second-pass-grasp

Full-text deep-read of a paper's Introduction, Method, and Results sections to draft the structured bundle (problem, method, key results with hedge levels, limitations), each field carrying a precise source anchor. Use this after first-pass-skim has classified the paper and drafted candidate angles — this is the main content-extraction pass of the reading pipeline.

跳到安装

仓库: yogsoth-ai/paper-reading
最近来源活动: 2026年8月6日 14:34
检测到的 SKILL.md 语言: 英语
星标: 1
分支: 0

安装方式

默认使用会先检查来源的 Prompt；你也可以切换为直接命令，或下载本地副本。

用 Codex 或 Claude 帮你安装复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。

直接命令不会经过审查 Prompt；运行前请先检查来源。

npx skills add https://github.com/yogsoth-ai/paper-reading --skill second-pass-grasp

命令会保持在同一行。复制前请横向滚动并检查完整内容。

想先保存到本地？可下载 SkillsMP 当前能够提供的文件。

检查来源文件

决定是否安装前，请先阅读 SKILL.md，以及 SkillsMP 当前展示的配套文件。

文件资源管理器

2 个文件

SKILL.md

来源说明 · 只读预览

返回搜索返回安装

angle-selection

Pick which candidate angle to write the article around, cross-checked against the verified bundle so the chosen angle is actually substantiated by the paper (not just appealing at the skim stage). Use this as the first step of drafting, after quality-assurance has passed, whenever you have candidate_angles from first-pass-skim and a verified bundle.

2026-08-06

audience-first-writing

Writing strategy that turns a verified paper bundle into a finished public-audience article — selecting an angle, applying a pre-set style constraint during drafting (never a post-hoc rewrite), and checking the result for drift against the bundle. Use this after quality-assurance has passed on the bundle — this is the final strategy of the paper-reading pipeline, producing the WeChat article itself.

2026-08-06

deep-read

Deep-reading strategy that turns a single specified academic paper into a structured, source-anchored bundle (problem, method, key results, limitations) ready for fact-checking and article drafting. Use this whenever the user names one specific paper (by arXiv ID, URL, or title) and wants it read, summarized, explained, or turned into content — this is the entry point of the paper-reading pipeline.

2026-08-06

查看这个仓库的全部 Skills

name	second-pass-grasp
description	Full-text deep-read of a paper's Introduction, Method, and Results sections to draft the structured bundle (problem, method, key results with hedge levels, limitations), each field carrying a precise source anchor. Use this after first-pass-skim has classified the paper and drafted candidate angles — this is the main content-extraction pass of the reading pipeline.
execution	subagent
prompt	./prompt.md
input	paper_ref (string), paper_type (string), skim_notes (string)
output	draft_bundle (dict), uncertain_fields (list of strings)
dependencies	{"sops":["spawn-agent","literature-research"]}