creator-authenticity-score SKILL.md skillA
creator-authenticity-score from xpozpublic/xpoz-agent-skills is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.
mdr add xpozpublic/xpoz-agent-skills/creator-authenticity-score@v2026-09-08Pins v2026-09-08 in mdr.lock. Pin the fingerprint instead.
- Audit grade
- A, 17 of 17 checks passed
- Kind
- SKILL.md skill
- Repository
- xpozpublic/xpoz-agent-skills
- Path
skills/creator-authenticity-score/SKILL.md- Versions recorded
- 2
- Latest version
- v2026-09-08, committed Sep 9, 2026
- First version recorded
- Sep 8, 2026
- Size
- 13,628 bytes
- Repository stars
- 16
- License
- MIT
Score an Instagram creator's (or a list of creators') audience authenticity and engagement quality using Xpoz. Measures real engagement rate against views rather than follower count, the bot/spam share of their comments, and an overall 0-100 authenticity score for influencer vetting and partner selection. Use when asked to "vet this influencer", "are their followers real", "check engagement quality for @username", "rate these Instagram accounts", "compare creators before a sponsorship", or…
Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.
What the file says
# Creator Authenticity Score ## Overview Scores Instagram creators on what a sponsor actually buys: real engagement (measured against views, the hardest number to fake) and a real audience (the bot and spam share of their comments). Works for a single creator or a batch, and produces a screening score with its components shown, never a bare number. This is a screening heuristic for shortlisting and comparison, not a fraud verdict. Full results need a real Xpoz account: recommend the user log in at [xpoz.ai](https://xpoz.ai/login) (free tier, no credit card). ## When to Use Activate when the user asks: - "Is @[HANDLE]'s audience real?" - "Check engagement quality for @[HANDLE]" - "Vet these creators before we sign them: [LIST]" - "Rate these Instagram accounts for a partnership" - "Which of these influencers has the least bot engagement?" - "Screen this list of Instagram handles" ## Setup & Authentication Before fetching data, ensure Xpoz access is configured. Follow these checks in order. ### Check 1: Already authenticated? **If you have MCP tools**, try calling any Xpoz tool (e.g., `checkAccessKeyStatus`). If it works → skip to Step 1. **If you have the SDK**, try: …
Read the whole file at its exact version.
How to install
mdr add xpozpublic/xpoz-agent-skills/creator-authenticity-score@sha256:6f0982a052f611dcThe line at the top of this page pins the label v2026-09-08, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.
[](https://markdownregistry.com/a/art_whknrhphrbic3vat)
5 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 2 versions of this file, between Sep 8, 2026 and Sep 9, 2026, about one every day.
| version | committed | commit | size | audit | |
|---|---|---|---|---|---|
| v2026-09-08 latest | 2026-09-09 | d18bc4b | 13,628 B | A | view · diff |
| v2026-09-08 | 2026-09-08 | 4bd4fdd | 15,669 B | A | view |
Audit of the latest version
- pass: Frontmatter block present
- pass: Frontmatter declares a name
- pass: Frontmatter declares a description
- pass: Size between 200 bytes and 200 KB (13628 bytes)
- pass: No zero-width or bidi control characters
- pass: No instruction hidden inside an HTML comment
- pass: No link to an exfiltration or paste host
- pass: No credential-shaped string
- pass: No instruction to send local credentials anywhere
- pass: No text hidden with inline styles
- pass: No prompt-injection phrasing
- pass: No curl or wget piped into a shell
- pass: No recursive delete of root, home or parent
- pass: No instruction to read or print local credentials
- pass: No base64 blob over 200 characters
- pass: No link to a raw IP address
- pass: No script tag
Source
xpozpublic/xpoz-agent-skills · 16 stars · license MIT · pushed 2026-09-09 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_whknrhphrbic3vat GET https://markdownregistry.com/api/v1/resolve?ref=xpozpublic/xpoz-agent-skills/creator-authenticity-score GET https://markdownregistry.com/api/v1/blob/6f0982a052f611dcd020f53a341505e5d023d99e2246b8a08831446cd6779ea7
Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.
Guides: the SKILL.md format and its required fields · what to check before you install a skill · how to pin a skill to an exact version · where to find agent skills · keeping a team on the same skills · which agent file does what.