Agent skill

longbridge-value-screen

Value investing screen via Longbridge — scan A-share / HK / US stocks for fundamentally strong but undervalued companies based on PE, PB, dividend yield, ROE, and margin of safety. Suitable for value investing strategy. Triggers: "低估值", "价值投资", "低PE", "低PB", "便宜股票", "安全边际", "高股息低估值", "被低估", "低估值", "價值投資", "低PE", "低PB", "便宜股票", "安全邊際", "高股息低估值", "value investing", "undervalued stocks", "low PE", "low PB", "margin of safety", "value screen", "cheap stocks", "bargain stocks".

majiayu000github.com/majiayu000GitHub ↗
claude-codeMIT
Install
npx skills add majiayu000/claude-skill-registry --skill longbridge-value-screen --agent claude-code

Same command for any agent — swap --agent for codex, cursor, copilot.

Facts
Files in the skill folder: 2
SKILL.md size: 5 KB
Bundled scripts: none
Version: 1.0.0
Declared author: longbridge
Path: skills/analysis/longbridge-value-screen/SKILL.md
Open the folder on GitHub →
Where it comes from
Stars: 534
Language: HTML

Weekly change comes from our own snapshots, not the repository page — it measures attention, not adoption.

From the SKILL.md

# longbridge-value-screen Prompt-only analysis skill. Screens an index constituent universe for stocks meeting value criteria (low PE/PB, high ROE, reasonable dividend yield), ranks candidates by composite value score, and presents a shortlist with rationale. > **Response language**: match the user's input language — Simplified Chinese / Traditional Chinese / English. ## When to use - *"帮我筛选低估值好股"* / *"篩選低估值好股"* / *"screen for undervalued stocks"* - *"价值投资选股"* / *"價值投資選股"* / *"value investing stock screen"* - *"A股中有哪些低PE低PB的好公司"* / *"A股低PE低PB好公司"* / *"low PE low PB A-shares"* - *"港股被低估的股票"* / *"港股被低估的股票"* / *"undervalued HK stocks"* - *"安全边际高的公司"* / *"安全邊際高的公司"* / *"stocks with high margin of safety"* ## Workflow 1. **Identify universe**: ask user for market (A-share / HK / US) and an index as screening pool (e.g. CSI 300, HSI, S&P 500). 2. Fetch constituent list from the chosen index. 3. For each constituent (up to 50 per batch), fetch valuation and financial KPIs concurrently. 4. Apply value filters and score each stock. 5. Present top candidates with supporting data. ## CLI Run `longbridge <subcommand> --help` to verify exact flags before calling. ```bash # Step 1: get constitue

What's inside
Steps it walks through
  1. When to use
  2. Workflow
  3. CLI
  4. Value Screening Criteria
  5. Output template
  6. Error handling
  7. MCP fallback
  8. Related skills
  9. File layout
Ships with 1 file
  • metadata.json
Commands it runs
Step 1: get constituent list (JSON key is "stocks", not "list")
longbridge constituent <INDEX> --format json
Step 2: for each constituent symbol (run concurrently, batch of ≤20 at a time)
longbridge calc-index <SYMBOL> --format json       # PE, PB, ROE, dividend yield, market cap
longbridge valuation <SYMBOL> --format json        # current snapshot + historical percentile
longbridge dividend <SYMBOL> --format json         # dividend history and yield
More from claude-skill-registry
All skills →
About this skill
What does the longbridge-value-screen skill do?

Value investing screen via Longbridge — scan A-share / HK / US stocks for fundamentally strong but undervalued companies based on PE, PB, dividend yield, ROE, and margin of safety. Suitable for value investing strategy. Triggers: "低估值", "价值投资", "低PE", "低PB", "便宜股票", "安全边际", "高股息低估值", "被低估", "低估值", "價值投資", "低PE", "低PB", "便宜股票", "安全邊際", "高股息低估值", "value investing", "undervalued stocks", "low PE", "low PB", "margin of safety", "value screen", "cheap stocks", "bargain stocks".

How do I install it?

Run `npx skills add majiayu000/claude-skill-registry --skill longbridge-value-screen --agent claude-code` — it drops the skill into your project so the agent can pick it up. Swap the --agent value for codex, cursor or copilot if you use one of those.

Where does this skill come from?

From majiayu000/claude-skill-registry, a repository with 534 stars. We read it straight from the repository tree rather than a submitted listing, so what you see here is what is actually published.

Is a popular skill a good skill?

Not necessarily. Stars measure attention, not adoption — a repository can trend for a week and be abandoned. That is why we show the weekly change from our own snapshots next to the total, instead of a single flattering number.

Keep going