agentleFS
ajeeshworkspaceajeeshworkspace/indian-trading-skills/skills/scenario-analyzer/SKILL.md

scenario-analyzer

Skill75 starsChanged 8 months agoMITView on GitHub

Analyze news headlines, policy announcements, or geopolitical events to build 18-month probabilistic scenarios for Indian markets. Use when the user provides a headline or asks about the market impact of RBI policy, government announcements, global events, budget, or sector-specific news on NSE/BSE stocks.

1 other project uses a version of this.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

6 rules. About 0 are common, 6 are distinctive, and 0 are 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.

  • 0

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Use WebSearch to find related news from the past 2 weeks

    line 67
  2. Distinctive:

    Probability: Must sum to 100% across all 3

    line 75
  3. Distinctive:

    Use NSE sectoral indices:

    line 95
  4. Distinctive:

    All probabilities must sum to 100%

    line 130
  5. Distinctive:

    Every impact claim must have a causal chain (event → mechanism → impact)

    line 131
  6. Distinctive:

    Consider second-order effects (e.g., rate cut → weak INR → IT sector benefit)

    line 133

≈ “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

Scenario Analyzer (India Markets)

Overview

This skill takes a news headline or event and builds probabilistic 18-month scenarios with cascading 1st, 2nd, and 3rd order sector impacts and specific stock recommendations for the Indian market.

Architecture

Skill (Orchestrator)
├── Phase 1: Preparation
│   ├── Headline parsing (keywords, entities, actions, numbers)
│   ├── Event classification
│   └── Load references
├── Phase 2: Analysis
│   ├── Collect related news (past 2 weeks via WebSearch)
│   ├── Build 3 scenarios (Base/Bull/Bear, probabilities sum to 100%)
│   ├── Map 1°/2°/3° sector impacts
│   └── Identify 3-5 positive + 3-5 negative impact stocks
└── Phase 3: Report Generation
    ├── Compile findings
    ├── Assess scenario probability distribution
    └── Save report

Event Classification

Classify the headline into one of these categories:

CategoryIndian Context Examples
Monetary PolicyRBI rate decision, CRR/SLR change, liquidity measures
Fiscal PolicyUnion Budget, GST changes, PLI schemes, disinvestment
GeopoliticalIndia-China border, India-Pakistan, Russia-Ukraine, Middle East
CommodityCrude oil shock, gold prices, metal tariffs, food inflation
RegulatorySEBI rules, RBI NPA norms, telecom spectrum, pharma FDA
CorporateMajor M&A, earnings surprise, promoter pledging, fraud
Global MacroFed rate decision, US recession, China slowdown, tariffs
Weather/AgricultureMonsoon forecast, crop damage, food prices
Elections/PoliticalState elections, central govt policy shifts

Workflow

Phase 1: Preparation

  1. Parse the Headline
    • Extract key entities (companies, sectors, countries, institutions)
    • Identify the action (increase, decrease, ban, approve, delay)
    • Note any numbers (rate changes, ₹ amounts, percentages)
    • Classify the event type
  2. Load References
    Read: references/headline_event_patterns.md
    Read: references/sector_sensitivity_matrix.md
    Read: references/scenario_playbooks.md

Phase 2: Analysis

  1. Collect Context
    • Use WebSearch to find related news from the past 2 weeks
    • Identify any pre-existing trends or expectations
    • Note market's initial reaction if available
  2. Build 3 Scenarios

    For each scenario:

    • Name: Descriptive title
    • Probability: Must sum to 100% across all 3
    • Timeline: 3 phases (0-6 months, 6-12 months, 12-18 months)
    • Description: What unfolds in each phase
    • Key Assumptions: What must hold true

    Typical structure:

    • Base Case (40-55%): Most likely outcome given current trajectory
    • Bull Case (20-35%): Optimistic scenario with positive catalysts
    • Bear Case (15-30%): Pessimistic scenario with adverse developments
  3. Map Sector Impacts

    For each scenario, assess impacts using the sector sensitivity matrix:

    OrderDefinitionExample (RBI Rate Cut)
    1stDirect, immediateBanks: NIM compression, Housing: demand boost
    2ndIndirect, 3-6 monthsAuto: loan demand, Real estate: prices
    3rdTertiary, 6-18 monthsCement: construction demand, Durables: consumer spending

    Use NSE sectoral indices:

    • Nifty Bank, Nifty IT, Nifty Pharma, Nifty Auto, Nifty FMCG
    • Nifty Metal, Nifty Realty, Nifty Energy, Nifty Infra
    • Nifty PSU Bank, Nifty Private Bank, Nifty Financial Services
  4. Identify Stock Impacts

    For each scenario:

    • 3-5 stocks that benefit most (positive impact)
    • 3-5 stocks that suffer most (negative impact)

    For each stock, provide:

    • Ticker (NSE symbol)
    • Current price (use broker MCP get_ltp — Groww or Zerodha Kite — if available)
    • Impact channel (why this stock is affected)
    • Magnitude estimate (High/Medium/Low)

Phase 3: Report Generation

  1. Generate Report

    Save as reports/scenario_analysis_<topic>_YYYYMMDD.md with sections:

    1. Related News (5-10 recent articles with sources)
    2. Scenario Overview (3 scenarios with probabilities)
    3. Timeline (0-6m, 6-12m, 12-18m phases for base case)
    4. Sector Impact Matrix (1°/2°/3° impacts per sector)
    5. Positive Impact Stocks (3-5 with rationale)
    6. Negative Impact Stocks (3-5 with rationale)
    7. Investment Implications (actionable takeaways)
    8. Risk to Scenarios (what could shift probabilities)
    9. Disclaimer

Quality Standards

  • All probabilities must sum to 100%
  • Every impact claim must have a causal chain (event → mechanism → impact)
  • Stock picks must include the impact channel, not just "will benefit"
  • Consider second-order effects (e.g., rate cut → weak INR → IT sector benefit)
  • Flag any confirmation bias in scenario construction
  • Include both sectors that benefit AND those that lose

Example Usage

User: "RBI cuts repo rate by 25 bps to 6%"

Analyst:
1. Classification: Monetary Policy
2. Key entities: RBI, repo rate, 25 bps, 6%
3. Collects recent RBI commentary and market expectations
4. Scenarios:
   - Base (50%): One more cut expected → banks pass on, housing demand rises
   - Bull (30%): Cycle of 75-100 bps cuts → strong credit growth, equity rally
   - Bear (20%): Global inflation returns → RBI pauses → rate-sensitive sell-off
5. 1° impacts: Banks, NBFCs, Housing Finance, Auto
6. 2° impacts: Real Estate, Consumer Durables
7. 3° impacts: Cement, Infrastructure
8. Stock picks: HDFCBANK, BAJFINANCE, GODREJPROP (positive); IT exporters if INR weakens

Resources

references/headline_event_patterns.md

Historical Indian market event patterns and reactions.

references/sector_sensitivity_matrix.md

Event type × NSE sector impact matrix.

references/scenario_playbooks.md

Scenario construction templates with Indian market context.

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.