cmo-ai-prompt-research SKILL.md skillA
cmo-ai-prompt-research from ai-marketing-os-ltd/cmo-so-skills is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.
mdr add ai-marketing-os-ltd/cmo-so-skills/cmo-ai-prompt-research@v0.11.7Pins v0.11.7 in mdr.lock. Pin the fingerprint instead.
- Audit grade
- A, 17 of 17 checks passed
- Kind
- SKILL.md skill
- Repository
- ai-marketing-os-ltd/cmo-so-skills
- Path
plugins/cmo-so-ai-search/skills/cmo-ai-prompt-research/SKILL.md- Versions recorded
- 5
- Latest version
- v0.11.7, committed Oct 19, 2026
- First version recorded
- Oct 17, 2026
- Size
- 9,644 bytes
- Repository stars
- 4
- License
- MIT
Find the questions people ask AI assistants about the market, how they are answered, and which sites get cited. Use when the user says things like "What do people ask ChatGPT about our market?"; "Give me prompts we should track in AI search"; "Which questions should we watch for AI visibility?"; "Who gets cited when people ask AI about [category]?"; "Keyword research, but for AI assistants"; "Turn our head terms into questions people ask AI". Works with the CMO.so MCP server (cmo-so plugin).
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
# AI prompt research Keyword research finds what people type into Google; this finds what they ask an AI assistant. Maggie turns a few head terms into the questions buyers put to AI, groups them by intent, spot-checks how they are answered and which sites get cited, and hands back a short list of prompts worth watching. Research only: tracking is a separate choice the user confirms. ## When to use - Before choosing which prompts or keywords to monitor for AI visibility. - "What are people asking AI about [category]?" - Planning content for AI answers and wanting real question phrasing. - Finding where the brand is missing before an audit. Not for: a full diagnosis with recommendations (`cmo-ai-visibility-audit`), working through the cited sources (`cmo-ai-citation-gaps`), Google keyword demand (`cmo-keyword-research`) or reading the current score (`cmo-ai-visibility`). ## Before you start - Collect brand, site, offer, audience and competitors, one question at a time (reuse what `cmo-brand-profile` already holds when that skill has run in the session). With CMO.so, call `workspaces_list` if you do not know the website domain. …
Read the whole file at its exact version.
How to install
mdr add ai-marketing-os-ltd/cmo-so-skills/cmo-ai-prompt-research@sha256:c8cd4df40efcb606The line at the top of this page pins the label v0.11.7, 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_hq4eayigmsmthosy)
4 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 5 versions of this file, between Oct 17, 2026 and Oct 19, 2026, more than one a day.
| version | committed | commit | size | audit | |
|---|---|---|---|---|---|
| v0.11.7 latest | 2026-10-19 | f73e99e | 9,644 B | A | view · diff |
| v0.11.6 | 2026-10-19 | 4d1b95e | 9,644 B | A | view · diff |
| v0.11.5 | 2026-10-17 | 85699a9 | 9,644 B | A | view · diff |
| v0.11.4 | 2026-10-17 | f2d0d16 | 9,644 B | A | view · diff |
| v0.11.3 | 2026-10-17 | 61c2299 | 9,644 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 (9644 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
ai-marketing-os-ltd/cmo-so-skills · 4 stars · license MIT · pushed 2026-11-06 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_hq4eayigmsmthosy GET https://markdownregistry.com/api/v1/resolve?ref=ai-marketing-os-ltd/cmo-so-skills/cmo-ai-prompt-research GET https://markdownregistry.com/api/v1/blob/c8cd4df40efcb6068a10c589c76c68a84be0af6fab2ba3aa2c79d09c1374412a
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.