Read arXiv Paper
karpathy/nanochat
Fetches the TeX source of an arXiv paper from its URL, reads it and writes a markdown summary tied to the nanochat project.
Grant Master 文献调研阶段的多源检索、两遍筛选、开放全文获取和元数据合并方法. An agent skill from dashbear-ai/grant-master.
Install Academic Search
$ npx skills add dashbear-ai/grant-master --skill academic-search -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install dashbear-ai/grant-master academic-search --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/dashbear-ai/grant-master.git skills-src && mkdir -p .claude/skills && cp -r skills-src/references/academic-search .claude/skills/academic-search && rm -rf skills-srcUse ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.
Claude Code skills documentation · loads skills from .claude/skills/
Install the "academic-search" agent skill from https://github.com/dashbear-ai/grant-master/tree/main/references/academic-search into .claude/skills/academic-search/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "academic-search", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/dashbear-ai/grant-master/tree/main/references/academic-searchType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add dashbear-ai/grant-master --skill academic-search -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install dashbear-ai/grant-master academic-search --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/dashbear-ai/grant-master.git skills-src && mkdir -p .agents/skills && cp -r skills-src/references/academic-search .agents/skills/academic-search && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "academic-search" agent skill from https://github.com/dashbear-ai/grant-master/tree/main/references/academic-search into .agents/skills/academic-search/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "academic-search", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add dashbear-ai/grant-master --skill academic-search -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install dashbear-ai/grant-master academic-search --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/dashbear-ai/grant-master.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/references/academic-search .cursor/skills/academic-search && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "academic-search" agent skill from https://github.com/dashbear-ai/grant-master/tree/main/references/academic-search into .cursor/skills/academic-search/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "academic-search", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/dashbear-ai/grant-master.git --path references/academic-search--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add dashbear-ai/grant-master --skill academic-search -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install dashbear-ai/grant-master academic-search --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/dashbear-ai/grant-master.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/references/academic-search .gemini/skills/academic-search && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "academic-search" agent skill from https://github.com/dashbear-ai/grant-master/tree/main/references/academic-search into .gemini/skills/academic-search/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "academic-search", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install dashbear-ai/grant-master academic-searchInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add dashbear-ai/grant-master --skill academic-search -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/dashbear-ai/grant-master.git skills-src && mkdir -p .github/skills && cp -r skills-src/references/academic-search .github/skills/academic-search && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "academic-search" agent skill from https://github.com/dashbear-ai/grant-master/tree/main/references/academic-search into .github/skills/academic-search/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "academic-search", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add dashbear-ai/grant-master --skill academic-search -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install dashbear-ai/grant-master academic-search --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/dashbear-ai/grant-master.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/references/academic-search .opencode/skills/academic-search && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "academic-search" agent skill from https://github.com/dashbear-ai/grant-master/tree/main/references/academic-search into .opencode/skills/academic-search/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "academic-search", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
Facts
- Skill name
academic-search- GitHub stars
- 126
- Token cost
- ~758 tokens
- SKILL.md length
- 168 words
- Files
- 34
- Skills in repo
- 2
- Repo updated
- First seen
- Licence
- MIT
At a glance
Grant Master 文献调研阶段的多源检索、两遍筛选、开放全文获取和元数据合并方法. An agent skill from dashbear-ai/grant-master.
- Tasks that involve Academic paper search
- SKILL.md covers 从问题到检索计划, 两遍检索与全文, 合并与可追溯交付 and 按需参考
- Calls python3; reaches doi.org
What it does
Academic Search is an agent skill from dashbear-ai/grant-master. Grant Master 文献调研阶段的多源检索、两遍筛选、开放全文获取和元数据合并方法。
Its SKILL.md is about 760 tokens, which your agent loads only when the skill is triggered. The skill folder holds 36 other files (for example `NOTICE.md`, `README.md` and `api-cookbook.md`).
It sits in Research & Science, covering Academic paper search. The repository describes itself as: 中文项目申请书全流程写作工具链 Grant-Master，支持课题理解、文献调研、论文精读、方案收敛、大纲规划、正文写作、审阅与 docx 输出。 The licence is MIT.
When your agent uses it
- Tasks that involve Academic paper search
Example prompts
- “/academic-search”
Requirements
- Python 3
What it can do on your machine
Read from SKILL.md and the folder at commit 23c4948. It shows what the files ask for, not the result of running them.
Tool permissions
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
Runs code
Shell commands in SKILL.md call:
python3
From the folder's file list and the shell code blocks in SKILL.md.
Network
Hosts in commands or code, which the agent is likely to contact:
doi.org
Also links to:
github.com
From URLs in SKILL.md, links to its own repository left out.
Credentials
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Context cost
Academic Search loads about 758 tokens when it runs. Until then it costs about 15 tokens; SKILL.md has 168 words of instructions outside code blocks.
Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.
Safety
Auto-check passed
The automated check found no risky patterns in SKILL.md.
Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.
SKILL.md
The full file from dashbear-ai/grant-master at commit 23c4948, republished under its MIT licence (© dashbear-ai). 168 words, ~758 tokens.
Download SKILL.mdSave it as
.claude/skills/academic-search/SKILL.md (or your agent's skills folder). This skill also uses 33 other files; get the full folder from GitHub.- name
- academic-search
- description
- Grant Master 文献调研阶段的多源检索、两遍筛选、开放全文获取和元数据合并方法。
Grant Master 学术检索
来源：参考并改编自 ustc-ai4science/academic-search，MIT，Copyright (c) 2026 Chengmingyue。本项目检索协议、站点经验和工具从 Grant Master 提交 34e28f7 恢复；许可全文与改编范围见 NOTICE.md。
本方法是五阶段中的文献调研执行规则，由 auto 调用。gm method --project ID 返回本入口和 完整搜索协议，并绑定内容回执；先读最新用户修改，再研究。协议涉及的参考路径以插件根目录为准，研究输出以 context.root 为准，不能写进插件目录。
从问题到检索计划
读取课题准备、用户最新输入、总字数、现有文献及最新视角，确定本轮希望支持或推翻的问题。首轮形成计划，后续只补影响方案判断的证据缺口。将可读计划通过 gm publish 保存为 stage=1、id=research-plan。
每个 query 记录 query_id、问题、同义词/缩写、学科、平台、年份范围、纳入/排除标准、目标数量。先读对应 disciplines 文件，再按任务读取 API 与 site-patterns；无需把整个目录塞入上下文。按研究对象、体量及用户要求设定范围，不能用机械数量替代相关性。
两遍检索与全文
第一遍轻量获取题名、作者、年份、venue、引用数及采集来源/日期、稳定链接、开放全文状态，分重要和一般文献。第二遍针对核心论文核验摘要、全文、代码与 BibTeX。保留代表作、新工作和相反证据；实际无法达到目标时记录检索范围及不足，不补造条目。
默认由当前 AI 执行并合并独立 API 请求；没有必须创建的专用 worker。只有用户要求或当前任务明确允许且独立子任务值得分工时，才按有限批次分派。任务说明只传目标、输入输出路径和筛选条件，返回摘要及文件路径，不重复粘贴论文正文。
合法 OA PDF 用 ../../scripts/academic-search/oa-pdf-download.mjs 下载至 <项目>/literature/papers/；输入用 metadata-schema.md 定义的 JSON results。访问受限则保留 DOI/摘要和状态。用户提供的本地论文原件也先发布为 stage=1 的 PDF 资产，再用 paper 的 pdfId 关联。CDP 工具仅在当前宿主允许、且确需该访问方式时使用；可用的内置浏览器或 API 不要求额外启动代理。
合并与可追溯交付
以 DOI、arXiv ID、规范标题和年份依次去重，保留所有 query_id 与来源；相关性优先，再比较证据质量、venue、引用及时间，不混用不同来源引用计数。
每轮在 <项目>/literature/search/round-N/ 保存 search_summary.md、candidate_papers.md、search_results.json、download_queue.json（下载 manifest）。使用 gm publish stage=1 注册这些报告；逐篇使用 gm paper 登记题名、作者、年份、sourceUrl（DOI 或发表页）、pdfId 与 reportId，再 publish 对应阅读报告。paper 不接受直接 PDF 路径。所有路径显式传项目内路径，更新已有报告必须使用其版本。JSON 是检索结果，不能作为工作台状态文件写入。
PDF 与论文登记示例（将 <项目绝对路径> 替换为 context.root；ID 在项目内唯一）：
先将以下 JSON 保存到项目内参数文件，再执行 python3 <插件根>/workbench/gm.py publish --project ID --json <参数文件>。source 是项目 downloads 候选目录中尚未登记的本地文件，path 是不同的、尚未存在的目标路径；已由扫描登记的 PDF 应复用 context.docs 中的 ID，不能再用新 ID 重复登记同一路径。
{"id":"pdf-example","stage":1,"title":"论文原文","path":"literature/papers/example.pdf","source":"<项目绝对路径>/downloads/example.pdf","base_revision":null}随后用以下参数执行 gm.py paper --project ID --json <参数文件>：
{"id":"paper-example","title":"论文题名","authors":"作者姓名","year":"2026","venue":"发表来源","sourceUrl":"https://doi.org/实际DOI","pdfId":"pdf-example","reportId":"reading-example","status":"待精读"}最后通过 gm.py publish --project ID --id reading-example --stage 1 --file <阅读报告.md> 发布阅读报告；已有报告附带 --base 当前版本。无全文时省略 pdfId，并明确摘要证据范围。
完成检索后继续按本阶段研究经验精读与综合，通过 publish id=perspective 更新最新判断。只有实际达到该阶段资料要求才调用 finish。遇到研究方向、范围或全文缺口需要用户决策，向统一待办中心投递并等待，用户拒绝不视为确认。
按需参考
- search-protocol.md：检索步骤、筛选、下载与核实，method 一并返回。
- metadata-schema.md：字段、去重、下载清单与引用导出。
- api-cookbook.md：官方 API 调用模板。
- disciplines/：学科平台、术语和证据规则。
- site-patterns/：目标站点经验；运行前确认时效，不把历史接口可用性当作事实。
- venue-rankings.md、rankings/：按学科核验评级，不把 CS 分级套到其它领域。
- workflows/：用户需要系统综述时读取。
- cdp-api.md：使用可选 CDP 工具时读取。
© dashbear-ai, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
Files
SKILL.md and 33 other files in references/academic-search of dashbear-ai/grant-master.
- SKILL.md
- LICENSE
- NOTICE.md
- README.md
- api-cookbook.md
- cdp-api.md
- disciplines/README.md
- disciplines/biomedicine.md
- disciplines/chemistry-materials.md
- disciplines/computer-science.md
- disciplines/economics-social-science.md
- disciplines/humanities-law.md
- disciplines/physics-math.md
- metadata-schema.md
- rankings/README.md
- rankings/biomed-evidence-ranking.md
- search-protocol.md
- site-patterns/README.md
- … and 16 more
Open the folder on GitHubat commit 23c4948
Compare with similar skills
Academic Search next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Academic Search this skilldashbear-ai/grant-master | 126 | — | ~758 | Automated safety check: Pass | MIT | |
| Read arXiv Paperkarpathy/nanochat | 59k | 1 repos | ~494 | Automated safety check: Pass | MIT | |
| Perplexity Web Searchdavila7/claude-code-templates | 33k | 11 repos | ~3.5k | Automated safety check: Notes | MIT | |
| Literature Reviewneflibata-feng/MyArxiv-Agent | 126 | 20 repos | ~5.9k | Automated safety check: Notes | MIT | |
| Openalex Databaseneflibata-feng/MyArxiv-Agent | 126 | 12 repos | ~3k | Automated safety check: Pass | Custom licence | |
| Citation ManagementK-Dense-AI/claude-scientific-writer | 2.4k | 2 repos | ~3.9k | Automated safety check: Notes | MIT |
Similar skills
Perplexity Web Search
davila7/claude-code-templates
Runs web-grounded searches through Perplexity's Sonar models over OpenRouter for current events, recent literature and cited facts beyond the model's training cutoff.
Literature Review
neflibata-feng/MyArxiv-Agent
Conduct comprehensive, systematic literature reviews using multiple academic databases (PubMed, arXiv, bioRxiv, Semantic Scholar, etc.).
Openalex Database
neflibata-feng/MyArxiv-Agent
Query and analyze scholarly literature using the OpenAlex database.
Citation Management
K-Dense-AI/claude-scientific-writer
Finds papers in OpenAlex, PubMed and Google Scholar, turns DOIs, PMIDs and arXiv IDs into clean BibTeX, and validates citations for a manuscript or thesis.
Preprint Search on bioRxiv
LigphiDonk/Oh-my--paper
Searches bioRxiv life sciences preprints by keyword, author, date range or category with a Python script, returning JSON metadata and optional PDF downloads.
More from dashbear-ai/grant-master
Auto
dashbear-ai/grant-master
中文申请书五阶段研究与写作：课题准备、文献调研、方案制定、大纲规划、正文写作. An agent skill from dashbear-ai/grant-master.
Related
Categories
Questions about Academic Search
What does Academic Search do?
Grant Master 文献调研阶段的多源检索、两遍筛选、开放全文获取和元数据合并方法. An agent skill from dashbear-ai/grant-master. Academic Search is an agent skill from dashbear-ai/grant-master.
When should I use Academic Search?
Academic Search fits situations like: tasks that involve Academic paper search.
How do I install Academic Search in Claude Code?
Run `npx skills add dashbear-ai/grant-master --skill academic-search -a claude-code`. Or copy the skill folder (references/academic-search in dashbear-ai/grant-master) into .claude/skills/academic-search in your project. Claude Code loads it when a task matches its description.
How do I install Academic Search in Codex?
Run `npx skills add dashbear-ai/grant-master --skill academic-search -a codex`. Or copy the skill folder (references/academic-search in dashbear-ai/grant-master) into .agents/skills/academic-search in your project. Codex loads it when a task matches its description.
Can I use Academic Search in Cursor, Gemini CLI or GitHub Copilot?
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add dashbear-ai/grant-master --skill academic-search -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/academic-search, .gemini/skills/academic-search, .github/skills/academic-search and .opencode/skills/academic-search in your project.
What does Academic Search need to run?
Going by SKILL.md and its folder, Academic Search needs the command-line tools its instructions call (python3). Our summary lists: Python 3.
Does Academic Search access the network?
SKILL.md names 2 domains. In commands or code: doi.org; the agent is likely to contact it when it follows the instructions. As links in the text: github.com. This is read from the text; nothing was executed.
Is Academic Search safe to install?
Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.
What licence does Academic Search use?
Academic Search is published under the MIT licence (from the LICENSE file in the skill folder). It allows redistribution, so the full SKILL.md is shown on this page.
How many tokens does Academic Search use?
About 758 tokens (SKILL.md is roughly 3k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.
What are the alternatives to Academic Search?
Skills that share tags, products or a category with Academic Search: Read arXiv Paper (karpathy/nanochat, 59k stars), Perplexity Web Search (davila7/claude-code-templates, 33k stars), Literature Review (neflibata-feng/MyArxiv-Agent, 126 stars) and Openalex Database (neflibata-feng/MyArxiv-Agent, 126 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Academic Search?
dashbear-ai (a GitHub organization) maintains it in dashbear-ai/grant-master, which has 126 GitHub stars. The repository holds 2 skills in this directory. The repository was last updated on September 9, 2026.
Source: dashbear-ai/grant-master on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.