literature-synthesis SKILL.md skillA
literature-synthesis 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-synthesis@git:20260912.48adfedPins git:20260912.48adfed 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-synthesis/SKILL.md- Versions recorded
- 5
- Latest version
- git:20260912.48adfed, committed Sep 12, 2026
- First version recorded
- Sep 6, 2026
- Size
- 17,003 bytes
- Repository stars
- 41
- License
- MIT
通用学科科研文献跨篇证据综合分析、学术争议发掘与学派图谱技能。对标 PaperQA2 思路，严格遵循 Claims-first, narrative-later 原则。内置 Stage 0 Grill-Me 交互门禁、9 大学术争议类型诊断（Type A~I）、6 级共识度评级与适用边界标定、学派与知识演化图谱、独创 Devil's Advocate（反方辩驳挑刺）与独立 Gatekeeper、支持按任务动态加载跨学科 Domain Lens（不得将任何单一学科 Profile 设为默认执行本体）、闭环反馈上游 Search/Extraction Gap 任务包，以及争议驱动型综述（Narrative Review）自动生成能力。.
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
# 学科文献综合分析与学术争议发掘专业技能 (literature-synthesis) 本技能用于在严谨科研场景下，基于多篇已经验证的文献证据单元（优先接收 `literature-evidence-extraction` 的结构化证据表或本地文献集合），进行**跨文献证据对撞、学术争议深度发掘、学派与方法学演进分析、共识边界标定与争议驱动型综述生成**（Cross-Study Evidence Grounding, Controversy Mapping & Paradigm Synthesis）。 > **核心哲学**： > 本技能是 **Evidence-Grounded Scientific Synthesizer（证据锚定型科学综合分析器）**，绝非“流水账文献总结器”，更不是“按论文篇数民主投票的统计工具”。 > > 严厉执行总原则：**Claims first, narrative later.** > 严厉禁止反模式：**Read papers → immediately write review prose (流水账综述).** > 核心任务链：**Evidence units → Claim extraction → Normalization → Clustering → Agreement/Conflict detection → Methodological diagnosis → School identification → Evidence weighting → Consensus boundary → Knowledge gaps → Controversy-driven narrative.** --- ## ⚡ 上下文预算与按需渐进加载准则 (Progressive Context Loading Protocol) > [!CAUTION] > **统一执行深度底线规则 (Execution Depth Core Rule)**： > 执行前独立确认 `execution_depth`；研究目标不能替代深度选择。未指定且无有效配置时必须展示快速／标准／深度的工作范围与资源差异。未确认不得启动研究执行。下游沿用同一运行的已确认配置。所有档位保留证据和审计底线；预算不足时输出部分结果及待办，不自动扩额。 > [!CAUTION] > **严禁全量一次性预加载**：本 Skill 包含 23 个系统模块。在触发激活时，**绝对禁止**一次性通读 `references/`、`role/`、`examples/` 或 `assets/` 中的所有文件。Agent 必须严格遵守以下阶段化按需读取策略，严守上下文预算！ …
Read the whole file at its exact version.
How to install
mdr add daylily-huang/scholarflow/literature-synthesis@sha256:da2c040133de62d0The line at the top of this page pins the label git:20260912.48adfed, 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_dfijdvqrio5twagb)
0 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 5 versions of this file, between Sep 6, 2026 and Sep 12, 2026, about one every day.
| version | committed | commit | size | audit | |
|---|---|---|---|---|---|
| git:20260912.48adfed latest | 2026-09-12 | 48adfed | 17,003 B | A | view · diff |
| git:20260910.f1f2f40 | 2026-09-10 | f1f2f40 | 17,024 B | A | view · diff |
| git:20260908.2c54c02 | 2026-09-08 | 2c54c02 | 17,024 B | A | view · diff |
| git:20260907.675920c | 2026-09-07 | 675920c | 16,153 B | A | view · diff |
| git:20260906.2d1aa87 | 2026-09-06 | 2d1aa87 | 16,138 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 (17003 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_dfijdvqrio5twagb GET https://markdownregistry.com/api/v1/resolve?ref=daylily-huang/scholarflow/literature-synthesis GET https://markdownregistry.com/api/v1/blob/da2c040133de62d03f08965acbbd876cb53223f227db62fda5228a70af98ef7b
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.