four-color-cards

Four-Color Card Generation Skill (Tongzhengsi + Jianchayuan + Chengxiangfu)

How to Use

• Mainly invoked by the Tongzhengsi Worker to generate the blue card (facts) / green card (explanation).
• The yellow card (risk) is handed to the Jianchayuan for review of overclaiming; the red card (action) is handed to the Chengxiangfu to complete strategic recommendations.
• The four cards are uniformly recorded by the Taishige to ensure each card is traceable.

Input

• markdown: Structured document produced by Mijuanfang parsing
• intent: User intent / query objective
• llm_available: Whether the LLM is available (affects the yellow card generation path)

Output

• blue_card: Fact card—traceable statements, with source snippets
• green_card: Explanation card—mechanism/background explanation of the facts
• yellow_card: Risk card—overclaiming, uncertainty, and potential bias (reviewed by the Jianchayuan)
• red_card: Action card—next-step recommendations (completed by the Chengxiangfu)

Dependencies

• LLM API (generates blue/green/red cards)
• Overclaiming detection rule set (provided by the Jianchayuan, used for the yellow card)
• Parsing confidence (from doc-parse; low confidence triggers a manual review flag)

Failure Handling

• LLM unavailable → degrade to the rule engine for card generation, with the yellow/red cards explicitly marked "LLM not enabled".
• Jianchayuan review timeout → the yellow card is temporarily delivered using the rule engine result, and marked pending_review。
• Missing source → the corresponding fact is marked "no source" in the blue card, and no assertion is generated directly.

Reuse Value

• Methodology is general: scientific research analysis, financial research reports, and legal document analysis can all apply the four-color card framework.
• Strong auditability: each card carries its source and generation method, naturally fitting the observability/audit review dimensions of Agent Infra.

Semifinal code package execution (runnable package)

• Real entry point:scripts/run_four_color_cards.py --stage {extract|review|propose}
• Mapping of the three subtasks:
  • extract → Tongzhengsi comm.tongzhengsi.TongZhengSiAgent(blue card: fact extraction)
  • review → Jianchayuan audit.jichayuan.JianChaYuanAgent(green card: Gap/explanation)
  • propose → Chengxiangfu strategy.chengxiangfu.ChengXiangFuAgent(red card: action recommendations)
• Run example:
  • python skills/four-color-cards/scripts/run_four_color_cards.py --stage extract
  • python skills/four-color-cards/scripts/run_four_color_cards.py --stage review
  • python skills/four-color-cards/scripts/run_four_color_cards.py --stage propose
• Artifacts:examples/snse_survey/skill_outputs/four_color_<stage>.json
• Iron rule of traceability: the green card cites the blue card, and the red card cites the green/blue cards; nothing may be stored without a source (enforced by card_model).