CtrlK
BlogDocsLog inGet started
Tessl Logo

unit-economics

Analyze unit economics for PE targets — ARR cohorts, LTV/CAC, net retention, payback periods, revenue quality, and margin waterfall. Essential for software/SaaS, recurring revenue, and subscription businesses. Use when evaluating revenue quality, building a cohort analysis, or assessing customer economics. Triggers on "unit economics", "cohort analysis", "ARR analysis", "LTV CAC", "net retention", "revenue quality", or "customer economics".

76

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

87%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

A concise, highly actionable analysis skill with concrete formulas, benchmark thresholds, and a clean five-step workflow. Its only gap is the absence of explicit validation/checkpoint feedback loops in the workflow, which caps workflow clarity at 2.

Suggestions

Add explicit validation checkpoints to the workflow — e.g., after building the cohort matrix, a step to reconcile ending ARR back to the ARR bridge and flag discrepancies, creating a validate-fix-retry loop.

Include a brief 'sanity-check' checklist in Step 4 (e.g., confirm recurring vs. recognized revenue split is consistent across all metrics) so the Revenue Quality Score has an explicit verification step before scoring.

Add one or two concrete examples of red-flag interpretation (e.g., what NDR>120% alongside >15% logo churn implies) to make the 'Important Notes' as actionable as the rest of the skill.

DimensionReasoningScore

Conciseness

Lean and efficient throughout — defines actions, formulas, and thresholds without explaining concepts Claude already knows (e.g., never defines what ARR or churn is). Every token earns its place, matching the score-3 'lean and efficient' anchor rather than the padded score-2 example.

3 / 3

Actionability

Concrete executable guidance: specific formulas ('LTV = (ARPU × Gross Margin) / Churn Rate'), an ARR bridge structure, a cohort matrix template, and explicit benchmark thresholds ('NDR >120% good, <100% concerning'). Matches the score-3 'concrete, specific examples' anchor; not pseudocode-like as in the score-2 example.

3 / 3

Workflow Clarity

A clear five-step sequence (Identify model → Core metrics → Benchmarking → Revenue quality score → Output) with a synthesis scoring table, but no explicit validation checkpoints or error-feedback loops, which the score-3 anchor requires. It exceeds the score-1 'steps unclear' case but lacks the feedback loops needed for a 3.

2 / 3

Progressive Disclosure

Single self-contained file with no bundle files and well-organized sections (Workflow → Steps → Important Notes); no nested or deep references. Under the guideline for skills with no need for external references, the clean organization earns a 3 rather than the disorganized score-2 case.

3 / 3

Total

11

/

12

Passed

Description

100%

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 well-crafted description that states concrete capabilities, provides explicit 'Use when' trigger guidance, and lists natural trigger terms users would actually say. It is distinct from other skills and free of vague fluff.

DimensionReasoningScore

Specificity

Lists multiple concrete actions — 'ARR cohorts, LTV/CAC, net retention, payback periods, revenue quality, and margin waterfall' — matching the 'lists multiple specific concrete actions' anchor; not vague like the score-2 example which names only a domain and one action.

3 / 3

Completeness

Explicitly answers both what ('Analyze unit economics for PE targets — ARR cohorts, LTV/CAC...') and when ('Use when evaluating revenue quality, building a cohort analysis, or assessing customer economics'), matching the score-3 anchor; not merely implied as in the score-2 'Extract text and tables...' example.

3 / 3

Trigger Term Quality

Good coverage of natural terms users would say ('unit economics', 'cohort analysis', 'ARR analysis', 'LTV CAC', 'net retention', 'revenue quality', 'customer economics'); matches the score-3 anchor and exceeds the score-2 single-keyword example.

3 / 3

Distinctiveness Conflict Risk

Clear PE unit-economics niche with distinct triggers tied to specific metrics; unlikely to conflict with other skills, matching the score-3 'clear niche with distinct triggers' anchor rather than the generic score-2 example.

3 / 3

Total

12

/

12

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.

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
anthropics/financial-services
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.