compare-stocks
Skill0 starsChanged 38 days agoMITView on GitHub
Compare two or more Indian stocks side by side with DocStoX data. Use when the user asks to compare companies (for example "TCS vs Infosys"), pick between stocks in a sector, or see how several NSE or BSE companies stack up on growth, profitability, valuation or ownership.
In this repository4 other files it gives its agents.
- market-briefSkill
- research-stockSkill
- review-portfolioSkill
- screen-the-marketSkill
The file
We split this skill into the rules it gives an agent
2 rules. About 0 are common, 2 are distinctive, and 0 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈2
Distinctive · estimate
This author's own choices. Worth a look.
0
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 8
Put two to ten companies side by side on the same measures, from the same data, as of the same date.
- Distinctive: line 26
Start with one compact table, one row per company, with the measures that matter for the question.
≈ “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
Compare Indian stocks
Put two to ten companies side by side on the same measures, from the same data, as of the same date.
1. Resolve the symbols
Use NSE tickers. Resolve any company names with search_stocks. If the user named a sector instead of companies ("compare the big IT companies"), call get_peer_comparison on the best-known company in that sector and take the largest peers from its result, then confirm the list with the user if it is ambiguous.
2. Pull the numbers in batches
Batch tools take many symbols in one call. Use them instead of one call per company:
get_batch_fundamentalswith all the symbols: valuation, quality, growth and trend metricsget_batch_financialswith all the symbols: revenue and profit trend, withinclude_shareholdingset to true when ownership mattersget_batch_quotesfor prices and day change, when the user cares about recent price moves
For each company, get_peer_comparison adds the sector median, which tells you whether a figure is high or low for that industry.
3. Present a table, then the story
Start with one compact table, one row per company, with the measures that matter for the question. A sensible default set:
| Measure | Why it matters |
| Market cap (₹ crore) | Size |
| Revenue growth (YoY or 3-year) | Momentum of the business |
| Net profit margin | Profitability |
| ROE or ROCE | Return on capital |
| Debt to equity | Balance-sheet risk |
| P/E (and the sector median) | What the market pays |
| Promoter holding | Ownership |
Then explain, in a few sentences, where each company leads and lags, and what explains the differences (business mix, scale, cyclicality). Point out when a cheaper valuation comes with weaker growth or higher debt, so the comparison is fair.
Conventions: ₹ with Indian digit grouping, figures with their period (for example "FY26" or "June 2026 quarter"), and "not available" for missing values rather than estimates. Compare like with like: do not compare a bank's ratios with an IT company's.
Describe; never rank the stocks as buys or sells. End investment-related answers with:
This is for informational purposes only and not investment advice. Please consult a SEBI-registered advisor before investing.
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.