四色卡片生成 Skill(通政司 + 监察院 + 丞相府)
SkillDocs & knowledgeTurns a parsed document into four color-coded cards: blue for facts, green for explanations, yellow for risks, and red for next actions. The result is an audit-ready breakdown that keeps what is known separate from what is assumed and what still needs to happen. It is the core analysis output of a structured analysis methodology.
Available today. Use it from your connected AI after setup.
No other account needed.
Add the skill, then give your AI a document it has already parsed and say what you want to get out of the analysis. Your AI will return the four cards.
Then ask your AI: use the 四色卡片生成 Skill(通政司 + 监察院 + 丞相府) skill
What your AI can do with it
- Sort the facts in a document onto blue cards
- Capture explanations on green cards
- Flag risks on yellow cards
- List next actions on red cards
- Shape the cards around the goal you describe
- Produce an audit-ready summary of a parsed document
What this skill tells your AI
The instructions your AI receives, as published by anbeime/skill in antinet-agentteams/skills/four-color-cards/SKILL.md and read by ahel’s review.
使用方式
- 由通政司 Worker 主调用,生成蓝卡(事实)/ 绿卡(解释)。
- 黄卡(风险)交由监察院复核过度声明;红卡(行动)交由丞相府补全策略建议。
- 四卡片统一经太史阁留痕,保证每张卡片可溯源。
输入(Input)
markdown:密卷房解析产出的结构化文档intent:用户意图 / 查询目标llm_available:LLM 是否可用(影响黄卡生成路径)
输出(Output)
blue_card:事实卡——可溯源的陈述,附来源片段green_card:解释卡——对事实的机制/背景说明yellow_card:风险卡——过度声明、不确定性与潜在偏差(经监察院复核)red_card:行动卡——下一步建议(经丞相府补全)
依赖(Dependencies)
- LLM API(生成蓝/绿/红卡)
- 过度声明检测规则集(监察院提供,用于黄卡)
- 解析置信度(来自 doc-parse,低置信度触发人工复核标记)
失败处理(Failure Handling)
- LLM 不可用 → 降级到规则引擎生成卡片,黄卡/红卡显式标注「未启用 LLM」。
- 监察院复核超时 → 黄卡暂以规则引擎结果交付,并标记
pending_review。 - 来源缺失 → 对应事实在蓝卡中标注「无来源」,不直接生成断言。
复用价值(Reuse Value)
- 方法论通用:科研分析、金融研报、法律文档分析均可套用四色卡片框架。
- 可审计性强:每张卡片带来源与生成方式,天然契合 Agent Infra 的可观测/审计评审维度。
复赛代码包执行(runnable package)
- 真实入口:
scripts/run_four_color_cards.py --stage {extract|review|propose} - 三个子任务映射:
extract→ 通政司comm.tongzhengsi.TongZhengSiAgent(蓝卡:事实抽取)review→ 监察院audit.jichayuan.JianChaYuanAgent(绿卡:Gap/解释)propose→ 丞相府strategy.chengxiangfu.ChengXiangFuAgent(红卡:行动建议)
- 运行示例:
python skills/four-color-cards/scripts/run_four_color_cards.py --stage extractpython skills/four-color-cards/scripts/run_four_color_cards.py --stage reviewpython skills/four-color-cards/scripts/run_four_color_cards.py --stage propose
- 产物:
examples/snse_survey/skill_outputs/four_color_<stage>.json - 溯源铁律:绿卡 cite 蓝卡、红卡 cite 绿卡/蓝卡,无来源不得入库(由 card_model 强制)。
Signals
- GitHub stars
- 7k
- Forks
- 628
- Last commit
- Sep 2026
ahel recommends instead
Advanced
- Catalog kind
- skill
- Gateway key
four-color-cards- Source
- github.com/anbeime/skill