summarizing-earnings-calls
Transforms earnings call transcripts into structured summaries with financial guidance, KPI changes, management sentiment, and analyst Q&A highlights. Use when processing quarterly earnings calls, preparing investment research, or tracking company performance narratives.
Best use case
summarizing-earnings-calls is best used when you need a repeatable AI agent workflow instead of a one-off prompt.
Transforms earnings call transcripts into structured summaries with financial guidance, KPI changes, management sentiment, and analyst Q&A highlights. Use when processing quarterly earnings calls, preparing investment research, or tracking company performance narratives.
Teams using summarizing-earnings-calls should expect a more consistent output, faster repeated execution, less prompt rewriting.
When to use this skill
- You want a reusable workflow that can be run more than once with consistent structure.
When not to use this skill
- You only need a quick one-off answer and do not need a reusable workflow.
- You cannot install or maintain the underlying files, dependencies, or repository context.
Installation
Claude Code / Cursor / Codex
Manual Installation
- Download SKILL.md from GitHub
- Place it in
.claude/skills/summarizing-earnings-calls/SKILL.mdinside your project - Restart your AI agent — it will auto-discover the skill
How summarizing-earnings-calls Compares
| Feature / Agent | summarizing-earnings-calls | Standard Approach |
|---|---|---|
| Platform Support | Not specified | Limited / Varies |
| Context Awareness | High | Baseline |
| Installation Complexity | Unknown | N/A |
Frequently Asked Questions
What does this skill do?
Transforms earnings call transcripts into structured summaries with financial guidance, KPI changes, management sentiment, and analyst Q&A highlights. Use when processing quarterly earnings calls, preparing investment research, or tracking company performance narratives.
Where can I find the source code?
You can find the source code on GitHub using the link provided at the top of the page.
SKILL.md Source
# Summarizing Earnings Calls
## When To Use
- Processing a quarterly or annual earnings call transcript into a structured research summary
- Preparing investment memos where beat/miss framing and guidance changes are the primary deliverable
- Tracking management narrative shifts across consecutive quarters for a coverage universe
- Building a comparable summary format across multiple tickers for portfolio-level review
## Inputs To Gather
Collect before drafting. Do not proceed without the required items.
| Field | Required | Purpose |
|---|---|---|
| **Ticker / Company name** | Yes | Determines industry KPI set and peer context |
| **Quarter & fiscal year** | Yes | Anchors YoY and QoQ comparisons |
| **Consensus estimates** (Revenue, EPS minimum) | Yes | Enables beat/miss framing — omit beat/miss language entirely if unavailable |
| **Prior-quarter guidance** (if any) | Yes | Quantifies guidance revisions |
| **User's coverage context** | Recommended | "SaaS infrastructure analyst" vs. "generalist" shifts emphasis |
| **Specific focus areas** | Recommended | e.g., "margin trajectory," "China exposure," "AI capex" |
| **Prior-quarter summary** | Optional | Enables language-delta and KPI-trend analysis |
| **Industry vertical** | Auto-infer | Drives KPI extraction set (see Industry KPI Matrix below) |
## Workflow
### 1. Structural Parse
Segment the transcript into canonical sections:
1. **Operator / Safe Harbor** — confirm disclaimer exists; do not summarize it.
2. **CEO Prepared Remarks** — strategic narrative, high-level results, thematic emphasis.
3. **CFO Prepared Remarks** — revenue, margins, EPS, cash flow, balance sheet, guidance.
4. **Other Executive Remarks** — segment heads, CTO on product, etc.
5. **Analyst Q&A** — treat each question/answer pair as a discrete unit.
If section headers are missing, infer boundaries from speaker changes and flag with `[INFERRED SECTION BREAK]`.
### 2. Headline Numbers Extraction
Build the Financial Snapshot Table with these columns: Metric | Reported | Consensus | Beat/Miss | YoY Δ | QoQ Δ. Include at minimum: Revenue, Adj. EPS, Gross Margin, Operating Margin, FCF.
Rules:
- **Always state GAAP vs Non-GAAP basis.** If management leads with Non-GAAP, include both. Flag large adjustments (SBC > 10% of revenue, restructuring, one-time items).
- Use basis points (bps) for margin deltas, percentages for revenue/EPS deltas.
- Write "Not disclosed" for undisclosed metrics — never infer values.
### 3. Guidance Analysis
Build the Guidance Table with columns: Metric | New Guidance | Prior Guidance | Δ | Consensus | vs. Street.
Classify each metric as: **Raised / Maintained / Lowered / Narrowed / Initiated / Withdrawn**.
Quantify magnitude at midpoint: "$150M raise at midpoint, +2.1% vs prior guide" — not just "guidance was raised."
### 4. Segment & KPI Deep Dive
Extract segment-level disclosures and map to industry-relevant KPIs.
#### Industry KPI Matrix
| Vertical | Key KPIs |
|---|---|
| **SaaS / Cloud** | ARR, NRR/NDR, RPO/cRPO, CAC payback, gross retention, logo adds, DBE |
| **Retail / Consumer** | Same-store sales, comp growth, inventory turns, store count Δ, e-commerce mix |
| **Banks / Financials** | NIM, provision for credit losses, CET1 ratio, loan growth, deposit costs, NCO rate |
| **Industrials** | Book-to-bill, backlog, organic growth, price vs volume, input cost trends |
| **Pharma / Biotech** | Pipeline milestones, Rx volume, pricing/reimbursement, patent cliffs, R&D % of revenue |
| **Semiconductors** | Design wins, wafer utilization, ASP trends, inventory days, lead times |
| **Media / Streaming** | Subscriber adds/churn, ARPU, content spend, ad revenue mix |
For each reported segment, produce a mini-table: Segment | Revenue | YoY Δ | Margin | Commentary (use direct management language in commentary).
### 5. Management Sentiment & Tone
Score on a 5-point scale across four dimensions — overall confidence, demand environment, margin outlook, competitive positioning — each supported by a direct quote.
- **Hedging language flags**: Track frequency of "we believe," "we expect," "cautiously optimistic." Compare to prior quarter if available.
- **Tone shifts**: Explicitly call out language-strength changes vs. prior quarter (e.g., "shifted from 'confident' to 'cautiously optimistic' on enterprise demand").
- **Forward-looking statements**: Note material claims but flag as subject to safe-harbor provisions. Do not treat as commitments.
### 6. Analyst Q&A Extraction
Structure each exchange with columns: # | Analyst (Firm) | Topic | Key Takeaway | New Info? | Evasion Flag.
- **New Information**: Flag any Q&A disclosure absent from prepared remarks — this is where alpha lives.
- **Evasion Detection**: Flag non-answers, redirects, or vague language. Evasion on a topic is itself a signal.
- **Follow-up patterns**: Note when multiple analysts pressed on the same topic — indicates Street-level concern.
### 7. Capital Allocation & Balance Sheet
Tabulate: share repurchases, dividends, net debt/EBITDA, M&A commentary, and CapEx — each with current quarter, prior quarter, and commentary.
### 8. Risks & Watchlist
Compile from three sources:
- **Management-disclosed**: Macro, regulatory, supply chain, FX, competitive.
- **Q&A-implied**: Topics where multiple analysts pushed or management evaded.
- **Data-inferred**: Decelerating growth, margin compression, rising DSO.
Tag each item: `[HIGH]` `[MEDIUM]` `[LOW]`.
## Output
Assemble the final summary in this order:
1. **Header**: Ticker, Company, Quarter, Date, Call Duration
2. **TL;DR** (3–5 bullets): Most investable takeaways — what changed, what surprised
3. **Financial Snapshot Table** (Step 2)
4. **Guidance Table** (Step 3)
5. **Segment & KPI Detail** (Step 4)
6. **Management Tone** (Step 5)
7. **Analyst Q&A Highlights** (Step 6)
8. **Capital Allocation** (Step 7)
9. **Risks & Watchlist** (Step 8)
10. **Appendix**: GAAP/Non-GAAP reconciliation notes, definitions of non-standard KPIs
After presenting the draft, ask the user to verify: completeness of metrics, emphasis balance across sections, accuracy of consensus/guidance figures (highest error-risk fields), sentiment scoring alignment, and formatting for their distribution workflow.
## Quality Checks
| # | Check |
|---|---|
| 1 | Every reported metric cites GAAP or Non-GAAP basis |
| 2 | Beat/miss framing uses user-provided consensus — never fabricated estimates |
| 3 | Guidance deltas quantified at midpoint, not just directional |
| 4 | No forward-looking statement presented as a commitment or fact |
| 5 | Analyst names and firms attributed where identifiable |
| 6 | Evasion flags supported by specific non-answer quotes |
| 7 | YoY and QoQ deltas use consistent basis (same quarter, same metric definition) |
| 8 | Industry-specific KPIs match the company's actual vertical |
| 9 | Risks section includes at least one item from each source (disclosed, Q&A-implied, data-inferred) |
| 10 | `[VERIFY]` tags attached to any data point sourced from inference rather than explicit transcript text |
| 11 | No material Q&A information omitted from summary |
| 12 | Compliance disclaimer present if output will be distributed externally |
| 13 | No editorializing without quoted evidence ("management sounded defensive" requires a supporting quote) |
| 14 | Escalate to human review when transcript is partial, has audio-to-text artifacts, or uses unusual reporting frameworks |
## Reference Files
| File | Description |
|---|---|
| `references/EARNINGS-SUMMARY-TEMPLATE.md` | Output structure template for earnings call summaries with all nine sections and appendix |Related Skills
summarizing-discharge-notes
Transforms hospital discharge paperwork into structured patient summaries with medications, follow-up appointments, activity restrictions, and warning signs. Use when processing discharge documents, creating patient handoffs, or preparing transition-of-care summaries.
managing-earnings-releases
Structures earnings release preparation with GAAP/non-GAAP reconciliation and forward guidance documentation. Use when preparing earnings releases, reconciling non-GAAP measures, or drafting press releases.
analyzing-earnings-quality
Assesses earnings quality through accruals analysis, cash conversion, and accounting red flag identification. Use when evaluating earnings quality, detecting accounting anomalies, or analyzing accruals.
conducting-quality-of-earnings-analysis
Adjusts reported earnings for non-recurring items, accounting policy choices, and run-rate normalizations. Use when performing QofE analysis, adjusting EBITDA, or validating seller financial presentations.
skill-name
Replace with a specific description of what this skill does and when to use it. Include keywords that help agents identify relevant tasks.
writing-surgical-consultation-notes
Creates structured surgical consultation responses with assessment and surgical candidacy determination. Use when responding to surgical consults, evaluating surgical candidates, or documenting surgical recommendations.
writing-operative-reports
Creates structured operative notes with findings, technique, specimens, and estimated blood loss. Use when dictating operative reports, documenting surgical procedures, or recording intraoperative findings.
writing-irb-submissions
Creates IRB submission packages with protocol summaries, consent forms, and risk-benefit analysis. Use when submitting to IRB, preparing ethics applications, or writing consent documents.
writing-grant-applications-research
Structures NIH/foundation grant applications with specific aims, significance, and innovation sections. Use when writing research grants, preparing NIH applications, or structuring grant proposals.
writing-admission-orders
Generates structured admission order sets with diagnosis-specific protocols and safety checks. Use when admitting patients, creating admission orders, or setting up inpatient care plans.
validating-new-laboratory-tests
Structures test validation with precision, accuracy, linearity, and reference range establishment. Use when validating new assays, documenting method comparisons, or establishing reference ranges.
validating-clinical-data-quality
Structures data quality assessment with completeness, accuracy, and consistency validation. Use when auditing clinical data, assessing data quality, or validating data integrity.