skills/finance/summarizing-earnings-calls/SKILL.md
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.
npx skillsauth add casemark/skills summarizing-earnings-callsInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
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) |
Segment the transcript into canonical sections:
If section headers are missing, infer boundaries from speaker changes and flag with [INFERRED SECTION BREAK].
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:
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Classify each metric as: Raised / Maintained / Lowered / Narrowed / Initiated / Withdrawn.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."
Extract segment-level disclosures and map to industry-relevant KPIs.
| 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).
Score on a 5-point scale across four dimensions — overall confidence, demand environment, margin outlook, competitive positioning — each supported by a direct quote.
Structure each exchange with columns: # | Analyst (Firm) | Topic | Key Takeaway | New Info? | Evasion Flag.
Tabulate: share repurchases, dividends, net debt/EBITDA, M&A commentary, and CapEx — each with current quarter, prior quarter, and commentary.
Compile from three sources:
Tag each item: [HIGH] [MEDIUM] [LOW].
Assemble the final summary in this order:
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.
| # | 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 |
| File | Description |
|---|---|
| references/EARNINGS-SUMMARY-TEMPLATE.md | Output structure template for earnings call summaries with all nine sections and appendix |
tools
Audits the complete in-scope medical-record universe in a litigation matter and produces an attorney-facing, Bates-cited analysis of treatment gaps, missing records or providers, baseline coverage, material billing or production mismatches, and complaint evolution. Use when asked to find missing medical records, analyze treatment gaps or first-care timing, identify absent providers, assess whether a production is complete, or prepare a records-request target list. Use medical-record-chronology instead when the primary request is a chronological clinical narrative.
development
Drafts a legally compliant Private Placement Memorandum for Regulation D offerings (Rule 506(b)/506(c)), covering full disclosure framework including risk factors, capitalization, securities terms, use of proceeds, and investor qualification requirements. Enforces SEC anti-fraud compliance under Section 10(b)/Rule 10b-5, blue sky law considerations, and accredited investor verification under Rule 501. Use this skill when drafting PPMs, offering memorandums, Reg D disclosure documents, or private offering circulars for issuers raising capital from sophisticated investors. Also trigger when the user mentions private placement disclosure, offering memorandum, Reg D fundraising, or accredited investor verification. Even if the user just says "PPM" or "draft our offering memo," use this skill.
data-ai
Generates structured privacy and data protection law briefings across US, EU, UK, and other jurisdictions. Organizes by jurisdiction with compliance deadlines, enforcement actions, and legislative changes. Use when preparing privacy law briefings, compliance updates, regulatory change summaries, or data protection landscape reviews.
testing
Generates structured summaries of prior art references for patent prosecution, validity analysis, and freedom-to-operate assessments. Maps disclosures to claim elements with precise citations. Use when summarizing prior art, analyzing patent landscapes, mapping references to claims, or preparing office action responses.