ara-rigor-review skillA
ara-rigor-review is agent-read markdown (skill) from yogsoth-ai/de-anthropocentric-research-engine: 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.
Indexed from public GitHub and served as immutable, content-addressed versions. Install it pinned to an exact SHA-256 with the mdr CLI, and every file is verified against the hash recorded here before it reaches your agent. The deterministic audit below grades the latest version, and the same file always earns the same grade.
What the file says
# SOP: ARA Rigor Review **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? ## Preflight 先确认外部 `rigor-reviewer` skill 可 load。不可用则提示安装并**停下**。 ## Procedure 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): - D1 Evidence Relevance — 证据是否在**实质**上支撑每条 claim; - D2 Falsifiability Quality — 证伪标准是否有意义、可操作、范围合适; - D3 Scope Calibration — claim 是否恰好断言其证据所支撑的,不多不少; - D4 Argument Coherence — 是否从 problem→solution→evidence 逻辑闭合; - D5 Exploration Integrity — exploration tree 是否记录了真实研究过程(含失败); - D6 Methodological Rigor — 实验设计/baseline/ablation/报告是否到位。 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。 ## Output `ara/level2_report.json` + 一句话总结(grade + 最该关注的 finding),交付用户。
Read the whole file at its exact version.
How to install
mdr add yogsoth-ai/de-anthropocentric-research-engine/ara-rigor-review@v1.0.0mdr add yogsoth-ai/de-anthropocentric-research-engine/ara-rigor-review@sha256:ee6822832a6d7e06Pin to a label to follow the author's releases, or to a sha256 to freeze the exact bytes forever. Either way the resolved hash is written to mdr.lock, and mdr install reproduces it on any machine.
[](https://markdownregistry.com/a/art_bzhamkvh4hr2bep6)
1 badge views in 30 days
Versions
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 (2056 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
yogsoth-ai/de-anthropocentric-research-engine · 497 stars · license Apache-2.0 · pushed 2026-09-23 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_bzhamkvh4hr2bep6 GET https://markdownregistry.com/api/v1/resolve?ref=yogsoth-ai/de-anthropocentric-research-engine/ara-rigor-review GET https://markdownregistry.com/api/v1/blob/ee6822832a6d7e068bccd47f891614658c190788ed42ba3ab822589da983a912
Your agent 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.