CtrlK
BlogDocsLog inGet started
Tessl Logo

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

74

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

88%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 tightly written, highly actionable instruction skill: concrete formulas, explicit failure protocols, authorization gates, and a realistic worked example. Its main weaknesses are the triple repetition of the denominator rule, long compound sentences in the LTV and STAR steps, and a reference list dominated by cross-repo paths that are unverifiable from this bundle.

Suggestions

State the denominator-verification rule once (e.g., in the Done-when contract or the closing paragraph) and reference it from the other two spots instead of repeating it fully in all three.

Move the detailed LTV-basis requirements (step 6) and the R1-R6 evidence qualifications (step 9) into references/roi-templates.md blocks, keeping only the formula and the gate handoff inline.

Trim the Reference Materials list to the in-bundle template plus the few cross-repo documents actually needed for a run, or group the sibling-skill links under the existing Next Best Skill section to avoid duplication.

DimensionReasoningScore

Conciseness

The body is dense and free of beginner-concept padding, but the denominator-verification rule is stated three times (Done-when #4, step 2's rules, and the full closing paragraph after step 10) and steps 6 and 9 run as long compound sentences that could be trimmed.

4 / 5

Actionability

Exact formulas (Simple ROI, ROAS, the LTV formula), an explicit NEEDS_INPUT protocol, ready-to-use invocations, and a complete worked example give fully executable guidance for an instruction-only skill, with each step linked to a concrete template.

5 / 5

Workflow Clarity

Steps 1-10 are clearly sequenced with explicit validation gates (denominator checks, profitability-verification status, authorization required before saves) and NEEDS_INPUT feedback loops for missing or invalid inputs.

5 / 5

Progressive Disclosure

The body is a well-organized overview with a clearly signaled one-level-deep reference to references/roi-templates.md (verified present with matching anchors), but most listed references point outside the bundle to unverifiable paths and steps 6/9 carry inline detail that belongs in the templates file.

4 / 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.

An exemplary description: concrete capability list, quoted natural-language triggers in both English and Chinese, and an explicit use/don't-use boundary. It leaves no ambiguity about what the skill does or when it should be selected.

DimensionReasoningScore

Specificity

"produces direct ROI/ROAS, earned media value, attribution-modeled revenue, LTV-based ROI, and a stakeholder-ready summary" lists multiple concrete outputs with comprehensive coverage of the skill's capabilities.

5 / 5

Completeness

It explicitly answers both questions: an explicit "Use when the user asks to..." clause with concrete trigger phrases, a clear what-list of outputs, and an explicit negative boundary ("Not for building the full slide/written report — use report-generator").

5 / 5

Trigger Term Quality

Quoted natural user phrasings ("calculate influencer ROI", "prove campaign value", "what was our ROAS") plus ROI/ROAS synonyms and Chinese equivalents (达人营销ROI计算/投资回报测算) give comprehensive trigger coverage.

5 / 5

Distinctiveness Conflict Risk

The niche (influencer campaign ROI math) is clearly distinct, and the explicit "Not for... use report-generator" boundary actively reduces conflict risk with the adjacent reporting skill.

5 / 5

Total

20

/

20

Passed

Validation

81%

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

CriteriaDescriptionResult

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
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.