agentleFS
d-wweid-wwei/openclaw-financial-services/skills/fsi-er-cmd-earnings/SKILL.md

fsi-er-cmd-earnings

Skill16 starsChanged 9 months agoApache-2.0View on GitHub

Analyze quarterly earnings and create an earnings update report — usage: /earnings [company name or ticker] [quarter, e.g. Q3 2024]

The file

We split this skill into the rules it gives an agent

7 rules. About 0 are common, 6 are distinctive, and 1 is very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈6

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 1

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Create a professional equity research earnings update report analyzing quarterly results.

    line 11
  2. Distinctive:

    If not provided, ask:

    line 21
  3. Distinctive:

    CRITICAL: Before proceeding, verify you have the latest data:

    line 27
  4. Distinctive:

    Search for "[Company] latest earnings results [current year]"

    line 28
  5. Distinctive:

    Verify the earnings release is within the last 3 months

    line 29
  6. Distinctive:

    If data is stale, inform the user and search for the latest.

    line 32
  7. Very specific:

    Use skill: "earnings-analysis" to create the report:

    line 36

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 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.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Earnings Analysis Command

Create a professional equity research earnings update report analyzing quarterly results.

Workflow

Step 1: Gather Information

Parse the input for:

  • Company name or ticker
  • Quarter (e.g., Q3 2024, Q2 FY25)

If not provided, ask:

  • "What company's earnings would you like to analyze?"
  • "Which quarter? (e.g., Q3 2024)"

Step 2: Verify Timeliness

CRITICAL: Before proceeding, verify you have the latest data:

  1. Search for "[Company] latest earnings results [current year]"
  2. Verify the earnings release is within the last 3 months
  3. Confirm transcript date matches release date

If data is stale, inform the user and search for the latest.

Step 3: Load Earnings Analysis Skill

Use skill: "earnings-analysis" to create the report:

  1. Data Collection (search for latest):
    • Earnings release (press release)
    • 10-Q filing from SEC EDGAR
    • Earnings call transcript
    • Investor presentation/supplemental materials
    • Consensus estimates (Bloomberg/FactSet)
  2. Beat/Miss Analysis:
    • Revenue vs consensus: Beat/Miss by $X or X%
    • EPS vs consensus: Beat/Miss by $X or X%
    • Key segment performance vs expectations
    • Explain WHY results differed
  3. Key Metrics Analysis:
    • Revenue breakdown by segment/geography
    • Margin trends (gross, operating, net)
    • Guidance: raised/maintained/lowered
    • Updated forward estimates
  4. Generate Charts (8-12):
    • Quarterly revenue progression
    • Quarterly EPS progression
    • Margin trends
    • Revenue by segment
    • Beat/miss summary
    • Estimate revisions
    • Valuation charts
  5. Create Report (8-12 pages):
    • Page 1: Summary with rating and price target
    • Pages 2-3: Detailed results analysis
    • Pages 4-5: Key metrics & guidance
    • Pages 6-7: Updated investment thesis
    • Pages 8-10: Valuation & estimates
    • Sources section with clickable hyperlinks

Step 4: Deliver Output

Provide:

  1. DOCX report - 8-12 page earnings update
  2. Summary highlighting:
    • Beat/miss on key metrics
    • Guidance changes
    • Thesis impact (positive/negative/neutral)

Report Structure Reference

PAGE 1: EARNINGS SUMMARY
┌─────────────────────────────────────────────────────────────────┐
│ [Company] Q3 2024 Earnings Update                               │
│ Rating: BUY | Price Target: $XXX (from $XXX)                    │
├─────────────────────────────────────────────────────────────────┤
│ KEY TAKEAWAYS                                                   │
│ • Revenue beat by X% on strong [segment] performance            │
│ • EPS beat by $X.XX driven by margin expansion                  │
│ • FY guidance raised to $X.XX-$X.XX (from $X.XX-$X.XX)         │
│ • Thesis intact; maintain BUY rating                            │
├─────────────────────────────────────────────────────────────────┤
│ RESULTS SNAPSHOT                                                │
│ ┌─────────────┬──────────┬──────────┬──────────┐               │
│ │ Metric      │ Actual   │ Consensus│ Beat/Miss│               │
│ │ Revenue     │ $X.XXB   │ $X.XXB   │ +X.X%    │               │
│ │ EPS         │ $X.XX    │ $X.XX    │ +$X.XX   │               │
│ │ Gross Margin│ XX.X%    │ XX.X%    │ +XXbps   │               │
│ └─────────────┴──────────┴──────────┴──────────┘               │
└─────────────────────────────────────────────────────────────────┘

PAGES 2-3: DETAILED RESULTS
- Segment-by-segment analysis
- Geographic breakdown
- Key drivers of beat/miss

PAGES 4-5: METRICS & GUIDANCE
- Margin analysis
- Full-year guidance comparison
- Updated quarterly estimates

PAGES 6-7: THESIS UPDATE
- What's changed
- Risks and catalysts
- Investment recommendation

PAGES 8-10: VALUATION
- Updated DCF/comps if material
- Price target justification
- Scenario analysis

SOURCES SECTION (with clickable hyperlinks):
- Earnings Release: [hyperlink]
- Form 10-Q: [EDGAR hyperlink]
- Earnings Call Transcript: [hyperlink]
- Consensus estimates: Bloomberg as of [date]

Quality Checklist

Before delivery:

  • Earnings data is from latest quarter (not stale)
  • Beat/miss quantified with specific numbers
  • All charts embedded (8-12 total)
  • Sources section with clickable hyperlinks
  • Every figure/table has source citation
  • Guidance changes clearly documented
  • Rating and price target stated upfront
  • 8-12 pages, 3,000-5,000 words

Download now (ZIP)

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
What did you use it for? e.g. Reviewing pull requests in a Rails app

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.