formated-results
Closing skill for the research-executor, loaded as the last step of formated-specs. Summarize the design just produced into one research-result JSON fenced…
SOP: Run the external ARA rigor-reviewer (Seal Level 2, six-dimension semantic review) over ../ara/ and pass its level2_report.json to the user
$ npx -y skills add yogsoth-ai/de-anthropocentric-research-engine --skill ara-rigor-review --agent claude-codeHow it fires
How this skill gets triggered: by you, by Claude, or both.
/ara-rigor-reviewContext preview
The summary Claude sees to decide when to auto-load this skill.
SOP: Run the external ARA rigor-reviewer (Seal Level 2, six-dimension semantic review) over ../ara/ and pass its level2_report.json to the user
name: ara-rigor-review description: 'SOP: Run the external ARA rigor-reviewer (Seal Level 2, six-dimension semantic review) over ../ara/ and pass its level2_report.json to the user' version: 1.0.0 category: ara-from-context type: sop campaign: ara-from-context input: A populated ara/ directory (Level 1 passed) output: ara/level2_report.json (grade + D1–D6 + findings) dependencies: skills: - rigor-reviewer
**Key question**: 这份 ARA 的认识论严谨度如何?逻辑弧在结构上闭合了吗?
先确认外部 `rigor-reviewer` skill 可 load。不可用则提示安装并**停下**。
1. **跑 Level 2**:`Skill` load **rigor-reviewer**,传 `<artifact_dir>` = `../ara/`。 它对 ARA 跑六维语义审查(全是要读懂 + 推理的语义检查,不是结构校验):
2. **产物**:`rigor-reviewer` 在 artifact 根目录写 `level2_report.json` (每维 1–5 分 + strengths/weaknesses/suggestions + severity 排序 findings + overall grade + 给作者的问题)。
3. **D5 低分不是错误,是"探索素材不足"信号。** 透传给用户,由用户决定是否回 `context-exploring` 补打捞过程线。**本 SOP 不自动循环。**
> 注意:`rigor-reviewer` 的 D1–D6 是 **ARA 自己的**维度,与 DARE 的 D1–D5 评判 > 标准是两套东西,不要混。本 SOP 只透传 ARA 的报告,不施加 DARE 的 D1–D5。
`ara/level2_report.json` + 一句话总结(grade + 最该关注的 finding),交付用户。
The complete research orchestration system for AI-native science. What It Does Design Philosophy Architecture (v3.2.2) Quick Start Configuration Roadmap License DARE is not a tool that helps you do research. It is the researcher.
Repo: yogsoth-ai/de-anthropocentric-research-engine
Closing skill for the research-executor, loaded as the last step of formated-specs. Summarize the design just produced into one research-result JSON fenced…
Spec-slot skill for the research-executor. Emit the 4-layer DARE orchestration of the assigned topic as one research-graph JSON fenced block in your reply.…
Loss-1 judge (codex role). Given one sample's de-identified dialogue and its PolicyCard, decide axis-by-axis whether the user-simulator enacted the card's…
Loss-2 judge (codex role). Over one topic's 6 shuffled research-design samples, pairwise-rank by quality using the D1–D5 standard. Emit the pairwise log; the…
The optimizer brain for the ladder-foundry pretraining loop. Runs the two-level nested batch loop, delegates gating to gate_eval, attributes a failing batch to…
Tactic: Extract atomic units from one paper and score how much of a caller-supplied summary covers. Use for ACU-style binary or Nugget-style ternary recall…