geo-audit SKILL.md skillA
geo-audit from hahaknight/claude-skills-pro is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.
mdr add hahaknight/claude-skills-pro/geo-audit@git:20260915.f7660cfPins git:20260915.f7660cf in mdr.lock. Pin the fingerprint instead.
- Audit grade
- A, 17 of 17 checks passed
- Kind
- SKILL.md skill
- Repository
- hahaknight/claude-skills-pro
- Path
free-skills/geo-audit/SKILL.md- Versions recorded
- 1
- Latest version
- git:20260915.f7660cf, committed Sep 15, 2026
- Size
- 4,762 bytes
- Repository stars
- 6
- License
- MIT
Five-dimension diagnostic for how AI search engines talk about a brand. Use when you have a question set plus raw AI answers (from Doubao, Qwen, Yuanbao, DeepSeek, or any generative engine) and need a reproducible GEO report — visibility, factual accuracy, decision completeness, source quality, and compliance risk — with baseline-vs-retest comparison.
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
# GEO Audit — Five-Dimension Answer Diagnostic You are auditing how AI search engines answer user questions about a brand or product line. Your output feeds content and compliance decisions, so every verdict must cite evidence from the actual answers. If a check would produce the same text regardless of input, the check is broken — say so. ## Core rule Every dimension verdict = rule output + quoted evidence + confidence. Distinguish **batch observations** from **platform laws**: one run on one date with one model version is an observation, never a conclusion about the engine. ## Required inputs 1. **Question set**: question text, cluster/persona/stage labels if available 2. **Raw answers**: text + platform + model/version + query date (no answer without these three metadata fields; ask for them) 3. **Brand dictionary**: brand names, product/SKU names and aliases 4. **Official domain whitelist**: domains that count as official sources 5. **Risk word list** (if the brand is in a regulated category) Missing dictionaries? Build them with the user before scoring — do not invent brand terms or whitelist domains. ## The five dimensions (operational rubric) …
Read the whole file at its exact version.
How to install
mdr add hahaknight/claude-skills-pro/geo-audit@sha256:2cdd1786f7c7462dThe line at the top of this page pins the label git:20260915.f7660cf, 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_oloxs33fpin6n3mo)
5 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 1 version of this file, committed on Sep 15, 2026.
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 (4762 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
hahaknight/claude-skills-pro · 6 stars · license MIT · pushed 2026-09-17 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_oloxs33fpin6n3mo GET https://markdownregistry.com/api/v1/resolve?ref=hahaknight/claude-skills-pro/geo-audit GET https://markdownregistry.com/api/v1/blob/2cdd1786f7c7462d4ccd8ccfad578cc084abf08e94648e0c3e386451d54610c7
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.
More from hahaknight/claude-skills-pro
Every file in hahaknight/claude-skills-pro