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.

71

Quality

88%

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

81%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 highly actionable, well-sequenced skill body with excellent validation gates and feedback loops for fragile batch/circular-write operations. Its main weakness is conciseness: cache-drift and write-order guidance is restated across multiple sections, and the lack of any bundle files means three long recipes and reference tables live entirely inline.

Suggestions

Consolidate the cache-drift / write-order-surgery guidance into one canonical section and have other sections link to it (e.g. '→ §Build-order & cache-drift') instead of restating the rules.

Consider splitting the three model recipes into separate reference files (e.g. references/recipe-3statement.md, recipe-dcf.md, recipe-lbo.md) and keeping SKILL.md as an overview that points to them, to improve progressive disclosure.

Move the Financial function patterns table and Known Issues list into a references/ file so the main body leads with architecture, recipes, and gates.

DimensionReasoningScore

Conciseness

The body is dense and mostly task-specific (runnable skeletons, explicit "not finance theory" / "terse reference" disclaimers), but cache-drift and write-order-surgery guidance is repeated across the Build-order, Circular-references, and Known Issues sections, and several callouts reappear in slightly different form — it could be tightened by consolidating those passages.

3 / 5

Actionability

Fully executable, copy-paste-ready bash heredocs with concrete cell paths, formulas, number formats, and prop flags across three complete recipes (3-statement, DCF, LBO), plus verification readbacks — specific examples cover the common model-building cases.

5 / 5

Workflow Clarity

Each recipe has a mandatory build order with numbered steps (Recipe A Steps 1–8) and the Audit & Delivery Gate section provides explicit validation checkpoints (Gates 1–6, 5b, 6.1) with REJECT/exit feedback loops and convergence-verify routines for the risky batch/circular-write operations.

5 / 5

Progressive Disclosure

Strong cross-skill progressive disclosure — it repeatedly defers to the base skill via clearly signaled one-level-deep references ("→ see xlsx v2 §X", "inherits, not re-taught") instead of re-teaching xlsx rules — but within this skill everything is inlined in a 555-line monolith with no bundle files, and the three full recipes could arguably be split into separate reference files.

4 / 5

Total

17

/

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 high-quality description: third-person voice, explicit what-and-when, comprehensive natural trigger terms, and a clear reverse-routing boundary against the base xlsx skill. The only mild weakness is that the concrete 'actions' are essentially one verb (build) applied to many model subtypes rather than several distinct verbs.

DimensionReasoningScore

Specificity

Names the concrete action ("build a financial model ... in Excel", "Output is a single formula-driven .xlsx") and enumerates many specific model types (3-statement, DCF, LBO, SaaS unit economics, sensitivity, debt schedule, fundraising), but the action set is largely one verb with comprehensive subtype coverage rather than multiple distinct actions.

4 / 5

Completeness

Explicitly answers both what ("build a financial model ... Output is a single formula-driven .xlsx") and when ("Use this skill when the user wants to..." plus a concrete 'Trigger on' list), with concrete trigger phrases and a reverse-routing exclusion clause.

5 / 5

Trigger Term Quality

An explicit, exhaustive trigger list including natural phrases and synonyms users would say ('financial model', 'DCF', 'WACC', 'NPV', 'IRR / XIRR', 'CAC / LTV', 'cap table forecast'), plus the .xlsx output context — comprehensive coverage with synonyms.

5 / 5

Distinctiveness Conflict Risk

Clear niche (financial modeling in Excel via officecli) with distinct finance-specific triggers and an explicit reverse handoff ("DO NOT invoke for a simple budget tracker, CSV dump, or operational KPI sheet — route those to officecli-xlsx base") that minimizes conflict with the sibling skill.

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 (561 lines); consider splitting into references/ and linking

Warning

Total

15

/

16

Passed

Repository
iOfficeAI/OfficeCLI
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.