Creator Content Scorecard

Evaluate creator content for ecommerce or affiliate marketing by scoring key elements and providing clear, prioritized feedback to improve conversion and eng...

Security Scan

Instruction-only skill whose declared purpose (scoring creator content) matches its instructions and resource requests; it asks for no credentials, installs, or system access.

Purpose & Capability

Name/description ask for content evaluation and the SKILL.md contains only guidance for scoring content. There are no unrelated requirements (no cloud creds, binaries, or config paths) that would be inconsistent with the stated purpose.

Instruction Scope

Runtime instructions are confined to: restating the content goal, scoring specified dimensions, diagnosing gaps, and recommending fixes. The instructions do not direct the agent to read system files, environment variables, or contact external endpoints. They rely on user-supplied content and context only.

Install Mechanism

No install spec and no code files — lowest-risk configuration. Nothing will be downloaded or written to disk by the skill itself.

Credentials

The skill requests no environment variables, credentials, or config paths. Its inputs are content, product details, and audience/goal metadata — all appropriate for a content-review tool.

Persistence & Privilege

always is false and the skill does not request persistent system presence or to modify other skills. Model invocation is enabled (the default) which allows autonomous use, but that is expected for an assistant skill and is not combined with broad privileges here.

Assessment

This is an instruction-only scorecard for evaluating creator content and appears internally consistent. Before installing, consider: (1) avoid submitting sensitive or private PII/product secrets into the skill inputs (it expects content and product/offer details); (2) if you do not want the skill to be invoked autonomously, disable model invocation for this skill in your agent settings; (3) if a future version adds an install step, external endpoints, or required credentials, re-evaluate — those would change the risk profile. I am highly confident in this assessment given there are no code files, no install steps, and no requested secrets.

Score a creator content draft, published post, or content concept so operators can judge quality, conversion fitness, and what to improve before the next iteration.

Use this skill when a user wants a structured evaluation of creator-led content for ecommerce, affiliate, or TikTok Shop workflows. It is useful for turning subjective reactions like “this feels weak” into a practical scorecard with diagnosis and next steps.

Solves

Content reviews often fail because feedback stays vague:

• “The hook is weak” but nobody explains why
• “It feels off-brand” without clear criteria
• “It may not convert” without identifying the missing proof, offer, or CTA
• different reviewers focus on different things, so quality is inconsistent

Goal: Turn creator content into a score-based review with clear reasons, risks, and highest-impact fixes.

Use when

• Reviewing a creator script, draft, raw clip, caption, or published post
• Comparing multiple content options before approval
• Auditing why content feels weak even if it looks polished
• Giving creators actionable feedback instead of taste-based comments
• Building a repeatable QC process for creator or affiliate content

Do not use when

• The user needs full attribution analysis or media-buying performance modeling
• There is no real content artifact or summary to evaluate
• The task is legal/compliance review only

Inputs

• Content asset, transcript, script, caption, or summary
• Product and offer details
• Target audience
• Channel and format
• Goal of the content (click, sale, add to cart, lead, engagement)
• Key proof points or claims
• CTA expectation
• Known constraints (brand, compliance, creator style)

Workflow

1. Restate what the content is trying to do.
2. Score the content across the most important dimensions.
3. Explain what is helping and hurting performance.
4. Identify the 3 biggest gaps limiting conversion or retention.
5. Recommend concrete revisions in priority order.
6. End with a go / revise / reject recommendation.

Scoring dimensions

Use a 1-5 score for each:

• Hook strength
• Audience relevance
• Problem-solution clarity
• Product demonstration / specificity
• Proof / credibility
• Offer clarity
• CTA strength
• Native creator feel
• Conversion readiness

Output

Return:

1. Content summary
2. Score table or bullet score list
3. What is working
4. Biggest gaps
5. Priority fixes
6. Final recommendation: go / revise / reject

Quality bar

• Specific to creator commerce and conversion logic
• Distinguish engagement strength from sales strength
• Prioritize feedback by likely business impact
• Avoid fake precision and generic creative-writing notes
• Make the feedback usable by operators and creators immediately

Resource

See references/output-template.md.