Longbridge Earnings
Earnings before and after the print: a preview framework for the upcoming release, then a fast summary card or a full Markdown research report.
- What
- Earnings before and after the print: a preview framework for the upcoming release, then a fast summary card or a full Markdown research report.
- Cost
- Free
- Needs
- Use "Longbridge Earnings" with your Muse.
- Install
- Copy the installer prompt below into your Muse — your agent does the rest.
⚠️ **Trading warning / Avertissement trading** : informational only, not investment advice. A beat can still sink a stock on weak guidance, and a summary card is a starting point for reading, not a decision. Curated by Skill Harbor: the earnings skill of the Longbridge platform, published by the broker itself, covering US, Hong Kong and A-share names. Before the release, it runs a preview: a review of the guidance given last quarter, recent events since then, the questions analysts pressed on the last call, and a key-things-to-watch framework for the upcoming print. After the release, the default is a fast in-chat summary card built from a single bundled collector script (pure Python standard library) that fetches snapshot, income statement, consensus against actuals, EPS forecasts, quote, valuation multiples, institutional ratings, segments, news and candles in parallel: a core KPI table graded beat or miss against estimates, revenue by segment, six to eight quarters of revenue and margin trend, a thesis status read, the street's rating distribution and target range, next-quarter consensus, and a one-line risk list. Ask explicitly and it expands into a full Markdown research report with segment and margin analysis, guidance review, a model update and a three-method valuation with the math shown. Ratings and target prices come from the institutional consensus feed, not from the skill's own computation. Data comes through the Longbridge CLI or the MCP server. From the longbridge/skills repository (MIT). Honest caveats: the lite card deliberately skips the earnings call transcript and web sources, so management tone and color are absent by design, and consensus figures are only as current as the feed behind them. Skill Harbor never reviews the code, review it yourself before use.
Version:
Install
Copy the install package below, then paste it into MuseThe install prompt below already includes the vetting steps: your agent follows the community checklist before installing anything with executable code. Want more?
Use "Longbridge Earnings" with your Muse. Prerequisites: install the Longbridge CLI once (brew tap longbridge/tap && brew install longbridge/tap/longbridge-terminal) or add the Longbridge MCP server, and clone the repo (git clone https://github.com/longbridge/skills) so the skill and its collector script are on hand. Python 3 is needed for the fast summary card (the script is pure standard library). No Longbridge account is required for the data used here. 1. Open the skill: https://github.com/longbridge/skills/blob/main/skills/longbridge-earnings/SKILL.md and copy the full SKILL.md text. 2. Paste it into a chat with Muse and add: "Give me the post-earnings summary card for this ticker: KPI beat or miss, segments, margin trend, street view, and next-quarter consensus." 3. Before a release, ask instead for the pre-earnings preview and check that it names the reporting date and the prior guidance it is tracking. Tip: say "full report" explicitly when you want the Markdown research report with valuation; otherwise you get the fast card by design. Safety: a skill is plain-text instructions; it runs nothing by itself. Informational only, not investment advice.
Saved to your recent installs. Find it anytime on /connect.
Questions
How do I install a build?
Every product page includes a copy-paste install prompt. Paste it into your Muse and it sets the build up for you — no manual configuration.
Where does my money go?
Straight to the seller. Skill Harbor never processes payments: checkout happens on the seller’s own page, usually Stripe.
What does the ✓ next to a creator’s name mean?
It means we confirmed the identity of the person behind the listing. It says nothing about the code itself — always check a build before installing it.