CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

3-statement-model

Build integrated IS/BS/CF financial workbooks in Excel.

Quality

69%

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/3-statement-model/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

73%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.

This is a strong, professionally structured skill: the workflow sequencing and validation apparatus are exemplary, with step-by-step user checkpoints and explicit integrity checks throughout. Its weaknesses are redundancy — the core linkage checks and input/formula conventions are stated multiple times — and one orphaned bundle file, which together keep conciseness and progressive disclosure a notch below excellent.

Suggestions

Consolidate the three overlapping integrity-check listings (Step 5 table, 'Core Linkages' table, and Check Categories Sections 2–6) into a single source of truth, pointing at references/formulas.md for detail.

Merge 'Understanding Template Structure' with 'Step 1: Analyze the Template Structure' — both cover input-vs-formula cell conventions, named ranges, and tab organization.

Link references/formatting.md from the formatting section (or remove it from the bundle) so every bundle file is discoverable from SKILL.md.

DimensionReasoningScore

Conciseness

Most of the body is dense, domain-specific tables (sign conventions, NOL rules, check formulas) that earn their tokens, but the same integrity checks appear three times — in 'Step 5: Cross-Statement Integrity Checks', 'Model Validation and Audit → Core Linkages', and again inside 'Check Categories' Sections 2–4 — and the input-vs-formula/font-color/named-range conventions are explained in both 'Understanding Template Structure' and 'Step 1'. This fits anchor 3 ('mostly efficient but includes some unnecessary explanation or could be tightened'); it is above anchor 2 because the padding is redundancy of genuinely useful content rather than explanation of things Claude already knows.

3 / 5

Actionability

The body gives concrete, executable guidance: an exact openpyxl formula-string example (ws['D15'] = '=D14*(1+Assumptions!$B$5)'), a recalc command, exact hex color codes, exact check formulas with expected results (Assets - Liabilities - Equity = 0), and precise settings (maximum iterations to 100, maximum change to 0.001). This matches anchor 4 ('mostly executable guidance with minor gaps'); anchor 5 is not reached because most operations (scenario dropdown setup, data validation, check-row construction) are described but not shown as copy-paste code — only one code snippet exists in ~420 lines of body.

4 / 5

Workflow Clarity

The 'Verify step-by-step with the user' protocol mandates stopping after each statement to show checks and confirm, the six-step completion process has explicit validation checkpoints per sheet plus cross-statement checks, and the 'Quick Debug Workflow' plus 'Master Check Formula' provide a fix-and-re-verify feedback loop for error recovery. This matches anchor 5 (clear sequence, explicit validation steps, feedback loops, checklists) exactly; it is clearly above anchor 4, which allows minor validation gaps.

5 / 5

Progressive Disclosure

The bundle is used at one level deep with well-signaled links: 'see [references/sec-filings.md] ... only needed when populating templates with public company data' and 'See [references/formulas.md] for all formula details', both of which exist as real files. This fits anchor 4 ('good structure; most content appropriately placed; references mostly clear; minor organization gaps'); it misses anchor 5 because references/formatting.md exists in the bundle but is never linked from SKILL.md (orphaned, undiscoverable), and the long inline 'Check Categories' sections 1–9 could themselves live in a reference file.

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 states a specific, distinct capability but reads like a title rather than a trigger: it has a clear 'what' and no 'when', and omits the natural vocabulary (three-statement model, financial model, income statement/balance sheet/cash flow) users would actually say. It sits at the mediocre middle of the scale — informative but not optimally matched.

Suggestions

Add a 'when' clause, e.g. 'Use when the user asks to build, complete, or audit an integrated three-statement financial model or mentions linking the income statement, balance sheet, and cash flow statement.'

Include natural synonyms and file extensions: 'three-statement model', 'financial model', '3-statement', '.xlsx' — alongside or in place of the IS/BS/CF abbreviation.

Optionally widen the 'what' slightly to cover the skill's other capabilities (populating templates, validation/audit checks, scenario toggles) so the description matches what the body delivers.

DimensionReasoningScore

Specificity

'Build integrated IS/BS/CF financial workbooks in Excel' names the domain and one concrete action with specific artifacts (IS/BS/CF, Excel), but coverage is not comprehensive — template population, validation, scenarios, and margin/credit analysis from the body are absent. This matches anchor 3 ('names domain and 1-2 concrete actions, but not comprehensive'); it is above anchor 2 (which lacks concrete actions) and below anchor 4 (which lists several specific actions).

3 / 5

Completeness

The 'what' is clear (build integrated IS/BS/CF financial workbooks in Excel), but there is no 'when' — no 'Use when...' clause or equivalent explicit trigger guidance, which per the judging guidelines caps completeness at 3. It is not anchor 2 (the 'what' is specific, not vague) and cannot be anchor 4 without any 'when' element.

3 / 5

Trigger Term Quality

'Excel' and 'IS/BS/CF' are terms finance users do say, but common natural variations are missing: 'three-statement model', 'financial model', 'income statement / balance sheet / cash flow' spelled out, '.xlsx'. Fits anchor 3 ('some relevant keywords but missing common variations or synonyms'); not anchor 2 (keywords are domain-relevant, not generic like 'works with files') and not anchor 4 (no synonyms or file extensions present).

3 / 5

Distinctiveness Conflict Risk

'integrated IS/BS/CF financial workbooks' carves out a distinct niche (three-statement integrated modeling vs. generic spreadsheet work), with only minor overlap risk against closely related skills such as excel-author, dcf-model, and lbo-model listed in the metadata. Matches anchor 4 ('mostly distinct; minor overlap risk with closely related skills'); anchor 5 would require explicit distinct trigger phrases that the description lacks.

4 / 5

Total

13

/

20

Passed

Validation

81%

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

CriteriaDescriptionResult

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/3-statement-model/SKILL.md

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.