CtrlK
BlogDocsLog inGet started
Tessl Logo

creating-financial-models

This skill provides an advanced financial modeling suite with DCF analysis, sensitivity testing, Monte Carlo simulations, and scenario planning for investment decisions

45

Quality

47%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./skills/custom_skills/creating-financial-models/SKILL.md

The canonical home for this skill is creating-financial-models in anthropics/claude-cookbooks

SKILL.md
Quality
Evals
Security

Quality

Content

28%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 reads as a feature catalog rather than executable guidance: it is verbose with generic best-practice padding, contains no runnable code or concrete workflow, and references scripts that are not present in the bundle. It is reasonably sectioned but inlines content that belongs in separate reference files.

Suggestions

Replace the descriptive capability lists with concrete, executable guidance (e.g. a runnable DCF code snippet or the exact command to invoke dcf_model.py with its arguments).

Actually provide the referenced scripts in a scripts/ directory, or remove the "Scripts Included" section if they are not bundled.

Cut generic padding (Best Practices, Updates and Maintenance, Limitations) that Claude already knows, and move detailed per-analysis methodology into separate reference files linked from the overview.

DimensionReasoningScore

Conciseness

Multiple padded sections restate concepts Claude already knows ("Best Practices Applied", "Valuation Principles", "Updates and Maintenance", "Limitations and Disclaimers"), making it noticeably verbose beyond a few unnecessary explanations.

2 / 5

Actionability

The body only describes capabilities ("Build complete DCF models", "Calculate terminal values") with no executable code or commands, and the only concrete artifacts named ("dcf_model.py", "sensitivity_analysis.py") do not exist in any scripts/ directory.

2 / 5

Workflow Clarity

There is no sequenced workflow or validation checkpoints for the multi-step modeling operations; content is organized by feature rather than as a process, giving only a faint implicit input-to-output order.

2 / 5

Progressive Disclosure

Section headers provide reasonable structure, but detailed per-method methodology and the script reference are inlined rather than split into reference files, and the only file references point to non-existent scripts.

3 / 5

Total

9

/

20

Passed

Description

66%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 is specific and uses natural finance-domain trigger terms, but it lacks an explicit "Use when..." clause, leaving the activation guidance only weakly implied. It is otherwise a clear, mostly distinctive capability statement.

Suggestions

Add an explicit trigger clause, e.g. "Use when building DCF valuations, running Monte Carlo or sensitivity analysis, or comparing investment scenarios."

Include common synonyms users might say (valuation, WACC, LBO, IRR) to broaden natural keyword coverage.

Trim the framing phrase "This skill provides an advanced financial modeling suite with" to lead directly with the concrete capabilities.

DimensionReasoningScore

Specificity

Names four concrete modeling techniques ("DCF analysis, sensitivity testing, Monte Carlo simulations, and scenario planning") rather than vague language, though they read more as capability categories than fully granular actions, leaving minor coverage gaps.

4 / 5

Completeness

Clearly states what the skill does, but "for investment decisions" only weakly implies when to use it and there is no explicit "Use when..." trigger clause, which caps completeness at 3.

3 / 5

Trigger Term Quality

Includes natural domain terms users would say ("financial modeling", "DCF analysis", "Monte Carlo simulations", "scenario planning"), but misses common synonyms and specifics like valuation, WACC, or LBO.

4 / 5

Distinctiveness Conflict Risk

Targets a fairly distinct niche (advanced financial modeling) with specific technique triggers, though "financial modeling" is broad enough to risk minor overlap with a generic spreadsheet or Excel skill.

4 / 5

Total

15

/

20

Passed

Validation

100%

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

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
anthropics/anthropic-cookbook
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.