/0!, #REF!) plus a delivery checklist and pre-delivery recalc. Minor incoherence — duplicated Section 6 numbering, a 10-section numbering scheme that restarts, and the truncated line "🚩ixing pure-play and conglomerates" — keeps it below 5.

4 / 5

Progressive Disclosure

The body has section structure, but no bundle files exist at all: references/, scripts/, assets/ are absent and the one referenced path (examples/comps_example.xlsx) is dangling. Hundreds of lines that clearly belong in separate reference files — the full Excel formulas reference guide, the thrice-repeated industry-specific additions, the formatting checklists — are inlined in SKILL.md, matching the anchor for content that should be separate being inline.

3 / 5

Total

13

/

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 communicates a clear, concrete capability but is bare-bones: it answers only "what" with a single action, provides no "when to use" trigger guidance, and omits the field's natural vocabulary ("comps", "trading comps", "peer analysis", "multiples"). It sits solidly at the midpoint of the rubric.

Suggestions

Add an explicit trigger clause, e.g. "Use when the user asks for comparable-company analysis, trading comps, peer benchmarking, or valuation multiples (EV/Revenue, EV/EBITDA, P/E) in an Excel workbook."

Enumerate the key actions to lift specificity: e.g. "build comps workbooks with operating metrics, valuation multiples, and quartile statistics" instead of the single verb "build".

Include the natural synonyms practitioners use — "comps", "trading comps", "peer analysis", ".xlsx" — so the skill triggers on how users actually phrase the request.

DimensionReasoningScore

Specificity

"Build comparable-company valuation workbooks in Excel" names the domain and one concrete action (building workbooks) but does not list the several specific actions (populating multiples, computing quartile statistics, benchmarking) that a 4 or 5 requires.

3 / 5

Completeness

The "what" is clear (build comparable-company valuation workbooks in Excel), but there is no "Use when..." clause or any trigger guidance at all, which caps completeness at 3 per the judging guidelines.

3 / 5

Trigger Term Quality

Relevant keywords are present ("comparable-company", "valuation", "Excel"), but the natural terms practitioners actually say are missing: "comps", "trading comps", "peer analysis", "multiples", ".xlsx" — matching the anchor for some relevant keywords missing common variations.

3 / 5

Distinctiveness Conflict Risk

"Comparable-company valuation workbooks" carves a fairly distinct niche, though it could overlap with closely related finance skills (dcf-model, lbo-model, excel-author) mentioned in its own metadata — minor overlap risk only.

4 / 5

Total

13

/

20

Passed

Validation

75%

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

CriteriaDescriptionResult

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
Reviewed

Table of Contents

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.