Now liveThe Skillselion MCP - thousands of ranked skills, loaded into your agent mid-task. No install.Get it →
pionex-official avatar

Financial Analysis Earnings Preview

  • 70 installs
  • 5 repo stars
  • Updated July 24, 2026
  • pionex-official/pionex-skills

Helps with ai & agent building tasks.

About

financial-analysis-earnings-preview is a Claude Code skill in the AI & Agent Building category.

  • financial-analysis-earnings-preview
  • AI & Agent Building
  • AI-coding skill

Financial Analysis Earnings Preview by the numbers

  • 70 all-time installs (skills.sh)
  • +3 installs in the week ending Aug 4, 2026 (Skillselion tracking)
  • Ranked #5,726 of 16,546 AI & Agent Building skills by installs in the Skillselion catalog
  • Data as of Aug 4, 2026 (Skillselion catalog sync)
npx skills add https://github.com/pionex-official/pionex-skills --skill financial-analysis-earnings-preview

Add your badge

Show developers this skill is listed on Skillselion. Paste this into your README.

Listed on Skillselion
Installs70
repo stars5
Last updatedJuly 24, 2026
Repositorypionex-official/pionex-skills

What it does

Helps with ai & agent building tasks.

Files

SKILL.mdMarkdownGitHub ↗

Earnings Preview

Build a pre-earnings preview with consensus estimates, historical trend, scenarios, and catalyst checklist. Uses SEC EDGAR for historical financials and web search for consensus/dates.

Setup

No dependencies required. All scripts use Python standard library only.

Workflow

Step 1 — Find earnings date and consensus (web search)

Always search first. Do NOT rely on training data for consensus estimates.

Search A — earnings date:

  • [Company] [ticker] earnings date Q[X] FY[YYYY]
  • [Ticker] earnings release date when

Search B — consensus estimates (run in parallel with Step 2):

  • [Company] Q[X] FY[YYYY] earnings preview consensus estimate revenue EPS
  • [Ticker] earnings estimates Wall Street expectations Q[X] FY[YYYY]

If Search B returns only vague language without absolute dollar figures, run:

  • [Ticker] Q[X] FY[YYYY] revenue estimate $B analyst consensus

Extract ALL before proceeding:

FieldNotes
Earnings dateExact date; "date not confirmed" if unavailable
Quarter being reported (e.g. Q2 FY2026)Explicit fiscal quarter — not "next quarter"
Revenue consensus estimateMust be absolute dollar value (e.g. "$29.3B")
Adj. EPS consensus estimateMust be a dollar figure (e.g. "$2.18")
Prior guidance rangeCompany's guidance for this period
Key analyst themes2-3 expectations or concerns

Verify the earnings date is in the future. If it has passed, that quarter is already reported — search for the next upcoming date instead.

---

Step 2 — Pull historical trend (scripts)

Run in parallel with Search B:

bash run.sh <SYMBOL> --form 10-Q --periods 8
bash run.sh <SYMBOL> --form 10-K --periods 3

10-Q data is YTD cumulative. Derive standalone quarters by subtraction:

  • Q1 = Q1 YTD
  • Q2 = H1 YTD − Q1 YTD
  • Q3 = 9M YTD − H1 YTD
  • Q4 = Full-year (10-K) − 9M YTD

Present as mandatory trend table (minimum 4 quarters + estimate row):

QuarterRevenueYoYGross MarginOp. MarginDiluted EPS
Q[X-3] FY[YYYY] A$X.XB+X%XX.X%XX.X%$X.XX
Q[X] FY[YYYY] E$X.XB(E)+X%E$X.XX(E)

The last row "Q[X] FY[YYYY] E" is consensus from Step 1 — mark as "(E)" for estimate.

---

Step 3 — Build scenarios

BullBaseBear
RevenueBeat consensus by ~X%In-lineMiss by ~X%
Adj. EPSBeatIn-lineMiss
Gross marginExpansion vs prior yearFlatCompression
Key driverUpside in [segment]Steady executionWeakness in [risk]

Anchor to history: Use the company's historical beat/miss magnitude from the trend table to size the bull and bear scenarios. For example, if the company has beaten revenue consensus by ~10% in recent quarters (e.g. NVDA), use ~8-12% for bull — not a generic 2-4%. For mature companies with consistent ~1% beats, use ~1-3%. State the primary trigger for each scenario.

---

Step 4 — Catalyst checklist

List 3-5 watchpoints:

[ ] Key question (e.g. "Does [segment] revenue accelerate above X%?")
    Why it matters: [1-2 sentences]
    What to look for: [specific metric or commentary]

Focus on: key segment variance, margin trajectory, forward guidance, prior quarter risks.

---

Output Format

Header box (mandatory, always first):

[COMPANY] ([TICKER]) — Q[X] FY[YYYY] EARNINGS PREVIEW
Earnings date: [exact date or "TBC"]

Consensus:   Revenue $X.XB (+X% YoY)  |  Adj. EPS $X.XX (+X% YoY)
Prior guidance: [range or "not provided"]
Source: [source name, retrieved YYYY-MM-DD]

Section 1 — Trend table (mandatory, min 4 quarters + estimate row)

Section 2 — Trend commentary (3-5 sentences)

Section 3 — What the Street expects

Section 4 — Scenarios (Bull / Base / Bear table)

Section 5 — Catalyst checklist (3-5 watchpoints)

Closing caveat:

Earnings previews are based on consensus estimates from public sources and historical reported data. Actual results may differ materially. This is not investment advice.

---

Formatting Rules

  • Revenue / profit: B or M, e.g. "$29.3B"
  • Margins: one decimal percent, e.g. "48.2%"
  • EPS: two decimals, e.g. "$2.18"
  • Growth rates: one decimal, e.g. "+12.4% YoY"

Limitations

  • No real-time consensus: estimates from web search — always note source and date
  • SEC EDGAR lag: filed data may not include most recent quarter
  • 10-Q is cumulative YTD: always subtract prior periods for standalone quarters
  • US stocks only: SEC EDGAR covers US-listed equities only

Related skills

This week in AI coding

Five minutes, every Monday - the tools, releases and tactics for developers.

unsubscribe anytime.