four-color-cards SKILL.md skillA
four-color-cards from anbeime/skill is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.
mdr add anbeime/skill/four-color-cards@git:20260902.d0fbb12Pins git:20260902.d0fbb12 in mdr.lock. Pin the fingerprint instead.
- Audit grade
- A, 17 of 17 checks passed
- Kind
- SKILL.md skill
- Repository
- anbeime/skill
- Path
antinet-agentteams/skills/four-color-cards/SKILL.md- Versions recorded
- 1
- Latest version
- git:20260902.d0fbb12, committed Sep 2, 2026
- Size
- 2,953 bytes
- Repository stars
- 8,334
- License
- none declared
基于解析后的文档与用户意图，生成四色卡片——事实蓝卡、解释绿卡、风险黄卡、行动红卡，是八官署方法论的核心分析输出。.
Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.
What the file says
# 四色卡片生成 Skill（通政司 + 监察院 + 丞相府）
## 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 extract`
…Read the whole file at its exact version.
How to install
mdr add anbeime/skill/four-color-cards@sha256:d218b987184cb27cThe line at the top of this page pins the label git:20260902.d0fbb12, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.
[](https://markdownregistry.com/a/art_7rofot3hyw5dfrml)
4 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 1 version of this file, committed on Sep 2, 2026.
Audit of the latest version
- pass: Frontmatter block present
- pass: Frontmatter declares a name
- pass: Frontmatter declares a description
- pass: Size between 200 bytes and 200 KB (2953 bytes)
- pass: No zero-width or bidi control characters
- pass: No instruction hidden inside an HTML comment
- pass: No link to an exfiltration or paste host
- pass: No credential-shaped string
- pass: No instruction to send local credentials anywhere
- pass: No text hidden with inline styles
- pass: No prompt-injection phrasing
- pass: No curl or wget piped into a shell
- pass: No recursive delete of root, home or parent
- pass: No instruction to read or print local credentials
- pass: No base64 blob over 200 characters
- pass: No link to a raw IP address
- pass: No script tag
Source
anbeime/skill · 8,334 stars · license none declared · pushed 2026-10-19 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_7rofot3hyw5dfrml GET https://markdownregistry.com/api/v1/resolve?ref=anbeime/skill/four-color-cards GET https://markdownregistry.com/api/v1/blob/d218b987184cb27cbd84fdc1306d8fb38774b6b993d6ff7c3a5bd737b9e45478
Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.
Guides: the SKILL.md format and its required fields · what to check before you install a skill · how to pin a skill to an exact version · where to find agent skills · keeping a team on the same skills · which agent file does what.