ESG Factor Engine
Paste the following prompt into your AI chat to install this skill:
Please install @user_89306994/esg-factor-engine using https://skillhub.cn/install/skillhub.md.
About this skill
Problem
ESG research often mixes ratings, news, policy, industry weights, and analyst judgment into one document, making it hard to trace which data is credible, which issues are material, and which signals warrant attention. The ESG Factor Engine skill structures that workflow into executable agent steps, so analysis is not reduced to a single composite score.
How it works
The skill is built on RealGreen AI's nine-agent architecture and uses scripts/full_workflow_v2.py to connect a 7-step pipeline with 8 human sign-off checkpoints:
- Credibility validation: cv_credibility_validator.py classifies sources as A, B, C, or D, supports cross-validation to promote B to A, and produces a CIQI index.
- Materiality assessment: si_strategic_interpreter.py uses MATERIALITY_MATRIX to cover 30+ sectors, including new energy, PV, lithium batteries, power, semiconductors, baijiu, coal, banking, and insurance.
- Risk and engagement: rsm_risk_signal_monitor.py monitors risk signals, while es_engagement_steward.py generates an engagement or stewardship plan.
- Human-in-the-loop: HumanAdvisor().sign(node, analyst_name, decision) records eight mandatory checkpoints, covering task scope, data provenance, dispute review, risk grading, trend interpretation, strategic alignment, investment recommendation, and compliance review.
Boundaries
It fits research support for single-stock analysis, portfolio diagnosis, and ESG score ranking. Outputs are for research reference only and do not constitute investment advice. Confirm that industry weights, data freshness, and compliance controls match internal requirements.
Use Cases
- During single-name ESG due diligence, use CV credibility, SI materiality, and RSM risk signals to draft a research workpaper for review.
- In portfolio ESG review, call diagnose_portfolio_esg from portfolio_analyst.py, trace data gaps, and record all eight HIA sign-off checkpoints and archive the decisions.
- When building an ESG score ranking, use esg_scorer.py's build_esg_score with sector weights and note credibility limits before research publication notes.
- During dispute review, apply CV levels and cross-validation to decide whether a B-grade source can be promoted to A grade.
Best For
- An ESG investment analyst conducting single-name due diligence who needs to check source credibility, sector materiality, and risk signals.
- A portfolio research assistant reviewing ESG risks who needs to diagnose holdings and log the eight HIA sign-off checkpoints.
- A research data analyst maintaining ESG rankings who needs to apply sector weights and flag data confidence gaps.
- A compliance reviewer validating disputed data who needs to test whether cross-validation can promote a B-grade source to A.
Related Skills
Based on Hengsheng Juyuan MCP financial data, it assesses equity, bond, commodity, and overseas markets and produces sourced risk reports with allocation guidance.
Applies a six-question industry-chain framework for structured fundamental analysis of sectors, profit pools, competition, ROIC, valuation, and domestic substitution.
Performs structured contract risk assessment, adds revision suggestions in the document, and generates a standalone review report.
A single-stock research framework that produces seven-dimension drafts, integrated analysis, scenario projections, and dual-track reference, with optional comparison and no investment advice.