agentleFS
ShubhamkumartrichyShubhamkumartrichy/claude-trading-skills-india/skills/fundamental-screening/SKILL.md

fundamental-screening

Skill64 starsChanged 16 days agoMITView on GitHub

Fundamental and governance screening of Indian listed companies in the style of Screener.in: valuation (P/E, P/B, EV/EBITDA, PEG vs history and peers), quality (ROCE, ROE, cash conversion, debt), growth, sector-specific metrics (banks, NBFCs, IT, FMCG, manufacturing), shareholding pattern (promoter, FII, DII, pledge), quarterly results reading, and India-specific red flags (promoter pledging, related-party transactions, auditor exits, surveillance lists, SME and operator stocks).

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
  1. Distinctive:

    Always state the period: TTM, FY26, or Q2 FY27 (India's FY runs April–March.

    line 28
  2. Distinctive:

    Cyclicals (metals, cement, chemicals): use EV/EBITDA through the cycle.

    line 49

≈ “Common” is an estimate: at least 1 in 5 of the 364,980 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

Fundamental Screening (India)

Technicals decide when; fundamentals decide whether to hold for long. Screen for quality and red flags first. Valuation only matters once those pass.

Where to get data

  • Company filings on nseindia.com and bseindia.com: quarterly results (due within 45 days of quarter end, 60 days for Q4), shareholding pattern (within 21 days of quarter end), annual reports, investor presentations, concall transcripts, and SAST/pledge disclosures.
  • Aggregators: Screener.in (ratios, 10-year financials, peer tables), Trendlyne, Tickertape, Moneycontrol. Fetch with WebFetch and cite the page and date.
  • Broker MCPs generally give prices and holdings, not financials.
  • Always state the period: TTM, FY26, or Q2 FY27 (India's FY runs April–March; Q2 FY27 = Jul–Sep 2026).

1. Quality (pass at least 4 of 6 for a "quality" tag)

MetricGoodNotes
ROCE (5-yr avg)> 15%Use ROE for banks/NBFCs
Operating cash flow / net profit (5-yr)> 80%Low means profits aren't converting to cash
Debt / equity< 0.5 (non-financials)Interest coverage > 4×
Sales growth (5-yr CAGR)> 10%Compare with India's nominal GDP growth
Profit growth (5-yr CAGR)≥ sales growthWatch "other income"-driven profits
Promoter holdingStable/rising, pledge ≈ 0%Pledge > 20% of promoter stake is a red flag

2. Valuation (relative, never absolute)

  • P/E vs the company's own 5- and 10-year median and vs 3–5 listed peers. PEG = P/E ÷ EPS growth (%).
  • Banks/NBFCs: P/B and P/ABV with ROA > 1.2%, GNPA/NNPA trend, credit cost, NIM, CASA ratio (banks), capital adequacy > 15%.
  • IT services: constant-currency revenue growth, EBIT margin, deal TCV, attrition, US exposure.
  • FMCG/consumer: volume growth vs price growth, gross margin vs raw materials, distribution reach.
  • Capital goods/infra: order book ÷ revenue (years of visibility), working-capital days, execution.
  • Cyclicals (metals, cement, chemicals): use EV/EBITDA through the cycle. Low P/E at peak earnings is a trap.

3. Shareholding pattern (quarterly)

SignalReading
Promoter stake rising (open-market buys)Insider confidence
Promoter stake falling via OFS/blocksCheck the reason: debt repayment vs exit
Pledged shares risingMargin-call risk on a price fall; forced selling spirals
FII + DII (MF) stake risingInstitutional accumulation
Retail/public share rising while price risesLate-stage retail chase; caution

4. Red flags (any one is serious)

  • Promoter pledge above about 20%, or pledge invocations.
  • Auditor resignation or qualified opinion, or frequent changes of auditor or CFO.
  • Large related-party transactions, loans to promoter entities, complex subsidiary webs.
  • Receivables or "other current assets" growing much faster than sales. Repeated "exceptional items".
  • Persistent negative operating cash flow with reported profits.
  • Frequent equity dilution: preferential allotments, warrants to promoters at low prices.
  • Inclusion in ASM/GSM/ESM surveillance, trade-for-trade series (BE/BZ), or a 2%/5% price band.
  • SEBI, ED, SFIO or tax actions. Delayed results filings.
  • Operator/tip-stock pattern: tiny free float, upper-circuit streaks, volume spikes with no news, Telegram/WhatsApp promotion, an SME listing at an extreme multiple.

5. Reading quarterly results

  1. YoY first (seasonality), then QoQ. Separate revenue growth into volume and price where disclosed.
  2. EBITDA margin trend and its drivers: raw materials, employee cost, pricing.
  3. Strip out one-offs (exceptional items, tax write-backs, other income spikes).
  4. Compare with consensus if available (news), management guidance, and the previous concall.
  5. Note the price reaction. A good result with a falling price means expectations were higher.

Output

# [Company] — fundamental screen ([data period], sources)
Verdict: [Quality compounder | Fair | Cyclical | Speculative | Avoid] — one line why
| Quality | Value | Pass? |
...
Valuation: P/E x vs 5-yr median y, peers z → [cheap/fair/rich]
Shareholding: promoter a% (pledge b%), FII c%, DII d% — trend
Red flags: none / [list]
What to watch: next results date, guidance items, risks

State that this is not investment advice, and that fundamentals inform long-term holding, not short-term price moves.

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.