fsi-lseg-cmd-research-equity
Skill16 starsChanged 9 months agoApache-2.0View on GitHub
Generate a comprehensive equity research snapshot with consensus estimates, fundamentals, and price performance — usage: /research-equity <ticker e.g. AAPL> [period e.g. FY2024-FY2026]
In this repository99 other files it gives its agents.
- fsi-comps-analysisSkill
- fsi-er-catalyst-calendarSkill
- fsi-er-cmd-catalystsSkill
- fsi-er-cmd-earnings-previewSkill
- fsi-er-cmd-earningsSkill
- fsi-er-cmd-initiateSkill
- fsi-er-cmd-model-updateSkill
- fsi-er-cmd-morning-noteSkill
- fsi-er-cmd-screenSkill
- fsi-er-cmd-sectorSkill
- fsi-er-cmd-thesisSkill
- fsi-er-earnings-analysisSkill
- fsi-er-earnings-previewSkill
- fsi-er-idea-generationSkill
- fsi-er-initiating-coverageSkill
- fsi-er-model-updateSkill
- fsi-er-morning-noteSkill
- fsi-er-sector-overviewSkill
- fsi-er-thesis-trackerSkill
- fsi-fa-3-statementsSkill
- fsi-fa-check-deckSkill
- fsi-fa-check-modelSkill
- fsi-fa-cmd-3-statementsSkill
- fsi-fa-cmd-check-deckSkill
- fsi-fa-cmd-competitive-analysisSkill
- fsi-fa-cmd-compsSkill
- fsi-fa-cmd-dcfSkill
- fsi-fa-cmd-debug-modelSkill
- fsi-fa-cmd-lboSkill
- fsi-fa-cmd-ppt-templateSkill
- fsi-fa-competitive-analysisSkill
- fsi-fa-dcf-modelSkill
- fsi-fa-lbo-modelSkill
- fsi-fa-ppt-template-creatorSkill
- fsi-fa-skill-creatorSkill
- fsi-ib-buyer-listSkill
- fsi-ib-cim-builderSkill
- fsi-ib-cmd-buyer-listSkill
- fsi-ib-cmd-cimSkill
- fsi-ib-cmd-deal-trackerSkill
- fsi-ib-cmd-merger-modelSkill
- fsi-ib-cmd-one-pagerSkill
- fsi-ib-cmd-process-letterSkill
- fsi-ib-cmd-teaserSkill
- fsi-ib-datapack-builderSkill
- fsi-ib-deal-trackerSkill
- fsi-ib-merger-modelSkill
- fsi-ib-pitch-deckSkill
- fsi-ib-process-letterSkill
- fsi-ib-teaserSkill
- fsi-lseg-bond-futures-basisSkill
- fsi-lseg-bond-relative-valueSkill
- fsi-lseg-cmd-analyze-bond-basisSkill
- fsi-lseg-cmd-analyze-bond-rvSkill
- fsi-lseg-cmd-analyze-fx-carrySkill
- fsi-lseg-cmd-analyze-option-volSkill
- fsi-lseg-cmd-analyze-swap-curveSkill
- fsi-lseg-cmd-macro-ratesSkill
- fsi-lseg-cmd-review-fi-portfolioSkill
- fsi-lseg-equity-researchSkill
- The first 60 shown.
The file
We split this skill into the rules it gives an agent
6 rules. About 0 are common, 1 is distinctive, and 5 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈1
Distinctive · estimate
This author's own choices. Worth a look.
5
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 21
Ask the user for:
- Very specific: line 28
Call qa_ibes_consensus with the ticker for FY1 and FY2 estimates.
- Very specific: line 36
Call qa_company_fundamentals for the last 3-5 fiscal years.
- Very specific: line 42
Call qa_historical_equity_price for 1Y history.
- Very specific: line 48
Call tscc_historical_pricing_summaries with interval: "P1D", tenor: "3M".
- Very specific: line 54
Call qa_macroeconomic for GDP, CPI, and policy rate in the company's primary market.
≈ “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.
Files
Research Equity
This command uses LSEG quantitative analytics, historical pricing, and macroeconomic data tools. See CONNECTORS.md for available tools.
Generate a comprehensive equity research snapshot combining analyst consensus estimates, historical financials, price performance, and macroeconomic context.
See the equity-research skill for domain knowledge on fundamental analysis and estimate interpretation.
Workflow
1. Gather Input
Ask the user for:
- Ticker symbol (required) — IBES ticker format (e.g., AAPL, MSFT, VOD)
- Forward period of interest (optional, default: next 2 fiscal years)
- Any specific focus areas (e.g., earnings, revenue, dividends)
2. Gather Consensus Estimates
Call qa_ibes_consensus with the ticker for FY1 and FY2 estimates.
- Measures: EPS, Revenue, EBITDA, DPS
- Period type: "A" (annual)
Extract: median/mean estimate, analyst count, high/low range, dispersion.
3. Pull Historical Fundamentals
Call qa_company_fundamentals for the last 3-5 fiscal years.
Extract: revenue growth, margin trends, leverage, earnings trajectory.
4. Assess Price Performance
Call qa_historical_equity_price for 1Y history.
Compute: YTD return, 1Y return, 52-week range, beta.
5. Recent Price Action Detail
Call tscc_historical_pricing_summaries with interval: "P1D", tenor: "3M".
Extract: daily OHLCV, volume trends, recent momentum.
6. Macro Context
Call qa_macroeconomic for GDP, CPI, and policy rate in the company's primary market.
Summarize: economic environment as tailwind or headwind for the sector.
7. Synthesize the Report
Present: consensus estimates table, historical financials summary, valuation metrics (forward P/E = price / consensus EPS), price performance, macro backdrop, and investment thesis summary.
Output Format
Present as a structured research note. Lead with the investment thesis summary (1-2 sentences), then detail supporting sections with tables.
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
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.