How do I install the Geo Discover skill?

Run npx skillmds@latest add yaojingang/geo-discover in your terminal (requires Node.js), paste this page's agent-chat prompt into Claude, Cursor, or any MCP-connected agent, or download the SKILL.md file and copy it into your agent's skills directory.

Is Geo Discover safe to use?

This skill has not completed SkillMD's automated safety review yet. SkillMD never runs a skill's scripts for you; review the SKILL.md before installing.

Which AI agents work with Geo Discover?

This skill is tagged as working with Claude Code, Claude.ai, OpenAI Codex. SKILL.md is an open format, so most agents that read a skills directory can load it too.

Is Geo Discover free to use?

Yes. Installing skills from SkillMD is free, and the skill stays under its author's original license.

Who published Geo Discover?

yaojingang (@yaojingang) published this skill. Their other Agent Skills are listed on their SkillMD profile.

Geo Discover by yaojingang — Agent Skill

Name: Geo Discover
Author: yaojingang

Geo Discover

Discover evidence-aware GEO questions, query rewrites, intent clusters, and prioritized content opportunities from a structured brief. Use for AI search intent mining, question or keyword expansion, query research, FAQ discovery, 拓词, and GEO topic discovery in Chinese or English.

yaojingang Updated Sep 17, 2026

File contents

GEO Discover

Workflow

Read references/discovery-method.md; read references/discovery-method-v2.md when requesting a non-legacy execution mode.
Prepare a protocol 1.0.0 file-backed GEO brief.
Run python3 scripts/run_discover.py --input <brief.json> --output <runs-root> --execution-mode <legacy|deterministic|research|provider>. Legacy remains the compatibility default.
Inspect quality-report.json and run-lineage.json; surface all warnings and failed checks.
Deliver the Artifact Bus directory as the output contract.

Output contract

Treat the output argument as the runs root. Produce <runs-root>/<run-id>/input/geo-brief.json, run-manifest.json, run-lineage.json, evidence-ledger.json, query-map.json, opportunity-map.json, and quality-report.json. Return the actual <runs-root>/<run-id> directory.

Boundaries

Legacy and deterministic modes are offline and file-backed. Research mode consumes only approved evidence already present in the brief. Provider mode needs an explicit runtime adapter; the packaged CLI has no adapter and degrades to deterministic generation with a recorded failure. Discovery records missing evidence and never invents platform responses, volume, ranking, conversion, competitor, or customer data. Diagnosis and content generation remain separate Registry stages.

Frequently asked questions