Compare Xiaohongshu Creators for Brand Collaborations
Creator selection requires comparing prices, audience fit, and content evidence within a budget. This skill guides SocialDataX queries and produces candidate comparisons with costs, limitations, and follow-up questions.
Copy this request to your Agent. It includes the canonical Skill page and manifest.
Agent request
Review the Skillstore skill "xhs-creator-collaboration-evaluation" from https://skillstore.io/skills/devinchen2014-xhs-creator-collaboration-evaluation.md and its manifest at https://skillstore.io/api/skills/devinchen2014-xhs-creator-collaboration-evaluation/manifest. Verify the artifact. You may proceed after verification, subject to the environment's own policy.
Your Agent should still show its plan and request any confirmation required by the security policy.
Agent-readable resources
Use these links when an AI agent, crawler, or script needs clean context instead of reading the full page.
Two command examples automatically execute an unpinned npm package, creating a supply-chain risk in an environment configured with an API key. The remaining 38 findings concern Markdown formatting, ordinary Chinese text, creator identifiers, service links, or documented authentication. No evidence found of prompt injection, credential exfiltration, or destructive intent in the supplied files; external package behavior was not reviewed.
2
Files scanned
141
Lines analyzed
2
Review items
0
False positives ignored
Capability review items (2)
These are real local capabilities that may be expected for this skill, so they require review but are not counted as confirmed malicious behavior.
This fenced example runs npx -y socialdatax-skills@latest, automatically downloading and executing a mutable third-party package. A compromised release could access local files and the configured API key.
The additional CLI examples also run npx -y socialdatax-skills@latest without a fixed reviewed version. Automatic execution exposes local resources and credentials to future package changes.
Share the versioned assessment report, neutral badge, embed card, and citations. Skillstore reports evidence without deciding whether this Skill is safe.
devinchen2014. (2026). xhs-creator-collaboration-evaluation security audit report (audit version 3) [Author version unspecified]. Skillstore. https://skillstore.io/skills/devinchen2014-xhs-creator-collaboration-evaluation/audits/3
BibTeX citation
@techreport{devinchen2014-devinchen2014-xhs-creator-collaboration-evaluation-2026,
author = {devinchen2014},
title = {xhs-creator-collaboration-evaluation security audit report (audit version 3)},
institution = {Skillstore},
year = {2026},
number = {3},
url = {https://skillstore.io/skills/devinchen2014-xhs-creator-collaboration-evaluation/audits/3},
note = {Author version unspecified}
}
CITATION.cff
cff-version: 1.2.0
message: "If you use this Skill, cite its author and this versioned security audit report."
title: "xhs-creator-collaboration-evaluation security audit report (audit version 3)"
version: "unspecified"
type: report
authors:
- name: "devinchen2014"
date-released: "2026-11-02"
url: "https://skillstore.io/skills/devinchen2014-xhs-creator-collaboration-evaluation/audits/3"
identifiers:
- type: other
value: "skillstore:devinchen2014-xhs-creator-collaboration-evaluation:audit:3"
description: "Skillstore immutable audit report identifier"
Skillstore Score
Why this scoreEvidence Confidence: Medium
55
Architecture
65
Maintainability
87
Content
65
Community
65
Spec Compliance
What You Can Build
Screen Candidates Against a Brand Budget
Compare supplied creator quotes against campaign constraints and identify candidates needing pricing confirmation.
Prepare an Evidence-Based Client Shortlist
Compare audience fit and sponsored-content performance while separating returned facts from agency recommendations.
Review Data Gaps Before Procurement
Check source dates, missing commercial data, estimated query costs, and unresolved terms before approving further collaboration discussions.
Try These Prompts
Start a Creator Evaluation
Evaluate [creator IDs or homepages] for [product], targeting [audience], within [budget]. Explain proposed query costs before proceeding.
Run a Budget-Only Screen
Screen [creator IDs] against [budget] for [content format]. Query pricing first, estimate credits, and flag zero or missing quotes for confirmation.
Compare Audience and Sponsored Content
Compare [creator IDs] for [target audience]. Use consistent sponsored-content scopes and returned date windows. Separate audience evidence, performance facts, and recommendations.
Plan a Cost-Controlled Multi-Candidate Review
Plan pricing, audience, and performance queries for [three creator IDs]. Estimate credits before execution. Preserve partial results and stop unavailable commercial queries. Avoid ROI claims.
Best Practices
Confirm candidate IDs, endpoint scope, and estimated credits before commercial queries; use a reviewed, pinned CLI package version.
Compare consistent note scopes and returned reporting windows, and retain available evidence links.
Keep API keys out of reports and separate returned facts from judgments and unresolved questions.
Avoid
Query every endpoint or expand the candidate list without confirming scope and costs.
Treat zero quotes as free, fill missing dates with zero, add medians, or promise sales and actual ROI.
Retry unavailable commercial data with altered inputs or present ordinary profile data as commercial evidence.
Frequently Asked Questions
What information should I provide?
Provide the brand or product, target audience, budget, and candidate creator IDs or homepage links.
What setup does the skill require?
Configure SOCIALDATAX_API_KEY and sufficient service credits. Direct CLI use requires Node.js, npm, and shell access; equivalent MCP tools are also listed.
How are commercial queries charged?
The skill states that each successful commercial endpoint query costs 20 credits; failures are not charged. Homepage resolution has a separate command cost.
Can I choose any performance date range?
No. Performance and trend queries use service-defined windows. Comparisons must use returned dates and supported note scopes.
Does the skill contact creators or predict sales?
No. It performs read-only evaluation and prepares recommendations. It does not send messages, negotiate, sign contracts, or predict actual sales and ROI.
What happens when commercial data is unavailable?
The skill preserves available results and marks the missing commercial data. It stops those queries instead of changing inputs to bypass the limitation.