survey synthesis
综合分析 — 读取所有单篇论文分析，用 LLM 合成面向实验实现的领域报告（SOTA / 瓶颈 / 创新 / 复现方案 / Reflection 风险点 / Coder 交接清单）。
Skill by yaleyoou
Install
Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.
npx agentmarket install skill/yaleyoou-survey-synthesis
Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.
Get the weekly diff
The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.
About
Use cases: ml, research
Reviews
Write a reviewNo reviews yet. Installed it? Reviews come from verified installers only. How reviews work
Permissions
What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.
- Tools
- No tools found
- Secrets
- None asked for
- Install scripts
- None found
- Runs as
- Python package
Network hosts it talks to 1
codeload.github.com· found in install command
Files it touches
~/.claude/skills/survey-synthesis
What's inside
- Skill name
survey synthesis- Description
- 综合分析 — 读取所有单篇论文分析，用 LLM 合成面向实验实现的领域报告（SOTA / 瓶颈 / 创新 / 复现方案 / Reflection 风险点 / Coder 交接清单）。
- License
- unknown
- Instructions
- 77 lines in SKILL.md · view on GitHub
Before installing
- Ships executable scripts
Agent Skills spec issues
- name: only lowercase letters, digits and single hyphens allowed
- name: "survey synthesis" does not match folder "survey-synthesis"
Files (2)
- SKILL.md
- survey_synthesis.py · scripts/
The license isn't open source, so the instructions aren't shown here. Read SKILL.md on GitHub
More from yaleyoou/Auto-Sci-Find-MutiAgent
- 0.510score
tavily-search
yaleyoou
Web search via Tavily API (alternative to Brave).
SkillCFreshness: C★ 3Claude Code +9 - 0.508score
experiment-tracker
yaleyoou
结构化实验记录与对比 — 记录每次实验的命令、超参数、git commit、GPU 信息、自动提取指标，支持 A/B 对比。
SkillCFreshness: C★ 3Claude Code +9 - 0.508score
result-evaluator
yaleyoou
复现结果评估 — 从论文分析中提取声称指标，与实验实际结果对比，用 LLM 给出复现评估（full/partial/failed）。
SkillCFreshness: C★ 3Claude Code +9 - 0.508score
code-profiler
yaleyoou
Python 性能分析 — cProfile 运行脚本，解析热点函数，自动识别瓶颈（数据加载/计算/I/O），生成分析报告。
SkillCFreshness: C★ 3Claude Code +9 - 0.505score
env-bootstrapper
yaleyoou
一键环境搭建 — 检测项目类型，创建虚拟环境，安装依赖，验证模块导入，锁定版本快照。
SkillCFreshness: C★ 3Claude Code +9 - 0.504score
plan_queries
yaleyoou
为指定领域生成结构化论文检索词，每个维度输出两套查询——学术 API 专用（queries）和 Tavily 网页搜索专用（tavily_queries）。
SkillCFreshness: C★ 3Claude Code +9 - 0.500score
paper search
yaleyoou
搜索并汇集论文。支持 queries-file 模式（读取 plan_queries 输出，一次性全源搜索）和单 query 模式。
SkillCFreshness: C★ 3Claude Code +9 - 0.497score
ref expand
yaleyoou
从筛选后的高相关论文出发，获取其参考文献列表，去重后生成可再次筛选的扩展论文池
SkillCFreshness: C★ 3Claude Code +9 - 0.497score
screen paper
yaleyoou
两阶段论文筛选 — 启发式粗筛 + LLM 精筛。读取搜索结果的 JSON，输出带相关性评分的筛选结果。
SkillCFreshness: C★ 3Claude Code +9 - 0.489score
paper-analysis
yaleyoou
This skill should be used when the user asks to deeply read parsed paper Markdown, analyze each paper with an LLM, find paper reviews or GitHub/code links via…
SkillCFreshness: C★ 3Claude Code +9 - 0.481score
pdf fetch
yaleyoou
This skill should be used when the user asks to download paper PDFs, fetch PDFs for screened papers, validate PDF MIME/size/readability, or produce…
SkillCFreshness: C★ 3Claude Code +9 - 0.481score
pdf parse
yaleyoou
This skill should be used when the user asks to parse, OCR, extract, or convert PDF files in a folder into Markdown, including "PDF to MD", "parse PDFs"…
SkillCFreshness: C★ 3Claude Code +9
Signals
- Stars
- 3
- Forks
- 0
- Open issues
- 0
- Last commit (this folder)
- Jun 8, 2026 (4 months ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- License unknown
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from yaleyoou
- 0.510score
tavily-search
yaleyoou
Web search via Tavily API (alternative to Brave).
SkillCFreshness: C★ 3Claude Code +9 - 0.508score
experiment-tracker
yaleyoou
结构化实验记录与对比 — 记录每次实验的命令、超参数、git commit、GPU 信息、自动提取指标，支持 A/B 对比。
SkillCFreshness: C★ 3Claude Code +9 - 0.508score
result-evaluator
yaleyoou
复现结果评估 — 从论文分析中提取声称指标，与实验实际结果对比，用 LLM 给出复现评估（full/partial/failed）。
SkillCFreshness: C★ 3Claude Code +9 - 0.508score
code-profiler
yaleyoou
Python 性能分析 — cProfile 运行脚本，解析热点函数，自动识别瓶颈（数据加载/计算/I/O），生成分析报告。
SkillCFreshness: C★ 3Claude Code +9 - 0.505score
env-bootstrapper
yaleyoou
一键环境搭建 — 检测项目类型，创建虚拟环境，安装依赖，验证模块导入，锁定版本快照。
SkillCFreshness: C★ 3Claude Code +9 - 0.504score
plan_queries
yaleyoou
为指定领域生成结构化论文检索词，每个维度输出两套查询——学术 API 专用（queries）和 Tavily 网页搜索专用（tavily_queries）。
SkillCFreshness: C★ 3Claude Code +9
Cite this page
survey synthesis skill. Agent Mart. https://agentmart.dev/skills/yaleyoou-survey-synthesis (last updated 2026-10-24)