Research Writing
alfonso0512/research-writing-skill
科研论文写作助手，提供 30 个 Prompt 模板覆盖论文写作全流程. An agent skill from alfonso0512/research-writing-skill.
extract structured benchmark information from academic papers when the input includes multiple pdfs, abstracts, or links and the user needs chinese notes or table-ready fields for tasks, datasets…
Install Benchmark Extractor
$ npx skills add chtc66/academic-skills --skill benchmark-extractor -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install chtc66/academic-skills benchmark-extractor --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/chtc66/academic-skills.git skills-src && mkdir -p .claude/skills && cp -r skills-src/benchmark-extractor .claude/skills/benchmark-extractor && 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 "benchmark-extractor" agent skill from https://github.com/chtc66/academic-skills/tree/main/benchmark-extractor into .claude/skills/benchmark-extractor/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "benchmark-extractor", 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/chtc66/academic-skills/tree/main/benchmark-extractorType 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 chtc66/academic-skills --skill benchmark-extractor -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install chtc66/academic-skills benchmark-extractor --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/chtc66/academic-skills.git skills-src && mkdir -p .agents/skills && cp -r skills-src/benchmark-extractor .agents/skills/benchmark-extractor && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "benchmark-extractor" agent skill from https://github.com/chtc66/academic-skills/tree/main/benchmark-extractor into .agents/skills/benchmark-extractor/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "benchmark-extractor", 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 chtc66/academic-skills --skill benchmark-extractor -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install chtc66/academic-skills benchmark-extractor --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/chtc66/academic-skills.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/benchmark-extractor .cursor/skills/benchmark-extractor && 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 "benchmark-extractor" agent skill from https://github.com/chtc66/academic-skills/tree/main/benchmark-extractor into .cursor/skills/benchmark-extractor/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "benchmark-extractor", 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/chtc66/academic-skills.git --path benchmark-extractor--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 chtc66/academic-skills --skill benchmark-extractor -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install chtc66/academic-skills benchmark-extractor --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/chtc66/academic-skills.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/benchmark-extractor .gemini/skills/benchmark-extractor && 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 "benchmark-extractor" agent skill from https://github.com/chtc66/academic-skills/tree/main/benchmark-extractor into .gemini/skills/benchmark-extractor/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "benchmark-extractor", 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 chtc66/academic-skills benchmark-extractorInstalls 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 chtc66/academic-skills --skill benchmark-extractor -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/chtc66/academic-skills.git skills-src && mkdir -p .github/skills && cp -r skills-src/benchmark-extractor .github/skills/benchmark-extractor && 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 "benchmark-extractor" agent skill from https://github.com/chtc66/academic-skills/tree/main/benchmark-extractor into .github/skills/benchmark-extractor/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "benchmark-extractor", 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 chtc66/academic-skills --skill benchmark-extractor -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install chtc66/academic-skills benchmark-extractor --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/chtc66/academic-skills.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/benchmark-extractor .opencode/skills/benchmark-extractor && 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 "benchmark-extractor" agent skill from https://github.com/chtc66/academic-skills/tree/main/benchmark-extractor into .opencode/skills/benchmark-extractor/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "benchmark-extractor", 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
benchmark-extractor- GitHub stars
- 360
- Token cost
- ~288 tokens
- SKILL.md length
- 64 words
- Files
- 4 (incl. references)
- Skills in repo
- 8
- Repo updated
- First seen
- Licence
- MIT
At a glance
extract structured benchmark information from academic papers when the input includes multiple pdfs, abstracts, or links and the user needs chinese notes or table-ready fields for tasks, datasets…
- Works in 3 steps: 先按论文逐篇抽取稳定字段。 → 参考 references/extraction_schema.md… → 参考…
- Documents & Office work in your project
- SKILL.md covers 工作流, 输入处理规则, 输出模式 and 输出规则, plus 2 more sections
- Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md
What it does
Benchmark Extractor is an agent skill from chtc66/academic-skills. extract structured benchmark information from academic papers when the input includes multiple pdfs, abstracts, or links and the user needs chinese notes or table-ready fields for tasks, datasets, metrics, baselines, sota claims, code release, or evaluation settings.
Its SKILL.md is about 290 tokens, which your agent loads only when the skill is triggered. The skill folder holds 5 other files, including reference files (for example `agents/openai.yaml`, `references/comparison_table_template.md` and `references/extraction_schema.md`).
It sits in Documents & Office. The repository describes itself as: Academic workflow skills for paper reading, survey writing, experiment summarization, rebuttal drafting, and weekly lab updates. The licence is MIT.
When your agent uses it
- Documents & Office work in your project
Example prompts
- “/benchmark-extractor”
Workflow steps
3 steps, taken from the first numbered list in SKILL.md.
- 先按论文逐篇抽取稳定字段。
- 参考 references/extraction_schema.md 统一字段名和缺失值写法。
- 参考 references/comparison_table_template.md 输出中文说明版或结构化表格版。
What it can do on your machine
Read from SKILL.md and the folder at commit 126e235. 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
No scripts in the folder and no shell commands in SKILL.md.
From the folder's file list and the shell code blocks in SKILL.md.
Network
No URLs in SKILL.md.
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
Benchmark Extractor loads about 288 tokens when it runs, and up to ~767 if it reads all its reference files. Until then it costs about 72 tokens; SKILL.md has 64 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 chtc66/academic-skills at commit 126e235, republished under its MIT licence (© chtc66). 64 words, ~288 tokens.
Download SKILL.mdSave it as
.claude/skills/benchmark-extractor/SKILL.md (or your agent's skills folder). This skill also uses 3 other files; get the full folder from GitHub.- name
- benchmark-extractor
- description
- extract structured benchmark information from academic papers when the input includes multiple pdfs, abstracts, or links and the user needs chinese notes or table-ready fields for tasks, datasets, metrics, baselines, sota claims, code release, or evaluation settings.
Benchmark Extractor
用这个 skill 从论文中抽取 benchmark、dataset、metric、baseline、SOTA 等结构化信息，方便后续整理成表格、CSV 或 JSON。
工作流
- 先按论文逐篇抽取稳定字段。
- 参考
references/extraction_schema.md统一字段名和缺失值写法。 - 参考
references/comparison_table_template.md输出中文说明版或结构化表格版。
输入处理规则
- 接收多篇 PDF、多篇摘要或一组论文链接。
- 如果不同论文信息完整度不一致，仍按统一 schema 填写。
- 未明确写出的字段统一写为
未知，不要臆造。
输出模式
- 中文说明版：适合先看整体 benchmark 版图。
- 结构化表格版：适合后续导出 CSV、JSON 或继续人工补全。
- 如果用户没有指定，默认同时给出简短说明和结构化表格。
输出规则
- 字段尽量包括：
- 论文标题
- 任务
- 数据集
- 指标
- baseline
- 是否报告 SOTA
- 是否开源代码
- 是否开源数据
- 评测设置说明
- 备注
- 对“是否报告 SOTA”这类字段，如果论文只是声称优于 baseline，但未明确写“state of the art”，优先写“未明确”。
证据与表述约束
- 不要根据常识自动补数据集、指标或开源状态。
- 如果只有摘要，明确说明当前抽取只是初步结果。
- 如果字段存在歧义，在备注里写出歧义来源。
何时读引用文件
- 始终读取
references/extraction_schema.md。 - 在组织表格输出时读取
references/comparison_table_template.md。
© chtc66, 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 3 other files (references) in benchmark-extractor of chtc66/academic-skills.
- SKILL.md
- agents/openai.yaml
- references/comparison_table_template.md
- references/extraction_schema.md
Open the folder on GitHubat commit 126e235
Compare with similar skills
Benchmark Extractor 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 |
|---|---|---|---|---|---|---|
| Benchmark Extractor this skillchtc66/academic-skills | 360 | — | ~288 | Automated safety check: Pass | MIT | |
| Research Writingalfonso0512/research-writing-skill | 487 | 1 repos | ~818 | Automated safety check: Pass | MIT | |
| Paper WritingMLNLP-World/Paper-Writing-Tips | 4.7k | — | ~630 | Automated safety check: Pass | None | |
| Math Modeling to EI Conference Paperjihe520/MathModelAgent | 6.2k | — | ~688 | Automated safety check: Pass | None | |
| PaperjurySpark-To-Paper-Skills/paperjury | 1.2k | — | ~5.3k | Automated safety check: Pass | MIT | |
| Journal Copyeditor DOCXmikemikeqqq/copyeditor-skill | 292 | — | ~3.9k | Automated safety check: Pass | MIT |
Similar skills
Paper Writing
MLNLP-World/Paper-Writing-Tips
学术论文写作检查与优化助手。基于 MLNLP-World 社区整理的论文写作技巧，帮助检查和优化学术论文。Use when: (1) 检查论文 LaTeX 格式和排版, (2) 优化公式符号使用, (3) 改进图表设计, (4) 润色英文学术表达, (5) 检查参考文献格式, (6) 投稿前终稿检查, (7) 用户询问论文写作技巧或规范。
Math Modeling to EI Conference Paper
jihe520/MathModelAgent
Rewrites a math modeling competition paper into an English EI conference submission, using a bundled IEEE LaTeX template, with evidence tracked back to the original paper.
Paperjury
Spark-To-Paper-Skills/paperjury
Three modes for CS-conference papers (CVPR/ICCV/ECCV vision, ACL/EMNLP/NAACL NLP, ICLR/NeurIPS/ICML/AAAI ML).
Journal Copyeditor DOCX
mikemikeqqq/copyeditor-skill
Comprehensive academic journal copyediting and manuscript review for Microsoft Word (.docx) files across disciplines and target journals.
Markdown to HTML Report
MegaSuperKitty/WeClaw
Drafts a report in Markdown with numbered inline citations and a references section, then renders it to a styled HTML file through a Jinja2 template on Windows.
More from chtc66/academic-skills
All 8 skills in this repoPaper Feishu Digest
chtc66/academic-skills
monitor recent arxiv papers and produce a chinese digest when the user needs a filtered paper watchlist, a ranked update for agent or rag related topics, or an optional feishu webhook push from…
Weekly Lab Update
chtc66/academic-skills
turn a week's paper reading, experiment progress, debugging notes, and next-step plans into a chinese weekly report, a chinese group-meeting outline, or an english brief when the user needs a…
Experiment Log Summarizer
chtc66/academic-skills
summarize machine learning experiment logs in chinese when the input includes training logs, eval results, hyperparameter changes, user notes, or multiple runs and the user needs a grounded…
Paper Deep Note
chtc66/academic-skills
produce a chinese deep reading note for a single academic paper when the input is a pdf, arxiv link, title with abstract, or paper excerpts and the user needs a grounded reading card, contribution…
Research Gap Finder
chtc66/academic-skills
analyze topic coverage, bottlenecks, controversies, and plausible research gaps when the input includes a research topic, a set of papers, or the user's early ideas and the user needs a grounded gap…
Review Rebuttal
chtc66/academic-skills
analyze academic reviews and draft a professional rebuttal when the input includes reviewer comments, a meta-review, paper abstract, or user supplied experiment status and the user needs concern…
Related
Categories
Questions about Benchmark Extractor
What does Benchmark Extractor do?
extract structured benchmark information from academic papers when the input includes multiple pdfs, abstracts, or links and the user needs chinese notes or table-ready fields for tasks, datasets…. Benchmark Extractor is an agent skill from chtc66/academic-skills. extract structured benchmark information from academic papers when the input includes multiple pdfs, abstracts, or links and the user needs chinese notes or table-ready fields for tasks, datasets, metrics, baselines, sota claims, code release, or evaluation settings.
When should I use Benchmark Extractor?
Benchmark Extractor fits situations like: documents & Office work in your project.
How do I install Benchmark Extractor in Claude Code?
Run `npx skills add chtc66/academic-skills --skill benchmark-extractor -a claude-code`. Or copy the skill folder (benchmark-extractor in chtc66/academic-skills) into .claude/skills/benchmark-extractor in your project. Claude Code loads it when a task matches its description.
How do I install Benchmark Extractor in Codex?
Run `npx skills add chtc66/academic-skills --skill benchmark-extractor -a codex`. Or copy the skill folder (benchmark-extractor in chtc66/academic-skills) into .agents/skills/benchmark-extractor in your project. Codex loads it when a task matches its description.
Can I use Benchmark Extractor 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 chtc66/academic-skills --skill benchmark-extractor -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/benchmark-extractor, .gemini/skills/benchmark-extractor, .github/skills/benchmark-extractor and .opencode/skills/benchmark-extractor in your project.
What does Benchmark Extractor need to run?
SKILL.md names no scripts, command-line tools or credentials: Benchmark Extractor is instructions for the agent only.
Does Benchmark Extractor access the network?
SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.
Is Benchmark Extractor 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 Benchmark Extractor use?
Benchmark Extractor is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
How many tokens does Benchmark Extractor use?
About 288 tokens (SKILL.md is roughly 1.2k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 479 tokens, read only when the agent opens those files.
What are the alternatives to Benchmark Extractor?
Skills that share tags, products or a category with Benchmark Extractor: Research Writing (alfonso0512/research-writing-skill, 487 stars), Paper Writing (MLNLP-World/Paper-Writing-Tips, 4.7k stars), Math Modeling to EI Conference Paper (jihe520/MathModelAgent, 6.2k stars) and Paperjury (Spark-To-Paper-Skills/paperjury, 1.2k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Benchmark Extractor?
chtc66 (a GitHub user) maintains it in chtc66/academic-skills, which has 360 GitHub stars. The repository holds 8 skills in this directory. The repository was last updated on April 5, 2026.
Source: chtc66/academic-skills on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.