Paper Navigator
EvoScientist/EvoSkills
Find and read academic papers (S2 + arXiv). An agent skill from EvoScientist/EvoSkills.
全自动科研平台：从论文检索、知识图谱构建、研究缺口分析、假设生成，到实验执行、论文写作、自审修正的完整科研流水线。Agent 按此 Skill 的指令自主推进研究流程。触发场景：做研究、搜论文、找研究缺口、生成假设、跑实验、写论文、文献综述、benchmark对比 / Triggers: research, literature review, paper search, hypothesis…
Install Research Platform
$ npx skills add ZS520L/HanakoPro --skill research-platform -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install ZS520L/HanakoPro research-platform --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/ZS520L/HanakoPro.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills2set/research-platform .claude/skills/research-platform && 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 "research-platform" agent skill from https://github.com/ZS520L/HanakoPro/tree/main/skills2set/research-platform into .claude/skills/research-platform/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "research-platform", 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/ZS520L/HanakoPro/tree/main/skills2set/research-platformType 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 ZS520L/HanakoPro --skill research-platform -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install ZS520L/HanakoPro research-platform --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/ZS520L/HanakoPro.git skills-src && mkdir -p .agents/skills && cp -r skills-src/skills2set/research-platform .agents/skills/research-platform && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "research-platform" agent skill from https://github.com/ZS520L/HanakoPro/tree/main/skills2set/research-platform into .agents/skills/research-platform/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "research-platform", 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 ZS520L/HanakoPro --skill research-platform -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install ZS520L/HanakoPro research-platform --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/ZS520L/HanakoPro.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/skills2set/research-platform .cursor/skills/research-platform && 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 "research-platform" agent skill from https://github.com/ZS520L/HanakoPro/tree/main/skills2set/research-platform into .cursor/skills/research-platform/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "research-platform", 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/ZS520L/HanakoPro.git --path skills2set/research-platform--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 ZS520L/HanakoPro --skill research-platform -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install ZS520L/HanakoPro research-platform --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/ZS520L/HanakoPro.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/skills2set/research-platform .gemini/skills/research-platform && 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 "research-platform" agent skill from https://github.com/ZS520L/HanakoPro/tree/main/skills2set/research-platform into .gemini/skills/research-platform/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "research-platform", 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 ZS520L/HanakoPro research-platformInstalls 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 ZS520L/HanakoPro --skill research-platform -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/ZS520L/HanakoPro.git skills-src && mkdir -p .github/skills && cp -r skills-src/skills2set/research-platform .github/skills/research-platform && 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 "research-platform" agent skill from https://github.com/ZS520L/HanakoPro/tree/main/skills2set/research-platform into .github/skills/research-platform/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "research-platform", 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 ZS520L/HanakoPro --skill research-platform -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install ZS520L/HanakoPro research-platform --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/ZS520L/HanakoPro.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/skills2set/research-platform .opencode/skills/research-platform && 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 "research-platform" agent skill from https://github.com/ZS520L/HanakoPro/tree/main/skills2set/research-platform into .opencode/skills/research-platform/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "research-platform", 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
research-platform- GitHub stars
- 103
- Token cost
- ~1.1k tokens
- SKILL.md length
- 236 words
- Files
- 17 (incl. scripts, references)
- Skills in repo
- 7
- Repo updated
- First seen
- Licence
- Apache-2.0
At a glance
全自动科研平台：从论文检索、知识图谱构建、研究缺口分析、假设生成，到实验执行、论文写作、自审修正的完整科研流水线。Agent 按此 Skill 的指令自主推进研究流程。触发场景：做研究、搜论文、找研究缺口、生成假设、跑实验、写论文、文献综述、benchmark对比 / Triggers: research, literature review, paper search, hypothesis…
- Works in 7 steps: ：论文检索与摄取 → ：知识图谱构建 → ：研究缺口分析 → …
- Tasks that involve Academic paper search
- SKILL.md covers 核心原则, 何时启用, 研究流程概览 and Phase 1：论文检索与摄取, plus 8 more sections
- Runs Python scripts from its folder; calls python; needs OPENALEX_API_KEY and SEMANTIC_SCHOLAR_API_KEY
What it does
Research Platform is an agent skill from ZS520L/HanakoPro. 全自动科研平台：从论文检索、知识图谱构建、研究缺口分析、假设生成，到实验执行、论文写作、自审修正的完整科研流水线。Agent 按此 Skill 的指令自主推进研究流程。触发场景：做研究、搜论文、找研究缺口、生成假设、跑实验、写论文、文献综述、benchmark对比 / Triggers: research, literature review, paper search, hypothesis generation, run experiments, write paper, benchmark, find research gap, survey
Its SKILL.md is about 1.1k tokens, which your agent loads only when the skill is triggered. The skill folder holds 22 other files, including scripts and reference files (for example `research_output/experiments/plan_1.json`, `research_output/gaps.json` and `research_output/hypotheses.json`). Compatibility notes: 需要 Python 3.11+，依赖: requests, sqlite3（内置）。可选: docker, pdflatex, matplotlib
It sits in Research & Science, covering Academic paper search, Literature review and Hypothesis generation. The repository describes itself as: Hanako优化版，增加文件diff，内置终端实时查看程序运行日志，消息撤回等程序员和研究生迫切需要的功能。 The licence is Apache-2.0.
When your agent uses it
- Tasks that involve Academic paper search
- Tasks that involve Literature review
- Tasks that involve Hypothesis generation
Example prompts
- “/research-platform”
Requirements
- Python 3
- Docker
- A credential in OPENALEX_API_KEY
- A credential in SEMANTIC_SCHOLAR_API_KEY
- Compatibility (from SKILL.md): 需要 Python 3.11+，依赖: requests, sqlite3（内置）。可选: docker, pdflatex, matplotlib
Workflow steps
7 steps, taken from the step headings in SKILL.md.
What it can do on your machine
Read from SKILL.md and the folder at commit 49ec8dc. 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
Ships 5 files in scripts/ (Python, from the files we listed), which the agent can run.
Shell commands in SKILL.md call:
python
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 these keys or tokens, usually read from environment variables:
OPENALEX_API_KEYSEMANTIC_SCHOLAR_API_KEYCORE_API_KEYSERPLY_API_KEYKAGGLE_API_KEY
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Compatibility
需要 Python 3.11+，依赖: requests, sqlite3（内置）。可选: docker, pdflatex, matplotlib
From compatibility in the SKILL.md frontmatter.
Context cost
Research Platform loads about 1.1k tokens when it runs, and up to ~4.9k if it reads all its reference files. Until then it costs about 74 tokens; SKILL.md has 236 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); the scripts in this folder are not scanned.
SKILL.md
The full file from ZS520L/HanakoPro at commit 49ec8dc, republished under its Apache-2.0 licence (© ZS520L). 236 words, ~1,103 tokens.
Download SKILL.mdSave it as
.claude/skills/research-platform/SKILL.md (or your agent's skills folder). This skill also uses 16 other files; get the full folder from GitHub.- name
- research-platform
- description
- 全自动科研平台：从论文检索、知识图谱构建、研究缺口分析、假设生成，到实验执行、论文写作、自审修正的完整科研流水线。Agent 按此 Skill 的指令自主推进研究流程。触发场景：做研究、搜论文、找研究缺口、生成假设、跑实验、写论文、文献综述、benchmark对比 / Triggers: research, literature review, paper search, hypothesis generation, run experiments, write paper, benchmark, find research gap, survey
- compatibility
- 需要 Python 3.11+，依赖: requests, sqlite3（内置）。可选: docker, pdflatex, matplotlib
- metadata.default-enabled
- true
全自动科研平台
核心原则
你是科研助手。你的目标不是代替研究者思考，而是把研究者从重复劳动中解放出来——搜论文、建知识图谱、找缺口、跑实验、写初稿。研究者保留所有决策权。
三条铁律：
- 数据驱动，不编造。 每一个声称必须有对应的实验结果或论文引用支撑。没有数据就说没有。
- 流程透明。 每一步做了什么、为什么这样做，随时可以向用户汇报。
- 用户决策，你执行。 方向选择、假设取舍、最终审阅由用户决定。你可以推荐，不能越权。
何时启用
用户提到以下任一意图时启用此 Skill：
- 搜索某领域论文、做文献综述
- 找研究缺口、生成研究假设
- 对比 benchmark、设计实验
- 写论文、修改论文
- "帮我研究一下..."、"这个方向有什么可以做的"、"搜一下最新的..."
研究流程概览
Phase 1: 论文检索与摄取
Phase 2: 知识图谱构建
Phase 3: 研究缺口分析
Phase 4: 假设生成
Phase 5: 实验设计与执行 [用户审核节点]
Phase 6: 论文写作
Phase 7: 自审与修正每个 Phase 完成后向用户汇报结果，等待确认再进入下一 Phase。用户说"全自动"或"继续"时跳过确认。
Phase 1：论文检索与摄取
目标
在目标领域检索论文，下载 OA 全文，提取结构化信息。
执行
Step 1.1：确认研究参数
向用户确认（如果未明确）：
- 研究领域/关键词
- 年份范围（默认 2024-2025）
- 偏好 venue（默认不限制）
- 检索深度（默认 100-300 篇）
Step 1.2：多源检索
运行 scripts/search_papers.py：
python scripts/search_papers.py --query "<关键词>" --year-start <年份> --year-end <年份> --max-results <数量> --output papers.json脚本自动调用 OpenAlex（主力）+ Semantic Scholar（详情+引用）+ Serply（GS 补缺），去重后保存为 JSON。
Step 1.3：展示检索结果
向用户汇报：
- 检索到多少篇论文
- OA 全文可获取比例
- 按引用数 Top 5 论文
- 主要发表 venue 分布
Step 1.4：结构化摄取（可选，用户要求时执行）
对需要深度分析的论文，逐篇提取：方法名、数据集、baseline、指标值、超参数、局限性。脚本自动处理，结果写入 UKG。
Phase 2：知识图谱构建
目标
将论文的结构化数据存入 SQLite 知识图谱，建立论文-方法-数据集-结果的关系网。
执行
运行 scripts/build_ukg.py：
python scripts/build_ukg.py --papers papers.json --db ukg.db脚本自动创建数据库表（papers, methods, datasets, results, citations），从 papers.json 导入数据，建立引用关系边。
汇报：入库论文数、方法数、数据集数、结果条目数。
Phase 3：研究缺口分析
目标
在 UKG 中识别尚未被充分研究的方向。
执行
运行 scripts/find_gaps.py：
python scripts/find_gaps.py --db ukg.db --output gaps.json脚本执行五类缺口检测：
- 组合缺口：(方法, 问题, 数据集) 未尝试的组合
- 矛盾缺口：同一指标数值冲突
- 局限缺口：各论文 limitation 聚类
- 交叉缺口：相邻领域方法可迁移
- 尺度缺口：方法在更大/更小规模上未测试
汇报：缺口数量和详情，标注优先级。
Phase 4：假设生成
目标
基于 UKG 和缺口，生成候选研究假设并排序。
执行
Step 4.1：生成假设池
运行 scripts/gen_hypotheses.py：
python scripts/gen_hypotheses.py --db ukg.db --gaps gaps.json --output hypotheses.jsonStep 4.2：评分与排序
对每个假设计算：
- 新颖性分：UKG 中最接近已有工作的语义相似度（越高越不新颖）
- 可行性分：数据是否公开、算力是否足够
- 影响力分：缺口涉及论文数、引用增速
Step 4.3：展示候选假设
向用户展示 Top 3 假设，每条包含：
- 假设陈述
- 新颖性/可行性/影响力评分
- 因果推理链
- 主要风险
- 建议的实验验证路径
等待用户选择。
Phase 5：实验设计与执行 [用户审核]
目标
为选定假设设计完整实验方案并执行。
执行
Step 5.1：设计实验
基于 UKG：
- 穷举相关 baseline
- 设计消融实验（组件依赖图）
- 确定评估指标和统计方法
- 预估算力和时间
向用户展示实验矩阵，确认后执行。
Step 5.2：执行实验
运行 scripts/run_experiment.py：
python scripts/run_experiment.py --hypothesis <假设编号> --db ukg.db --output-dir experiments/实验在 Docker 中并行执行。每 30 分钟汇报进度（完成数、当前最佳指标、预估剩余时间）。
用户可随时：暂停、跳过某实验、追加 baseline、修改超参数。
Step 5.3：结果分析
所有实验完成后自动执行统计分析、因果链验证、可视化生成。汇报给用户。
Phase 6：论文写作
目标
基于实验结果和 UKG 数据生成论文初稿。
执行
运行 scripts/write_paper.py：
python scripts/write_paper.py --db ukg.db --experiments experiments/ --template templates/paper.tex --output paper.pdf生成内容：
- Title（10 个候选，标记最优）
- Abstract（四段模板，数值自动填入）
- Introduction（缺口驱动的问题动机）
- Method（UKG 方法架构描述）
- Experiments（结果表 + 分析段落 + 消融图）
- Related Work（UKG 主题聚类对比）
- Conclusion + Limitations
编译为 PDF，向用户交付。
Phase 7：自审与修正
目标
对论文初稿进行对抗性审查，发现漏洞并修正。
执行
运行 scripts/review_paper.py：
python scripts/review_paper.py --paper paper.tex --db ukg.db --output review.md审查维度：
- 是否遗漏关键 baseline
- 统计是否规范（p 值、效应量、多重比较校正）
- 声称是否有实验支撑
- Related Work 是否遗漏重要工作
- 图表标注是否清晰
逐条报告问题，用户确认后自动修正（重新运行 Phase 6）。
API 密钥
API 密钥通过环境变量配置：
- OpenAlex:
OPENALEX_API_KEY - Semantic Scholar:
SEMANTIC_SCHOLAR_API_KEY - CORE:
CORE_API_KEY - Serply:
SERPLY_API_KEY - Kaggle:
KAGGLE_API_KEY
输出文件结构
每次研究任务在工作目录下创建 research_output/ 目录：
research_output/
├── papers.json ← Phase 1 检索结果
├── ukg.db ← Phase 2 知识图谱
├── gaps.json ← Phase 3 缺口分析
├── hypotheses.json ← Phase 4 假设
├── experiments/ ← Phase 5 实验结果
├── paper.pdf ← Phase 6 论文
└── review.md ← Phase 7 审查报告© ZS520L, Apache-2.0. 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 16 other files (scripts, references) in skills2set/research-platform of ZS520L/HanakoPro.
- SKILL.md
- references/image/api_keys/1779510988369.png
- research_output/experiments/plan_1.json
- research_output/gaps.json
- research_output/hypotheses.json
- research_output/paper.json
- research_output/paper.tex
- research_output/papers.json
- research_output/review.json
- research_output/review.md
- scripts/build_ukg.py
- scripts/find_gaps.py
- scripts/gen_hypotheses.py
- scripts/review_paper.py
- scripts/run_experiment.py
- … and 2 more
Open the folder on GitHubat commit 49ec8dc
Compare with similar skills
Research Platform 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 |
|---|---|---|---|---|---|---|
| Research Platform this skillZS520L/HanakoPro | 103 | — | ~1.1k | Automated safety check: Pass | Apache-2.0 | |
| Paper NavigatorEvoScientist/EvoSkills | 478 | — | ~6.3k | Automated safety check: Notes | Apache-2.0 | |
| Paper NavigatorAI4Scientist/nano-scientist | 128 | — | ~7.7k | Automated safety check: Notes | None | |
| Math Discovery Evidence Searchtradecatlabs/vibe-coding-cn | 17k | — | ~554 | Automated safety check: Pass | MIT | |
| Academic Research CompanionGRCEngClub/claude-grc-engineering | 419 | — | ~2.2k | Automated safety check: Pass | Custom licence | |
| Novelty CheckGRIND-Lab-Core/night_owl_research_agent | 106 | — | ~1k | Automated safety check: Pass | None |
Similar skills
Paper Navigator
AI4Scientist/nano-scientist
Find and read academic papers: disambiguate queries, discover papers (search, citation traversal, recommendations, arXiv monitoring, trending, GitHub search), evaluate (TLDR, citations, code, SOTA)…
Math Discovery Evidence Search
tradecatlabs/vibe-coding-cn
Turns a vague math interest into a bounded, searchable problem and builds a source-traced evidence graph, with novelty checks and conjectures drawn from evidence gaps.
Academic Research Companion
GRCEngClub/claude-grc-engineering
Guide a research project through the full academic lifecycle — from raw idea to concrete research question, literature grounding, methodology, writing, feedback, and publication.
Novelty Check
GRIND-Lab-Core/night_owl_research_agent
Validates that a research idea is genuinely novel vs. An agent skill from GRIND-Lab-Core/night_owl_research_agent.
Meta Search Builder
aipoch/medical-research-skills
Medical literature search strategy generator. An agent skill from aipoch/medical-research-skills.
More from ZS520L/HanakoPro
Office Documents
ZS520L/HanakoPro
A skill your agent uses when the user asks to open, read, inspect, understand, summarize, analyze, extract tables/text from, modify, update, repair, split, merge, rotate, or convert information from…
Hana Plugin Creator
ZS520L/HanakoPro
Create Hana plugin scaffolds and guide users through beginner or developer plugin planning, capability checks, manifest setup, runtime tools, iframe UI, SDK templates, and install-ready plugin…
Skill Creator
ZS520L/HanakoPro
Create new skills, modify and improve existing skills, and measure skill performance.
Quiet Musing
ZS520L/HanakoPro
Deep reasoning framework for complex tasks. An agent skill from ZS520L/HanakoPro.
User Guide
ZS520L/HanakoPro
Hanako 用户说明书。解答用户关于软件使用方法、功能介绍、常见问题和实用技巧的疑问. An agent skill from ZS520L/HanakoPro.
Image Gen Guide
ZS520L/HanakoPro
使用图片/视频生成工具时必读。包含工具参数、非阻塞工作流、任务路由。
Related
Categories
Questions about Research Platform
What does Research Platform do?
全自动科研平台：从论文检索、知识图谱构建、研究缺口分析、假设生成，到实验执行、论文写作、自审修正的完整科研流水线。Agent 按此 Skill 的指令自主推进研究流程。触发场景：做研究、搜论文、找研究缺口、生成假设、跑实验、写论文、文献综述、benchmark对比 / Triggers: research, literature review, paper search, hypothesis…. Research Platform is an agent skill from ZS520L/HanakoPro.
When should I use Research Platform?
Research Platform fits situations like: tasks that involve Academic paper search; tasks that involve Literature review; tasks that involve Hypothesis generation.
How do I install Research Platform in Claude Code?
Run `npx skills add ZS520L/HanakoPro --skill research-platform -a claude-code`. Or copy the skill folder (skills2set/research-platform in ZS520L/HanakoPro) into .claude/skills/research-platform in your project. Claude Code loads it when a task matches its description.
How do I install Research Platform in Codex?
Run `npx skills add ZS520L/HanakoPro --skill research-platform -a codex`. Or copy the skill folder (skills2set/research-platform in ZS520L/HanakoPro) into .agents/skills/research-platform in your project. Codex loads it when a task matches its description.
Can I use Research Platform 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 ZS520L/HanakoPro --skill research-platform -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/research-platform, .gemini/skills/research-platform, .github/skills/research-platform and .opencode/skills/research-platform in your project.
What does Research Platform need to run?
Going by SKILL.md and its folder, Research Platform needs Python for the scripts in its folder, the command-line tools its instructions call (python) and credentials named OPENALEX_API_KEY, SEMANTIC_SCHOLAR_API_KEY, CORE_API_KEY and SERPLY_API_KEY. Our summary lists: Python 3; Docker; A credential in OPENALEX_API_KEY; A credential in SEMANTIC_SCHOLAR_API_KEY. Compatibility (from SKILL.md): 需要 Python 3.11+，依赖: requests, sqlite3（内置）。可选: docker, pdflatex, matplotlib.
Does Research Platform 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 Research Platform 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. The check reads SKILL.md only: the scripts in the folder are not scanned, so read them before running anything.
What licence does Research Platform use?
Research Platform is published under the Apache-2.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
How many tokens does Research Platform use?
About 1.1k tokens (SKILL.md is roughly 4.4k 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 3.8k tokens, read only when the agent opens those files.
What are the alternatives to Research Platform?
Skills that share tags, products or a category with Research Platform: Paper Navigator (EvoScientist/EvoSkills, 478 stars), Paper Navigator (AI4Scientist/nano-scientist, 128 stars), Math Discovery Evidence Search (tradecatlabs/vibe-coding-cn, 17k stars) and Academic Research Companion (GRCEngClub/claude-grc-engineering, 419 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Research Platform?
ZS520L (a GitHub user) maintains it in ZS520L/HanakoPro, which has 103 GitHub stars. The repository holds 7 skills in this directory. The repository was last updated on May 31, 2026.
Source: ZS520L/HanakoPro on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.