mcpbeat Sign in

Earnings Flash Skill for Codex

Rapid first-read earnings flash for a given company

2k tokens
context cost
the whole folder, loaded on every use
2
files
instructions only
0
copies elsewhere
how many repositories repackaged it
4915
stars on the repo
on the repository, not the skill itself

Install

one command, takes just this skill from the repository
npx skills add https://github.com/openai/plugins --skill earnings-flash

What comes with it

214 bytes besides the instruction
agents/openai.yaml

The instruction itself

12 sections, as written by the author

Generate a rapid earnings flash for the company specified by the user named in the user's request. If no ticker or company is provided, ask for one before proceeding.

This is a lightweight, speed-focused version of the earnings-review skill — designed for a quick first read within minutes of a filing. It pulls just enough context from Daloopa to frame BEAT/MISS verdicts, then focuses on what's new and surprising.

Before starting, read ../data-access.md for data access methods and ../design-system.md for formatting conventions. Follow the data access detection logic and design system throughout this skill.

1. Company Lookup

Look up the company by ticker using discover_companies. Capture:

  • company_id
  • latest_calendar_quarter — anchor for all period calculations (see ../data-access.md Section 1.5)
  • latest_fiscal_quarter
  • Firm name for report attribution (default: "Daloopa") — see ../data-access.md Section 4.5

2. Prior Quarter Context (4 Quarters)

Calculate 4 quarters backward from latest_calendar_quarter. Search for and pull these core metrics:

Income Statement:

  • Revenue / Net Sales
  • Gross Profit
  • Operating Income / EBIT
  • Net Income
  • Diluted EPS

Cash Flow:

  • Operating Cash Flow
  • Free Cash Flow (or CapEx to compute it)

This is lighter than the earnings-review skill (4Q vs 8Q, no cost structure breakdown). The goal is just enough history to frame the latest quarter's results — not a full trend analysis.

3. Company-Specific KPIs

Think about the 3-5 most important KPIs for THIS company based on its business model. Search for those specific KPIs and pull for the same 4-quarter period. Also search for:

  • Segment/product revenue breakdown
  • Geographic revenue breakdown (if material)

Keep this targeted — discover the critical operating metrics, not everything available.

4. Guidance Series

Search for guidance series (revenue guidance, EPS guidance, margin guidance, any KPI guidance). If available, pull guidance data for the latest 2 quarters so you can compare the most recent actual results against what management guided.

CRITICAL: Apply +1 quarter offset — guidance from Q(N) applies to Q(N+1) results.

5. Get the Earnings Document

Use search_documents to find the most recent earnings-related filing. Search strategy:

  • Search for keywords ["results", "earnings"] in the latest 1-2 calendar quarters
  • If that returns nothing, try ["revenue"] or ["financial"] as broader terms

Read the document content from the search results. Focus on:

  • Earnings transcripts: Full document (management commentary, prepared remarks, Q&A)
  • 10-Q / 10-K: Financial statements and MD&A sections
  • 8-K: Full document (short event-driven filings)

If no document is found, proceed with the MCP fundamentals data only and note "No earnings document found — analysis based on financial data only."

5b. Stock Price Context

Get the current stock price using get_stock_prices (see ../data-access.md Section 1.7) — pass company_id and dates for the 3 most recent calendar days. Also pull prices around the earnings date (1 day before to 3 days after the latest_calendar_quarter end + ~30-45 days) to compute the post-earnings reaction. Include the next-day move percentage in the Executive Flash section.

6. Executive Flash

Write 3-5 bullet-point verdicts. Each bullet MUST compare the latest quarter's results against prior periods from Step 2 and/or guidance from Step 4. Format:

[BEAT/MISS/INLINE/MIXED] | Key number (YoY change) | One-sentence context

Examples:

  • BEAT | Revenue $95.4bn (+6.1% YoY) | Acceleration from +4.8% last quarter driven by iPhone 16 cycle
  • MISS | EPS $1.46 vs $1.52 prior year | Higher opex from AI investments weighed on margins
  • GUIDANCE UP | FY2026 revenue guided $400-405bn | Management raised full-year outlook on cloud strength

Use Daloopa citation links for all figures sourced from MCP. Use "(per filing)" for figures only found in the document.

Also include a one-line Management Tone assessment (confident/cautious/defensive/evasive/optimistic) if an earnings document was available. Support with specific language from the document.

7. Key Numbers Table

Present the latest quarter's results with comparison context:

| Metric | Latest Quarter | Prior Quarter | YoY Change | vs Guidance |

|--------|---------------|---------------|------------|-------------|

Include: revenue, EPS, margins, segment breakdowns, KPIs — all sourced from MCP with Daloopa citation links. Add a "vs Guidance" column if guidance data was available from Step 4 (show beat/miss amount).

Group by category: P&L, Segments, KPIs, Cash Flow.

For figures only available from the document (not in MCP), include them in a separate "Per Filing" sub-section below the table and note they are not cross-referenced.

8. Guidance & Outlook

Extract forward-looking statements from the earnings document (if available):

  • Explicit numerical guidance (revenue, EPS, margin ranges)
  • Changes from prior guidance (raised, lowered, narrowed, withdrawn)
  • Qualitative outlook language
  • Capex/investment plans

If guidance data was pulled from Daloopa in Step 4, compare new guidance against prior guidance with a table:

| Metric | New Guidance | Prior Guidance | Change |

|--------|-------------|---------------|--------|

If no document was found, summarize any guidance series data from Step 4 and note that no new guidance language is available.

9. Risk Flags

Call out concerning signals — this section should be sharp and skeptical:

  • Guidance cuts or narrowing
  • Missing disclosures or metrics that were previously reported
  • Growing gap between GAAP and non-GAAP
  • Cash flow divergence from earnings
  • One-time items that flatter the headline numbers
  • Management hedging or qualifying language (from document)

If no material risk flags, say so clearly: "No material risk flags identified."

10. Quick Read-Throughs

Write 2-3 bullets on what this filing implies for adjacent companies:

  • Suppliers: Positive or negative signal for key input providers
  • Customers: Demand signal for downstream buyers
  • Competitors: Share shift, pricing, or market growth implications

Format: [COMPANY/SECTOR]: [implication] (based on [specific data point])

11. Save Report

Save the HTML report to: reports/{TICKER}_earnings_flash_{PERIOD}.html (where PERIOD is the latest calendar quarter analyzed).

Use the design-system HTML template from ../design-system.md. Include all CSS inlined.

Add a FLASH banner at the top of the report. Insert this right after the opening <body> tag, before the <h1>:

<div style="background: #C0392B; color: white; text-align: center; padding: 8px 16px; font-size: 14px; font-weight: bold; letter-spacing: 2px; margin-bottom: 16px;">
    EARNINGS FLASH — FIRST READ
</div>

The <h1> should be: {TICKER} Earnings Flash — {PERIOD}

Add a disclaimer after the flash banner:

<p style="font-size: 10px; color: #6C757D; font-style: italic; margin-bottom: 16px;">
    This is a rapid first-read summary. For full analysis with 8-quarter trends, cost structure,
    and competitive read-throughs, run the earnings-review skill for {TICKER}.
</p>

Replace {FIRM_NAME} in the footer — see ../data-access.md Section 4.5.

All financial figures from Daloopa must use citation format: <a href="https://daloopa.com/src/{fundamental_id}">$X.XX million</a>

Tell the user where the HTML report was saved and highlight the 2-3 most notable findings.

Other skills for the same job

different authors, same section of the catalogue
Protocolsio Integration
by christophacham
×4

Integration with protocols.io API for managing scientific protocols. This skill should be used when working with protocols.io to search, create, update, or publish protocols; manage protocol steps and materials; handle discussions and comments; organize workspaces; upload and manage files; or integrate protocols.io functionality into workflows. Applicable for protocol discovery, collaborative protocol development, experiment tracking, lab protocol management, and scientific documentation.

16k tokens
Tailored Resume Generator
by frostant
×4

Analyzes job descriptions and generates tailored resumes that highlight relevant experience, skills, and achievements to maximize interview chances

3k tokens
Excalidraw Diagram Generator
by github
vendor ×3

Generate Excalidraw diagrams from natural language descriptions. Use when asked to "create a diagram", "make a flowchart", "visualize a process", "draw a system architecture", "create a mind map", or "generate an Excalidraw file". Supports flowcharts, relationship diagrams, mind maps, and system architecture diagrams. Outputs .excalidraw JSON files that can be opened directly in Excalidraw.

36k tokens scripts
Executing Plans
by ZhanlinCui
×3

Use when you have a written implementation plan to execute in a separate session with review checkpoints

542 tokens
Anndata
by christophacham
×3

Data structure for annotated matrices in single-cell analysis. Use when working with .h5ad files or integrating with the scverse ecosystem. This is the data format skill—for analysis workflows use scanpy; for probabilistic models use scvi-tools; for population-scale queries use cellxgene-census.

16k tokens
Benchling Integration
by christophacham
×3

Benchling R&D platform integration. Access registry (DNA, proteins), inventory, ELN entries, workflows via API, build Benchling Apps, query Data Warehouse, for lab data management automation.

14k tokens
Biopython
by christophacham
×3

Comprehensive molecular biology toolkit. Use for sequence manipulation, file parsing (FASTA/GenBank/PDB), phylogenetics, and programmatic NCBI/PubMed access (Bio.Entrez). Best for batch processing, custom bioinformatics pipelines, BLAST automation. For quick lookups use gget; for multi-service integration use bioservices.

24k tokens
Cellxgene Census
by christophacham
×3

Query the CELLxGENE Census (61M+ cells) programmatically. Use when you need expression data across tissues, diseases, or cell types from the largest curated single-cell atlas. Best for population-scale queries, reference atlas comparisons. For analyzing your own data use scanpy or scvi-tools.

8k tokens

How to use it

Copy the folder

Take openai/earnings-flash from the repository into ~/.claude/skills for personal use, or into .claude/skills inside a project.

Check the name does not clash

The agent identifies a skill by the name field in its header. Two skills with the same name cannot sit side by side — one of them will be ignored.