AI Summary<!-- Bilingual skill: this SKILL.md is the English primary; the Chinese mirror is SKILL.zh.md. Each references/.md has a Chinese mirror references/.zh.md (same content, two languages). The .md files are authoritative for the agent; the .zh.md files are for human readers. -->
Install
Copy this and paste it into Claude Code, Cursor, or any AI assistant:
I want to install the "analyst-research" skill in my project. Please run this command in my terminal: # Install skill into your project mkdir -p .claude/skills/analyst-research && curl --retry 3 --retry-delay 2 --retry-all-errors -o .claude/skills/analyst-research/SKILL.md "https://raw.githubusercontent.com/genli-ai/market-research-skills/main/skills/analyst-research/SKILL.md" Then restart Claude Code (or reload the window in Cursor) so the skill is picked up.
Description
End-to-end research workflow skill for investment analysts and policy researchers. Three scope modes the user picks at trigger time — light (4-5 page decision memo, ~15 min, 0 charts), medium (12-15 page topic brief, ~1 h, 6-10 charts), heavy (flagship report 30-40 pages / 15k+ words, ~2-3 h, 25-35+ charts, multi-stage workflow, multi-LLM, PDF + Word + WeChat + HTML derivations). Reports default to English; the AI replies in the user's chat language. Battle-tested on real macro/policy/equity reports (e.g. Saudi Vision 2030 deep-dive). Triggers when user types /analyst-research, /flagship-research, or describes needs like "research report", "topic analysis", "investment research", "做研报", "投研报告", "主题分析", "深度分析", "policy assessment", "industry deep-dive". Not for: pure news commentary (use topic-brief), slide decks (use deckster-slide-generator), one-shot Q&A.
analyst-research · investment research workflow skill
A field-validated AI-assisted research workflow for investment analysts and policy researchers, packaged as a reusable Claude skill. Built on the methodology that produced the Saudi Vision 2030 deep-dive (35 figures, 15k+ words). Three scope modes; user picks at trigger time. > License: MIT. Copyright © 2026 Ligen <ligen.thu@gmail.com>. See LICENSE.
Step 0 — pick a mode (REQUIRED before loading references)
When this skill is triggered, before loading any reference file, ask the user to pick a scope. Present these three options verbatim: ` This skill has three scope modes. Pick one based on your project size: light 4-5 page decision memo, 0 charts, ~15 min budget Single LLM session. Pure markdown footnote citations. Use for: exec brief, internal memo, quick decision support. medium 12-15 page topic analysis, 6-10 charts, ~1 h budget Single LLM. PDF + Word derivations. Sign-off checkpoint after draft. Use for: topic deep-dive, board memo with data, same-day analysis. heavy Flagship report 30-40 pages / 15k+ words, 25-35+ charts, ~2-3 h budget Single or multi-LLM. PDF + Word + WeChat md + HTML publication. Runs the full 11-step staged workflow (framing → sourcing → analysis → drafting → review), with 3 sign-off checkpoints. Use for: industry deep-dive, macro thesis, policy assessment, flagship investor publication. Which mode fits your project? (reply with light, medium, or heavy) ` If the user's trigger message already contains explicit scope hints (page count, chart count, time budget), infer the mode and ask one-line confirmation instead of presenting the full menu: > "Sounds like ~10 pages with a few charts — medium mode. Going with that?" After the mode is confirmed, ask one short language question: "Report language — English (default), or another language?" (see Language policy below). Then load the reference files for that mode.
Loading order per mode
First always read references/workflow.md (≈40 lines, mode router). It points you to the mode-specific workflow file. (Each reference also has a .zh.md Chinese mirror; the agent reads the English .md.)
light mode
• Required references/workflow.md — overview + mode router • Required references/workflow_light.md — 6-step skeleton, soft stops only, BLUF executive summary, grep self-check • Required references/_quarto-light.yml — Quarto template optimized for a 4-5 page memo (no TOC, no number sections, footnote citations, 11pt body) • No charts. No bibliography. No HTML/WeChat derivation. Skip report_style_spec.md and chart_template.py. Then proceed to workflow_light.md §1 hypothesis lock to start the 6-step flow.
Discussion
Health Signals
My Fox Den
Community Rating
Sign in to rate this booster