Market Research Skills
Turn Claude into a disciplined research analyst, verify facts against primary sources, brief any topic, draft flagship reports. Standalone or chained; runs across LLM…
Install: /plugin marketplace add https://github.com/genli-ai/market-research-skills.git
Works with Claude Code · 63 GitHub stars
Install
/plugin marketplace add https://github.com/genli-ai/market-research-skills.gitInstall command taken from the project's README or registry entry. Always review code before running it.
README excerpt
Read full README on GitHub →Market Research Skills
中文版本见本文件下半部分 / Chinese version below
Turn Claude — or any LLM terminal — into a disciplined research analyst.
A collection of Claude Skills covering the full market / equity / industry research workflow: verify a fact against primary sources, spin up a topic briefing, or draft a flagship report — each step is its own skill. Every skill enforces the discipline real analysts live by: cite the original source, flag what can't be verified, never fabricate a number. Use any skill standalone, or chain them into an end-to-end pipeline. Runs in Claude Code / Desktop and ports to other LLM terminals (Codex / Gemini / Copilot).
Skills currently included
| Skill | Purpose | Typical triggers |
|---|---|---|
| verifying | Trace a statement back to whitelisted primary sources | "verify X" / "is this true" / "find the original source" |
| topic-brief | Generate a thematic observation briefing (HTML, paste-into-WeChat-ready) for any subject (region / industry / issue / institution) | "做一份 XX 观察" / "generate a briefing on Y" / "/topic-brief" |
| analyst-research | Three-mode end-to-end research workflow. User picks scope at trigger: light (4-5 page memo, 0 charts, ~15 min), medium (12-15p topic analysis, 6-10 charts, ~1 h), or heavy (flagship 30-40p / 15k+ word report, 25-35+ charts, ~2-3 h, full multi-stage workflow: framing → sourcing → analysis → drafting → review, multi-LLM optional). Reports default to English; the AI replies in the user's chat language. Battle-tested on the Saudi Vision 2030 deep-dive. | "research report" / "投研报告" / "深度分析" / "做研报" / "5-page memo" / "/analyst-research" |
| local-vault | Build & query a local Markdown knowledge base: convert PDF / Office / images / code into retrieval-friendly Markdown (local-first, cloud OCR fallback), then answer questions over the vault with retrieval discipline (coverage self-checks, lossy-content flags, MOC proposals) | "build/sync my local knowledge base" / "convert these files to markdown for AI" / "整理我的资料库" / "本地知识库" |
The list grows with each release. Full change history in CHANGELOG.md.
Installation
Option 1 — Claude Code one-click /plugin install (recommended for Claude Code users)
This repo ships with .claude-plugin/marketplace.json — it is itself a marketplace. In Claude Code:
/plugin marketplace add https://github.com/genli-ai/market-research-skills.git
/plugin install market-research-skills@market-research-skills
Future updates in one command:
/plugin update market-research-skills@market-research-skills
Option 2 — Clone the entire repo to ~/.claude/skills/ (works for Claude Desktop / other LLM terminals)
git clone https://github.com/genli-ai/market-research-skills.git
cp -r market-research-skills/skills/* ~/.claude/skills/
Subsequent updates:
cd market-research-skills && git pull
cp -r skills/* ~/.claude/skills/
Option 3 — Install only one skill
Use sparse-checkout to pull a single subdirectory:
git clone --filter=blob:none --no-checkout https://github.com/genli-ai/market-research-skills.git
cd market-research-skills
git sparse-checkout init --cone
git sparse-checkout set skills/verifying
git checkout
cp -r skills/verifying ~/.claude/skills/
Option 4 — Download a packaged .zip file
Similar plugs
Makes your AI agent think like the laziest senior dev in the room. The best code is the code you never wrote.
Turn any codebase, with its docs, SQL schemas, configs, and PDFs, into a queryable knowledge graph. A /graphify skill for Claude Code, Cursor, Codex, and Gemini CLI: local…
Why use many token when few token do trick. Viral skill + proxy for coding agents that cuts 65% of tokens by talking like a caveman.
Production-grade engineering skills for AI coding agents.
The 1st Collaborative AI Design Agent Workspace. Local-first and open source. Create prototypes, websites, apps, dashboards, presentations, images, and videos with your team…