CtrlK
BlogDocsLog inGet started
Tessl Logo

officecli-financial-model

Use this skill when the user wants to build a financial model — 3-statement model, DCF valuation, LBO, SaaS unit economics, sensitivity / scenario analysis, debt schedule, or fundraising projections — in Excel. Trigger on: 'financial model', '3-statement model', 'P&L + BS + CF', 'DCF', 'WACC', 'NPV', 'terminal value', 'LBO', 'debt schedule', 'cash sweep', 'MOIC', 'IRR / XIRR', 'sensitivity table', 'scenario analysis', 'ARR model', 'unit economics', 'CAC / LTV', 'cap table forecast'. Output is a single formula-driven .xlsx. This skill is a scene layer on top of officecli-xlsx — it inherits every xlsx v2 rule (4-color code, visual floor, number formats, cache-drift, Known Issues, Delivery Gate minimum cycle). DO NOT invoke for a simple budget tracker, CSV dump, or operational KPI sheet — route those to officecli-xlsx base.

73

Quality

91%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Critical

Do not install without reviewing

SKILL.md
Quality
Evals
Security

Quality

Content

88%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.

A strong, highly actionable skill body with executable recipes, rigorous validation gates, and clear feedback loops. Its main weaknesses are repeated cache-drift guidance across sections and a large monolithic structure where the three recipes could be externalized into reference files.

Suggestions

Consolidate the cached-0 / cache-drift guidance: it is restated in Build-order & cache-drift, Financial function patterns, Gate 5, and Known Issues — define it once and cross-reference from the other sections to trim repetition.

Split the three recipes (3-statement, DCF, LBO) into per-recipe reference files (e.g. references/recipe-dcf.md) and keep SKILL.md as an overview with one-level-deep links, reducing the 47KB monolith.

Move the long Known Issues & Pitfalls list into a references/known-issues.md file, leaving a short inline summary plus a single clearly-signaled link.

DimensionReasoningScore

Conciseness

The body is dense and mostly actionable with no generic concept padding (it explicitly flags itself 'not a finance textbook' and tells Claude to pause and ask if unsure). It is not a 5 because the cached-0 / cache-drift guidance is restated across four sections (Build-order & cache-drift, Financial function patterns, Gate 5, Known Issues), and not a 3 because the content earns its tokens rather than being padded.

4 / 5

Actionability

It provides fully executable, copy-paste-ready bash commands and JSON batch heredocs with real formulas, named ranges, and concrete cell references across three complete recipes, matching the 'fully executable; specific examples cover the common cases' anchor.

5 / 5

Workflow Clarity

Each recipe has a MANDATORY build order and numbered Steps 1-8, plus explicit validation checkpoints (Gates 1-6, 5b, 6.1) and feedback loops ('fix and re-validate', convergence verify). Validation is present throughout, so the destructive/batch cap does not apply.

5 / 5

Progressive Disclosure

No bundle files exist; the skill is well-sectioned and clearly signals one-level-deep inheritance references ('→ see xlsx v2 §X', 'Read skills/officecli-xlsx/SKILL.md first'). It is not a 5 because three full recipes are inlined in a 47KB monolith that could be split into per-recipe reference files, and not a 3 because structure and external references are genuinely clear rather than buried.

4 / 5

Total

18

/

20

Passed

Description

95%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.

A strong, highly specific description that clearly states what it builds, when to trigger it (with an extensive natural-term trigger list and explicit anti-triggers), and how it differs from the base xlsx skill. Its only weakness is that the 'actions' are enumerated model types rather than multiple distinct verbs, keeping specificity just below the top anchor.

DimensionReasoningScore

Specificity

Names the financial-modeling domain and lists several concrete model types (3-statement, DCF, LBO, SaaS unit economics, sensitivity, debt schedule, fundraising) plus a specific output ('single formula-driven .xlsx'). It is not a 5 because the actions are enumerated model types rather than multiple distinct verbs as in the anchor-5 example, and not a 3 because coverage is clearly comprehensive rather than just 1-2 actions.

4 / 5

Completeness

It explicitly answers 'what' ('build a financial model … Output is a single formula-driven .xlsx') and 'when' ('Use this skill when the user wants to …', 'Trigger on: …', plus a negative-trigger 'DO NOT invoke for a simple budget tracker, CSV dump, or operational KPI sheet') with concrete trigger phrases.

5 / 5

Trigger Term Quality

The 'Trigger on:' list gives comprehensive natural terms including synonyms and abbreviations a user would actually say — 'financial model', 'DCF', 'WACC', 'NPV', 'IRR / XIRR', 'MOIC', 'CAC / LTV', 'sensitivity table', 'scenario analysis' — matching the comprehensive-coverage anchor.

5 / 5

Distinctiveness Conflict Risk

It carves a clear financial-modeling niche and explicitly de-conflicts with the related base skill ('route those to officecli-xlsx base'), giving distinct triggers and minimal overlap risk.

5 / 5

Total

19

/

20

Passed

Validation

93%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

skill_md_line_count

SKILL.md is long (562 lines); consider splitting into references/ and linking

Warning

Total

15

/

16

Passed

Repository
Team-Commonly/commonly
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.