ASP源码
PHP源码
.NET源码
JSP源码
DGR(决策级推理)是一种先进的治理协议,旨在将原始 LLM 输出转化为结构化、可审计的决策构件。通过强制执行符合架构验证的 JSON 格式,它确保每个 AI 生成的建议都包含关键上下文,例如明确的假设、识别的风险和内部一致性检查。这项技能填补了概率性 AI 推理与专业治理严格要求之间的空白。
使用像 DGR 这样的 Openclaw Skills 让团队能够为高风险决策维持清晰的纸面记录,确保 AI 辅助的工作流程对人类利益相关者保持透明且可审查。它专注于提高推理的过程质量、清晰度和可追溯性,而不仅仅是最终输出。
下载入口:https://github.com/openclaw/skills/tree/main/skills/sapenov/dgr
从源直接安装技能的最快方式。
npx clawhub@latest install dgr
将技能文件夹复制到以下位置之一
全局模式~/.openclaw/skills/
工作区
/skills/
优先级:工作区 > 本地 > 内置
将此提示词复制到 OpenClaw 即可自动安装。
请帮我使用 Clawhub 安装 dgr。如果尚未安装 Clawhub,请先安装(npm i -g clawhub)。
要在 Openclaw Skills 生态系统中使用 DGR,请确保该技能包在您的环境中已激活。您可以通过提供请求并指定模式来启动协议:
# 触发严格决策审计的示例
/dgr_strict "我们是否应该将主生产数据库迁移到无服务器架构?"
该技能依赖于 schema.json 和 prompt.md 文件,以确保所有输出都符合要求的治理标准。
DGR 技能将其治理数据组织成结构化的 JSON 格式。以下是用于这些构件的主要元数据分类:
| 字段 | 描述 |
|---|---|
assumptions |
被视为决策前提的明确条件或数据点数组。 |
risks |
识别潜在负面结果或不确定性的数组。 |
recommendation |
核心建议,包括理由和 review_required 布尔值。 |
consistency_check |
确认逻辑内部连贯性的自我评估文本。 |
mode |
用于生成记录的具体 DGR 模式(min、full 或 strict)。 |
name: dgr
description: Audit-ready decision artifacts for LLM outputs — assumptions, risks, recommendation, and review gating (schema-valid JSON).
homepage: https://www.clawhub.ai/sapenov/dgr
metadata:
clawdbot:
emoji: "??"
category: "reasoning"
Purpose: produce an auditable, machine?validated decision record for review and storage.
Slug: dgr · Version: 1.0.4 · Modes: dgr_min / dgr_full / dgr_strict · Output: schema-valid JSON
DGR is a reasoning governance protocol that produces a machine?validated, auditable artifact describing:
This skill is designed for high?stakes or review?required decisions where you want traceability and structured review.
dgr_min | dgr_full | dgr_strictThis skill does NOT guarantee:
DGR improves process quality (clarity, traceability, reviewability) — not outcome certainty.
Use when you need:
dgr_min, dgr_full, or dgr_strict.| Mode | Speed | Detail Level | Clarifications | Review Required | Use Case |
|---|---|---|---|---|---|
dgr_min |
Fastest | Minimal compliant output | Only critical gaps | Risk-based | Quick decisions, low stakes |
dgr_full |
Moderate | Fuller decomposition + alternatives | More proactive | Balanced | Standard decision support |
dgr_strict |
Slower | Conservative analysis | More questioning | Default on ambiguity | High-stakes, uncertain contexts |
A single JSON artifact matching schema.json.
Minimum acceptance criteria (see schema.json):
recommendation presentconsistency_check presentrecommendation.review_required = true.prompt.md — operational instructionsschema.json — output schema (stub aligned to DGR spec)examples/*.md — example inputs and outputsfield_guide.md — how to interpret DGR artifact fieldsdgr_min default).1.0.4 — Remove redundant CLAWHUB_SUMMARY.md; summary now sourced from SKILL.md front-matter.
1.0.3 — Tighten front-matter description for better conversion, add reasoning category, compress identity block for faster scanning.
1.0.2 — Add ClawHub front-matter metadata with emoji and homepage for improved discovery and presentation.
1.0.0 — Initial public release of DGR skill bundle with auditable decision reasoning framework, governance protocols, and structured output format.
Note: This is an opt?in reasoning mode. It is meant to be used alongside human decision?making, not as a replacement.