Community연구 & 데이터 분석github.com

kuntal-r-d/my-skills

name: macro-regime

지원 대상~Claude Code~Codex CLI~Cursor
npx skills add kuntal-r-d/my-skills

Ask in your favorite AI

Open a new chat with this agent skill pre-loaded.

문서

Macro Regime

When to use

Activate when a user wants the macro read on the Dhaka Stock Exchange: "what's the market regime?", "is this a risk-on environment?", "how do rates and reserves affect risk?", "give me a macro multiplier". This is the Macro Agent (PRD-002 REQ-020). Its risk multiplier is meant to be consumed downstream by signal-synthesizer (to scale the composite score) and risk-manager (to scale position sizing).

What it does

Reads the shared contract's macro block and computes a single risk multiplier in [0.5, 1.2], starting from 1.0 (neutral) and adjusting for each factor:

  • Policy rate — tight money (>=9%) lowers the multiplier; accommodative raises it.
  • Inflation — above 8% lowers it (real-return erosion, tightening risk).
  • FX reserves trendfalling lowers it (import-cover stress, BDT pressure); rising raises it; stable is neutral.
  • Politicscrisis/tense lower it; stable raises it.
  • Regulatoryfloor_prices/tightening lower it; normal is neutral.

The clamped multiplier maps to a regime label and to a normalised score in [-1, +1]. Output is a Thinking Card (see suite README).

How to run

python3 scripts/regime.py --input data.json --pretty
cat data.json | python3 scripts/regime.py

Reads macro (required) and optional mode/ticker/as_of. Returns score (-1..+1), confidence, rating (regime label), key_metrics.risk_multiplier, per-factor drivers, plain-language reasoning, and flags.

Try it now with the shared fixture:

python3 scripts/regime.py --input ../_fixtures/sample_input.json --pretty

Interpreting output

  • rating: risk_on (mult >=1.05), neutral (0.85–1.05), cautious (0.70–0.85), risk_off (<0.70).
  • key_metrics.risk_multiplier is the value downstream skills multiply into their risk budget — e.g. risk-manager sizes positions at base_risk * risk_multiplier.
  • flags: stale_macro appears when one or more macro fields are missing and confidence is capped accordingly — never a silent drop.

Notes

Factor weights, the multiplier→regime mapping, the score mapping, and how downstream skills consume the multiplier are documented in references/REGIME.md. Output is educational analysis only, never financial advice.

관련 스킬

Kaelio/ktx-ai-data-agents-mcp-context-skills

ktx is an executable context layer for data and analytics agents 🐙 Allow Claude Code, Codex, and any AI agent to query data accurately through MCP with skills, memory and a semantic layer

community

trailofbits/sarif-parsing

Parses and processes SARIF files from static analysis tools like CodeQL, Semgrep, or other scanners. Triggers on "parse sarif", "read scan results", "aggregate findings", "deduplicate alerts", or "process sarif output". Handles filtering, deduplication, format conversion, and CI/CD integration of SARIF data. Does NOT run scans — use the Semgrep or CodeQL skills for that.

community

AccioWork/.github

Organization profile & community health files for AccioWork — open-source e-commerce agent skills for product sourcing, market research, Shopify ops & more. Powered by Accio, the AI agent platform built for real business. ⭐ Star to follow updates → accio.com/work

community

Kaichera/sniff

🤖 Deploy self-hosted AI agents effortlessly using simple YAML configs, ensuring no vendor lock-in and full control over your AI workflows.

community

hyun2xyz/iiki

Wikibird research-to-HTML Agent Skill for Korean wiki-style explainers

community

davila7/scientific-slides

Build slide decks and presentations for research talks. Use this for making PowerPoint slides, conference presentations, seminar talks, research presentations, thesis defense slides, or any scientific talk. Provides slide structure, design templates, timing guidance, and visual validation. Works with PowerPoint and LaTeX Beamer.

community