Earnings Trade Analyzer
Score recent post-earnings movers with a five-factor system (gap, trend, volume, MA50 and MA200 position) and grade the strongest earnings reactions A to D.
- What
- Score recent post-earnings movers with a five-factor system (gap, trend, volume, MA50 and MA200 position) and grade the strongest earnings reactions A to D.
- Cost
- Free
- Needs
- Use "Earnings Trade Analyzer" 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. Post-earnings momentum is among the most volatile styles of trading; a top grade is a screening result, not a promise of returns. Curated by Skill Harbor: a scorer for post-earnings drift (PEAD) setups that ranks how stocks reacted to their earnings releases in the last few days. Each candidate is scored 0 to 100 across five weighted factors: the size of the earnings gap, the pre-earnings price trend, the volume trend into and after the report, and the stock's position relative to its 200-day and 50-day moving averages, then assigned a letter grade from A (strongest reactions) to D. The default run looks back 2 days and returns the top 20, with options for longer lookback windows, a minimum market-cap filter, and an entry-quality filter. The skill's script is careful about failure honesty: a broken earnings-calendar endpoint, an empty result over days when the market was actually open, or an exhausted API budget each exit as explicit failures rather than a fake "nothing happened today", so scheduled after-close runs do not silently report an empty day. It runs on Financial Modeling Prep (FMP) data. From the tradermonty/claude-trading-skills repository (MIT). Honest caveats: an FMP API key is required (the free tier's 250 calls per day covers the default run; larger lookbacks or full screening need FMP's paid tier). Earnings gaps can reverse violently, grades compress a lot of judgment into one letter, and the factors measure the reaction, not whether the underlying quarter was actually good. 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 "Earnings Trade Analyzer" with your Muse. Prerequisite: this skill needs a Financial Modeling Prep (FMP) API key (FMP_API_KEY environment variable or --api-key). The free tier (250 calls/day) covers the default run (2-day lookback, top 20); larger windows need FMP's paid tier. The skill itself is free and open source. 1. Open the skill: https://github.com/tradermonty/claude-trading-skills/blob/main/skills/earnings-trade-analyzer/SKILL.md and copy the full SKILL.md text. 2. Paste it into a chat with Muse and add: "Score the recent earnings reactions and show me the A and B grades with their five factors." 3. Dig into any name before considering it: read the actual earnings release, check the gap against the factors, and size any position for post-earnings volatility. Tip: if a scheduled run reports a failure code instead of candidates, that is the skill refusing to fake an empty day; retry with a narrower, more liquid universe. Safety: a skill is plain-text instructions; it runs nothing by itself. Never paste your FMP key into the chat itself, set it as an environment variable. Trading involves real risk of loss; this is 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.