roi-calculator

Use when the user asks to "calculate influencer ROI", "prove campaign value", or "what was our ROAS"; produces direct ROI/ROAS, earned media value, attribution-modeled revenue, LTV-based ROI, and a stakeholder-ready summary. Not for building the full slide/written report — use report-generator. 达人营销ROI计算/投资回报测算

Quality

88%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Quality

Content

85%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 is a well-structured, validation-rich calculation workflow with concrete formulas and a worked example, supported by a properly organized one-level-deep reference bundle. The only lever is trimming some repetitive qualification language.

Suggestions

Consolidate the repeated NEEDS_INPUT / denominator-check conventions into one stated rule rather than restating them across multiple steps.

For steps that currently emphasize what to avoid (e.g., EMV and attribution), add a one-line positive execution template inline so Claude has the exact next action, not just the constraint.

Move the bilingual summary/description fragments out of the body into frontmatter-only fields to keep the working body lean.

Dimension	Reasoning	Score
Conciseness	Dense and procedural, assuming competence without explaining what ROI/EMV/attribution are, though extensive qualification phrasing and repeated NEEDS_INPUT conventions leave minor room to tighten.	4 / 5
Actionability	Provides concrete inline formulas (Simple ROI, ROAS, EMV, LTV-based ROI) and a worked numeric example with linked step templates, but a few steps emphasize what to avoid over exact execution detail.	4 / 5
Workflow Clarity	A clear 10-step sequence with explicit validation checkpoints (denominator > 0, NEEDS_INPUT returns, 'Done when' criteria, profitability-verification status) and feedback loops that re-gather on missing input.	5 / 5
Progressive Disclosure	Body serves as an overview with bulk templates one level deep in references/roi-templates.md via verified anchored step links, and other references are clearly signaled and single-level.	5 / 5
	Total	18 / 20 Passed

Description

92%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 concrete, trigger-rich, and clearly scoped to a niche with an explicit boundary against a sibling skill. Minor additional trigger synonyms could push trigger quality to a perfect score.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'produces direct ROI/ROAS, earned media value, attribution-modeled revenue, LTV-based ROI, and a stakeholder-ready summary' — giving comprehensive coverage of the skill's capabilities.	5 / 5
Completeness	Explicitly answers both what it produces and when to use it with concrete trigger phrases, and adds a boundary exclusion ('Not for building the full slide/written report — use report-generator').	5 / 5
Trigger Term Quality	Includes natural phrases a user would say ('calculate influencer ROI', 'prove campaign value', 'what was our ROAS') with ROI/ROAS synonyms, but a few common variations are absent.	4 / 5
Distinctiveness Conflict Risk	Niche-specific to influencer ROI with an explicit handoff boundary against report-generator, leaving minimal overlap risk with other skills.	5 / 5
	Total	19 / 20 Passed

Validation

81%

Warnings & errors only

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

Validation — 13 / 16 Passed

Validation for skill structure

Criteria	Description	Result
metadata_field	'metadata' should map string keys to string values	Warning
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning
relative_links	Relative link issues: 18 suspicious	Warning

	Total	13 / 16 Passed

Repository: aaron-he-zhu/aaron-marketing-skills
Path: influencer/report/roi-calculator/SKILL.md
Commit: 5cd4a80

Reviewed: 3 days ago

Table of Contents

Discovery Implementation Validation

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.