earnings-analyzer
Skill2 starsChanged 5 months agoMITView on GitHub
Run a JPMorgan-style pre-earnings analysis on a specific ticker. Use when the user asks about an upcoming earnings report, "should I hold through earnings?", "what's the expected move?", or names a stock and earnings in the same query. Fetches portfolio via aifolimizer MCP.
1 other project uses a version of this.
Adopted by
Most recently taken up by
- BryceYuuu/open-workflow-skillstheir own version, first seen Sep 5, 2026
Other versions1 project uses a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 1
- BryceYuuu/open-workflow-skills★ 1same name
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository29 other files it gives its agents.
- AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- adversarial-researchSkill
- auto-rebalanceSkill
- cash-deploymentSkill
- daily-briefingSkill
- dividend-strategySkill
- earnings-postmortemSkill
- employer-stockSkill
- health-checkSkill
- macro-impactSkill
- momentum-scannerSkill
- optimize-allocationSkill
- pead-trackerSkill
- perf-optimizerSkill
- portfolio-healthSkill
- portfolio-reviewSkill
- position-reviewSkill
- pre-trade-checkSkill
- profile-setupSkill
- risk-assessmentSkill
- sector-rotationSkill
- stock-analysisSkill
- stock-compareSkill
- tax-loss-reviewSkill
- top-trades-todaySkill
- trade-journalSkill
- trading-deskSkill
- weekly-mirrorSkill
The file
We split this skill into the rules it gives an agent
10 rules. About 0 are common, 3 are distinctive, and 7 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈3
Distinctive · estimate
This author's own choices. Worth a look.
7
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 10
Before fetching market data, load prior decisions on this ticker so the verdict stays consistent across sessions:
- Very specific: line 19
Call mcp__aifolimizer__get_profile - account types and capital.
- Very specific: line 21
Call mcp__aifolimizer__get_earnings_calendar - confirmed next earnings date and days until
- Very specific: line 22
Call mcp__aifolimizer__get_fundamentals with symbols=[ticker] - EPS TTM, analyst target price, analyst recommendation
- Very specific: line 23
Call mcp__aifolimizer__get_recent_filings with ticker=ticker, forms=["8-K"] - pre-earnings 8-K events (guidance preannounce, M&A, exec …
- Very specific: line 24
Call mcp__aifolimizer__get_finnhub_news with ticker=ticker - news sentiment tally heading into the print (positioning into the event)
- Very specific: line 25
Call mcp__aifolimizer__get_earnings_results with symbols=[ticker], quarters=4 - authoritative last-4-quarters EPS …
- Distinctive: line 35
Historical price reaction: after each of last 4 earnings (% move + direction)
- Very specific: line 43
Call mcp__aifolimizer__log_recommendation with action (BUY/HOLD/SELL/ADD/TRIM), conviction (HIGH/MED/LOW), target_pct + stop_pct (% from …
- Distinctive: line 60
Don't confuse forward EPS estimate with reported EPS - clearly label estimate vs actual.
≈ “Common” is an estimate: at least 1 in 5 of the 364,980 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Earnings Analyzer (JPMorgan style)
Stage 0 - Decision Memory (load BEFORE forming any verdict)
Before fetching market data, load prior decisions on this ticker so the verdict stays consistent across sessions:
mcp__aifolimizer__get_ticker_decision_historywithticker=TICKER, max_decisions=5- prior actions, outcomes, reflectionsmcp__aifolimizer__get_ticker_reflectionwithsymbol=TICKER, n=3- prior recs + realized alphamcp__aifolimizer__get_cross_ticker_lessonswithmax_lessons=3- portfolio-level win/loss patterns
Reconciliation rule: if a prior decision exists and your new read flips it, state explicitly WHY it changed (new data / catalyst / price move). Never silently contradict a logged decision - that drift is exactly what this prevents.
How to run
- Call
mcp__aifolimizer__get_profile- account types and capital. Frame position sizing and tax impact of any pre-earnings trade - Confirm ticker via
mcp__aifolimizer__get_portfolio(or use stock with nearest earnings from get_earnings_calendar) - Call
mcp__aifolimizer__get_earnings_calendar- confirmed next earnings date and days until - Call
mcp__aifolimizer__get_fundamentalswithsymbols=[ticker]- EPS TTM, analyst target price, analyst recommendation - Call
mcp__aifolimizer__get_recent_filingswithticker=ticker, forms=["8-K"]- pre-earnings 8-K events (guidance preannounce, M&A, exec change) that reshape the setup. US-listed only - Call
mcp__aifolimizer__get_finnhub_newswithticker=ticker- news sentiment tally heading into the print (positioning into the event) - Call
mcp__aifolimizer__get_earnings_resultswithsymbols=[ticker], quarters=4- authoritative last-4-quarters EPS estimate/actual/surprise/beat-miss outcome. Do NOT WebSearch this; the MCP serves it. - WebSearch ONLY for what no MCP tool serves: options-implied move for earnings day (CBOE / broker IV), upcoming-quarter consensus EPS/revenue if absent from
get_fundamentals, and qualitative management guidance from the last call.
Output structure
- Last 4 quarters EPS vs consensus (beat/miss/meet) with price reactions
- Upcoming quarter consensus EPS and revenue
- Key metrics Wall Street is watching for this specific company
- Segment revenue breakdown and recent trends
- Management guidance summary from last call
- Historical price reaction after each of last 4 earnings (% move + direction)
- Bull case scenario - what beat looks like + price impact estimate
- Bear case scenario - what miss looks like + downside estimate
- Options-implied move for earnings day (search for recent IV)
- Recommended play: Buy before / Trim before / Hold through / Wait for post-earnings dip
After output - log decision
Call mcp__aifolimizer__log_recommendation with action (BUY/HOLD/SELL/ADD/TRIM), conviction (HIGH/MED/LOW), target_pct + stop_pct (% from entry - the schema takes percentages, not absolute prices), rationale (1-line thesis citing the play: buy before / trim before / hold through / wait), skill="earnings-analyzer". Feeds forward win-rate / track-record loop.
If the play is BUY/ADD, first call mcp__aifolimizer__get_positioning_signals with symbols=[ticker]: if crowding_score >= 70 the name is consensus-crowded into the print (late entry = negative expected alpha) - downgrade conviction or defer the add to post-earnings. This is a lighter check than the swing skills since earnings is an event catalyst, but a crowded pre-print add is exactly the chase to avoid.
Rules
- Decision summary at very top (one paragraph)
- Full breakdown below
- Under 500 words
- Reference user's actual cost basis from portfolio data to frame recommendation
Gotchas
get_earnings_calendarfrom yfinance can show next-FY date instead of next quarter for newly-listed or low-coverage tickers - sanity-check via WebSearch if days_until > 100.- Options-implied move NOT in MCP - must come from WebSearch (CBOE / OptionStrat / broker IV). Never fabricate IV.
- Last-4-quarters EPS beat/miss comes from
get_earnings_results(per-quarter estimate/actual/surprise/outcome) - do NOT WebSearch it.get_fundamentalscarries only the current/next quarter. Only options-implied move and qualitative guidance need WebSearch. - "Hold through earnings" is account-dependent: in non-reg account, early sell to lock gain triggers capital gains tax - call this out before recommending.
- Don't confuse forward EPS estimate with reported EPS - clearly label estimate vs actual.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

