CLAUDE.mdA
CLAUDE.md from daylily-huang/scholarflow is a CLAUDE.md file: the standing instructions Claude Code reads in that repo.
mdr add daylily-huang/scholarflow/CLAUDE.md@git:20261022.17c766aPins git:20261022.17c766a in mdr.lock. Pin the fingerprint instead.
- Audit grade
- A, 14 of 14 checks passed
- Kind
- CLAUDE.md file
- Repository
- daylily-huang/scholarflow
- Path
CLAUDE.md- Versions recorded
- 3
- Latest version
- git:20261022.17c766a, committed Oct 22, 2026
- First version recorded
- Sep 12, 2026
- Size
- 7,207 bytes
- Repository stars
- 41
- License
- MIT
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
# CLAUDE.md This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository. ## 项目定位 ScholarFlow 是面向严谨科研的智能体文献全生命周期工作流套件（Agent Skills Suite），完整覆盖从假说推敲到文献调研的 **4 个核心技能**： 1. `research-idea-debate` — 研究构想与假说推敲（五类苏格拉底视角讨论、单轮单问交互协议、想法成熟度守卫 RAW→TESTABLE、独立反例质询与确定性分歧判定、查证缺口双向交接） 2. `literature-discovery-acquisition` — 文献系统发现、初筛与全文获取（OpenAlex 检索、双向引文滚雪球、商业库题录摄取、双评阅人 κ 一致性） 3. `literature-evidence-extraction` — 证据可信抽取与声明审计（Quote-First 逐字引句、0-10 相关度剪枝、E1-E4 溯源/强度解耦） 4. `literature-synthesis` — 学术争议发掘与跨文献综合（加权证据评价、非多数决共识梯队、Claim ID 门禁） 核心设计：**防幻觉**（结论锚定带页码的原文引句）、**零强制第三方依赖**（全部运行时逻辑基于 Python 3.9+ 标准库，可选 `pip install "scholarflow[pdf]"` / `.[dev]`）。 ## 独立单篇阅读 新增 `skills/paper-close-read`，独立于上述四项研究流程及shared引擎。用户提供单篇全文即可按其SKILL.md开始，不继承检索/裁定流程的执行深度提问。内容由宿主模型撰写；确定性代码仅保证结构/覆盖/交互。新能力状态见CAPABILITY_STATUS的独立阅读节；变更设计见RFC-018。通用版不改写黑麂项目原技能。 相关验证：`python -m unittest discover -s tests -p test_paper_reader.py -v`；`python skills/paper-close-read/scripts/selftest.py --work-dir <临时目录>`；`python scripts/rebuild_readers.py <阅读目录>`。真实文献结果在examples/paper-close-read；浏览器报告绑定HTML摘要。独立技能通过仓库分发；对外发布仍以用户授权为准。 ## 测试与质检命令 ```bash …
Read the whole file at its exact version.
How to install
mdr add daylily-huang/scholarflow/CLAUDE.md@sha256:ba3fad2a0accbffdThe line at the top of this page pins the label git:20261022.17c766a, 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_b3is67dx7fx4zskd)
0 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 3 versions of this file, between Sep 12, 2026 and Oct 22, 2026, about one every 20 days.
| version | committed | commit | size | audit | |
|---|---|---|---|---|---|
| git:20261022.17c766a latest | 2026-10-22 | 17c766a | 7,207 B | A | view · diff |
| git:20260912.48adfed | 2026-09-12 | 48adfed | 6,417 B | A | view · diff |
| git:20260912.b43a20e | 2026-09-12 | b43a20e | 6,290 B | A | view |
Audit of the latest version
- pass: Size between 200 bytes and 200 KB (7207 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
daylily-huang/scholarflow · 41 stars · license MIT · pushed 2026-11-02 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_b3is67dx7fx4zskd GET https://markdownregistry.com/api/v1/resolve?ref=daylily-huang/scholarflow/CLAUDE.md GET https://markdownregistry.com/api/v1/blob/ba3fad2a0accbffd3c8f3f98ea2ae46853ddf18dfea7e01fe4f1f54238e05a00
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: what a CLAUDE.md file is · keeping AGENTS.md and CLAUDE.md in sync · which agent file does what.
More from daylily-huang/scholarflow
Every file in daylily-huang/scholarflow