literature-evidence-extraction SKILL.md skillA
literature-evidence-extraction from daylily-huang/scholarflow is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.
mdr add daylily-huang/scholarflow/literature-evidence-extraction@git:20260914.c8e6b6bPins git:20260914.c8e6b6b in mdr.lock. Pin the fingerprint instead.
- Audit grade
- A, 17 of 17 checks passed
- Kind
- SKILL.md skill
- Repository
- daylily-huang/scholarflow
- Path
skills/literature-evidence-extraction/SKILL.md- Versions recorded
- 5
- Latest version
- git:20260914.c8e6b6b, committed Sep 14, 2026
- First version recorded
- Sep 12, 2026
- Size
- 27,845 bytes
- Repository stars
- 41
- License
- MIT
通用学科科研文献证据可信抽取与事实核验专业技能。严格恪守 Quote → Extract → Verify → (Optional) Interpret 铁律，从学术论文（PDF/全文）中按定制 Schema 抽取结构化参数与方法表。内置四级证据体系（E1-E4）、6 大证据状态标签、复杂多实验上下文隔离、表格/附录优先挖掘、高危字段 OCR 零容忍防护、既有结论 Claim 事实审计及伴生 JSON 双轨输出。.
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
# 学科文献证据抽取与事实核验专业技能 (literature-evidence-extraction) 本技能用于在严谨科研场景下，从用户提供的学术论文全文（PDF、文本或补充材料）中，按照指定字段进行**严格、可追溯、证据绑定、零臆测**的信息抽取与结论核验（Evidence-Bound Literature Extraction & Claim Auditing）。 > **核心哲学**： > 本技能是 **Evidence Extractor（证据抽取器）**，绝非 Summarizer（概述器）或 Explainer（解释器）。 > 它只回答：**“这篇论文实际上写了什么？”** > 绝不回答：**“按照领域常识，它应该是什么？”** > > 严厉执行总原则：**Quote → Extract → Verify → Interpret** > 严厉禁止反模式：**Read → Remember → Guess → Answer** > 核心承诺：**严禁捏造看起来合理的参数；仅在已检查原文且作者确实未提供时标注 `not_reported`（`NR`），未查或无全文分别标为 `unchecked` 或 `inaccessible`。** > > **`NR` 的精确口径（审查 F09）**：`NR` 只表示**原文已检查且作者未报告**。 > 以下情形**都不等于** `NR`，必须分别标注，不得合并： > > | 情形 | 正确标注 | 含义 | > |---|---|---| > | 拿不到全文 | `inaccessible` | 看不到，不是作者没写 | > | 有全文但该字段尚未检查 | `unchecked` | 没查，不是没报告 | > | 数据来自作者转引他人文献 | `cited_only`（`support_type=REFERENCED`） | 本文未自测，不得冒充本文结果 | > | 可由原文数据重算得出 | `derived`（`support_type=DERIVED`） | 附公式与原始输入 | > | 已检查全文、作者确实未报告 | **`not_reported`（= `NR`）** | 唯一可写 `NR` 的情形 | > > 引句与定位是否真实有效，另由**来源核验**维度判定（`verified` / `unverified` / `failed`）； > 命题方向另由 `support` / `challenge` / `boundary` / `context` 表达。 > 五个维度各自回答不同问题，**不得互相替代**（详见 `docs/CAPABILITY_STATUS.md`）。 > …
Read the whole file at its exact version.
How to install
mdr add daylily-huang/scholarflow/literature-evidence-extraction@sha256:eda452467530c25fThe line at the top of this page pins the label git:20260914.c8e6b6b, 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_xm2d6ctiyo4lzn2k)
0 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 5 versions of this file, between Sep 12, 2026 and Sep 14, 2026, more than one a day.
| version | committed | commit | size | audit | |
|---|---|---|---|---|---|
| git:20260914.c8e6b6b latest | 2026-09-14 | c8e6b6b | 27,845 B | A | view · diff |
| git:20260912.e331a30 | 2026-09-12 | e331a30 | 27,488 B | A | view · diff |
| git:20260912.2073350 | 2026-09-12 | 2073350 | 26,759 B | A | view · diff |
| git:20260912.48adfed | 2026-09-12 | 48adfed | 26,666 B | A | view · diff |
| git:20260912.8b2e85d | 2026-09-12 | 8b2e85d | 25,627 B | A | view |
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 (27845 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_xm2d6ctiyo4lzn2k GET https://markdownregistry.com/api/v1/resolve?ref=daylily-huang/scholarflow/literature-evidence-extraction GET https://markdownregistry.com/api/v1/blob/eda452467530c25fb46d825a2b77848ef735be20a05279e11264075c76023998
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.