paper-narrative SKILL.md skillA
paper-narrative from yichen-zju/claude-for-research is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.
mdr add yichen-zju/claude-for-research/paper-narrative@git:20261014.9f2a5e0Pins git:20261014.9f2a5e0 in mdr.lock. Pin the fingerprint instead.
- Audit grade
- A, 17 of 17 checks passed
- Kind
- SKILL.md skill
- Repository
- yichen-zju/claude-for-research
- Path
claude/skills/paper-narrative/SKILL.md- Versions recorded
- 1
- Latest version
- git:20261014.9f2a5e0, committed Oct 14, 2026
- Size
- 5,225 bytes
- Repository stars
- 10
- License
- none declared
Shape the scientific story across a manuscript, abstract, figures, and evidence — choose the main narrative line, organize claims/evidence/section order/figure order, and fix the conclusion's landing point. Use when a task asks for paper structure, figure order, argument flow, narrative mainline selection, missing analyses, or manuscript revision strategy.
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
# Paper Narrative 职责：为全文选一条论证主线，组织主张、证据、章节推进与图序，并确定 结尾落点。产出一份**共享的轻量叙事计划**，供 intro-drafter、 paper-writing 与结尾写作共用——不让每个技能各自产生一套故事。 详细指导见 `references/story-patterns.md`（六种科学叙事范式 + 主线/结尾落点对应表）与 `references/conventional-structures.md` （常规叙事骨架：技术类六段、benchmark 六段，及范式 × 骨架组合规则）。 本文件只做选择、调用与交接。 ## Workflow ### Step 0: 读写叙事计划（共享主线） 读写 `outputs/.plans/<slug>.md` 的叙事计划段（没有则建立）。计划回答 七个问题，按任务轻重裁剪，不变成必填长表单： 1. 核心问题：读者需要理解或解决什么？ 2. 现有认识的缺口：已有方法、解释或评测具体遗漏了什么？ 3. 核心发现：我们的工作建立了什么新认识？ 4. 贡献与意义：因此新增了什么能力、解释、测量方式或设计原则？ 5. 主线与骨架：哪种范式立场最适合承载这项贡献（都不适配时允许其他 清晰叙事）？按哪种行文骨架组织（技术类方法论论文默认常规六段； benchmark 论文默认 benchmark 六段；组合规则见 conventional-structures.md）？ 6. 主张—证据对应：关键主张分别由哪些结果、证明、分析或图支撑？ 7. 章节推进与结尾落点：每一部分回答什么问题，最后希望读者记住什么？ 研究尚未完成时，明确区分**待检验的想法**与**已经成立的发现**；结果 变化后允许调整主线并更新计划。 **证据状态纪律（防补造、防自贬）**： - 计划与建议中只写材料提供了的事实。**禁止补造**材料没有的"前人缺 陷""已完成消融""已有测量"——需要但缺失的证据记为"待核查/可选追加 分析"，不得记为已有。 - **已观察的事实如实保留，只限制其因果解释**：观察到分布差异（如 p<0.01），差异本身是已成立证据，"它是不是原因"才是待检验的——把 观察整体降级为"待检验"是不必要的自我削弱。 - 状态标签（已有/待核查/可选追加）只出现在计划的证据表里，不扩散 成论文每段的免责声明。 ### Step 1: 选择叙事主线与行文骨架 读 `references/story-patterns.md`，按贡献的真实形态选一个最适合的 主线——六种范式之一**或其他适合的贡献主线**（必要时融合；都不 适配时允许任何清晰的证据叙事，如纯效率改进就直接按效率收益组织）。 …
Read the whole file at its exact version.
How to install
mdr add yichen-zju/claude-for-research/paper-narrative@sha256:b630c63dfb404b13The line at the top of this page pins the label git:20261014.9f2a5e0, 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_qr6zktzty5r64w6h)
1 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 1 version of this file, committed on Oct 14, 2026.
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 (5225 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
yichen-zju/claude-for-research · 10 stars · license none declared · pushed 2026-10-21 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_qr6zktzty5r64w6h GET https://markdownregistry.com/api/v1/resolve?ref=yichen-zju/claude-for-research/paper-narrative GET https://markdownregistry.com/api/v1/blob/b630c63dfb404b13acf1ca2f3e13f9e07666fc80dea8e93382d7cc1394dffa8e
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.
More from yichen-zju/claude-for-research
Every file in yichen-zju/claude-for-research