CtrlK
BlogDocsLog inGet started
Tessl Logo

ads-math

Calculate and model paid-media CPA, CPL, CPC, CPM, ROAS, MER, break-even targets, contribution margin, LTV:CAC, impression-share opportunity, budgets, forecasts, and experiment economics. Use for PPC math, ad calculator, break-even analysis, ROAS calculator, CPA calculator, budget forecast, LTV CAC, or MER.

75

Quality

93%

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

SKILL.md
Quality
Evals
Security

Quality

Content

86%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 tight, well-sequenced methodology checklist for instruction-only financial modeling that respects token budget and includes validation, though it omits reference formulas and an explicit error-recovery loop. Structure is appropriate for a short single-purpose skill with no bundle files.

Suggestions

In step 2, include the canonical formulas for the core metrics (e.g., CPA = spend ÷ conversions, ROAS = attributed revenue ÷ spend, MER = total revenue ÷ total ad spend) so the guidance is copy-paste ready.

Add a brief validate→fix→retry feedback loop after step 3 (e.g., 'If validation fails, correct the flagged input and re-validate before calculating') to reach the top workflow-clarity anchor.

Optionally show the machine-readable output shape (a small JSON skeleton of inputs/formulas/outputs/sensitivities) to make step 6's deliverable concrete.

DimensionReasoningScore

Conciseness

The ~15-line body is lean and assumes Claude's competence — no padding, no explaining what CPA/ROAS are — so every token earns its place per the top anchor.

5 / 5

Actionability

Concrete specifics are present (inputs to collect in step 1, validation checks in step 3, base/downside/upside cases, machine-readable outputs), but step 2 says 'Show the formula' without providing reference formulas, a minor gap below the copy-paste-ready bar of 5.

4 / 5

Workflow Clarity

A clear six-step sequence with an explicit validation step (step 3) and a guardrail line; it stops short of 5 because there is no validate→fix→retry feedback loop for when validation fails.

4 / 5

Progressive Disclosure

Under 50 lines with no external references needed and a well-organized heading plus numbered list, matching the simple-skill exception that allows a 5 on structure alone.

5 / 5

Total

18

/

20

Passed

Description

100%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 dense, well-constructed description that pairs a comprehensive list of concrete capabilities with an explicit, synonym-rich 'Use for' trigger clause in correct third-person voice. It cleanly satisfies the what/when requirement with low conflict risk.

DimensionReasoningScore

Specificity

Enumerates many concrete actions/metrics — 'Calculate and model paid-media CPA, CPL, CPC, CPM, ROAS, MER, break-even targets, contribution margin, LTV:CAC, impression-share opportunity, budgets, forecasts, and experiment economics' — giving comprehensive coverage rather than the minor gaps of a 4.

5 / 5

Completeness

Explicitly states what ('Calculate and model...') and when ('Use for...') with concrete trigger phrases, satisfying the top anchor; not a 4 because both halves are concrete and explicit.

5 / 5

Trigger Term Quality

'Use for PPC math, ad calculator, break-even analysis, ROAS calculator, CPA calculator, budget forecast, LTV CAC, or MER' covers natural user phrasings plus synonyms and acronyms, matching the comprehensive anchor.

5 / 5

Distinctiveness Conflict Risk

The paid-media financial-modeling niche with distinct triggers (CPA, CPL, ROAS, MER, LTV:CAC) has minimal overlap risk, fitting the clear-niche anchor.

5 / 5

Total

20

/

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
AgriciDaniel/claude-ads
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.