Markitdown
ImCa0/just-laws
Convert files and office documents to Markdown. An agent skill from ImCa0/just-laws.
使用 ScholarGraph v1.4 及以上版本 进行癌症融合基因文献调研的全流程技能。包括搜索、多轮合并去重、提取信息、生成报告和 Excel 表格。
$ npx skills add LeoYeAI/openclaw-master-skills --skill scholargraph-fusion-genes -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install LeoYeAI/openclaw-master-skills scholargraph-fusion-genes --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/LeoYeAI/openclaw-master-skills.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/scholargraph-cancer-fusiongenes-research-flow .claude/skills/scholargraph-fusion-genes && 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 "scholargraph-fusion-genes" agent skill from https://github.com/LeoYeAI/openclaw-master-skills/tree/main/skills/scholargraph-cancer-fusiongenes-research-flow into .claude/skills/scholargraph-fusion-genes/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "scholargraph-fusion-genes", 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/LeoYeAI/openclaw-master-skills/tree/main/skills/scholargraph-cancer-fusiongenes-research-flowType 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 LeoYeAI/openclaw-master-skills --skill scholargraph-fusion-genes -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install LeoYeAI/openclaw-master-skills scholargraph-fusion-genes --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/LeoYeAI/openclaw-master-skills.git skills-src && mkdir -p .agents/skills && cp -r skills-src/skills/scholargraph-cancer-fusiongenes-research-flow .agents/skills/scholargraph-fusion-genes && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "scholargraph-fusion-genes" agent skill from https://github.com/LeoYeAI/openclaw-master-skills/tree/main/skills/scholargraph-cancer-fusiongenes-research-flow into .agents/skills/scholargraph-fusion-genes/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "scholargraph-fusion-genes", 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 LeoYeAI/openclaw-master-skills --skill scholargraph-fusion-genes -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install LeoYeAI/openclaw-master-skills scholargraph-fusion-genes --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/LeoYeAI/openclaw-master-skills.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/skills/scholargraph-cancer-fusiongenes-research-flow .cursor/skills/scholargraph-fusion-genes && 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 "scholargraph-fusion-genes" agent skill from https://github.com/LeoYeAI/openclaw-master-skills/tree/main/skills/scholargraph-cancer-fusiongenes-research-flow into .cursor/skills/scholargraph-fusion-genes/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "scholargraph-fusion-genes", 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/LeoYeAI/openclaw-master-skills.git --path skills/scholargraph-cancer-fusiongenes-research-flow--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 LeoYeAI/openclaw-master-skills --skill scholargraph-fusion-genes -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install LeoYeAI/openclaw-master-skills scholargraph-fusion-genes --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/LeoYeAI/openclaw-master-skills.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/skills/scholargraph-cancer-fusiongenes-research-flow .gemini/skills/scholargraph-fusion-genes && 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 "scholargraph-fusion-genes" agent skill from https://github.com/LeoYeAI/openclaw-master-skills/tree/main/skills/scholargraph-cancer-fusiongenes-research-flow into .gemini/skills/scholargraph-fusion-genes/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "scholargraph-fusion-genes", 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 LeoYeAI/openclaw-master-skills scholargraph-fusion-genesInstalls 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 LeoYeAI/openclaw-master-skills --skill scholargraph-fusion-genes -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/LeoYeAI/openclaw-master-skills.git skills-src && mkdir -p .github/skills && cp -r skills-src/skills/scholargraph-cancer-fusiongenes-research-flow .github/skills/scholargraph-fusion-genes && 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 "scholargraph-fusion-genes" agent skill from https://github.com/LeoYeAI/openclaw-master-skills/tree/main/skills/scholargraph-cancer-fusiongenes-research-flow into .github/skills/scholargraph-fusion-genes/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "scholargraph-fusion-genes", 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 LeoYeAI/openclaw-master-skills --skill scholargraph-fusion-genes -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install LeoYeAI/openclaw-master-skills scholargraph-fusion-genes --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/LeoYeAI/openclaw-master-skills.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/skills/scholargraph-cancer-fusiongenes-research-flow .opencode/skills/scholargraph-fusion-genes && 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 "scholargraph-fusion-genes" agent skill from https://github.com/LeoYeAI/openclaw-master-skills/tree/main/skills/scholargraph-cancer-fusiongenes-research-flow into .opencode/skills/scholargraph-fusion-genes/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "scholargraph-fusion-genes", 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.
scholargraph-fusion-genes使用 ScholarGraph v1.4 及以上版本 进行癌症融合基因文献调研的全流程技能。包括搜索、多轮合并去重、提取信息、生成报告和 Excel 表格。
Scholargraph Fusion Genes is an agent skill from LeoYeAI/openclaw-master-skills. 使用 ScholarGraph v1.4 及以上版本 进行癌症融合基因文献调研的全流程技能。包括搜索、多轮合并去重、提取信息、生成报告和 Excel 表格。
Its SKILL.md is about 3.2k tokens, which your agent loads only when the skill is triggered. The skill folder holds 4 other files (for example `FLOW.md`, `_meta.json` and `generate_excel_template.js`).
It sits in Documents & Office, covering Excel spreadsheets. It works with Microsoft Excel. The repository describes itself as: 🧠 Curated collection of 1209+ best OpenClaw skills — weekly updated by MyClaw.ai. The licence is MIT.
3 steps, taken from the step headings in SKILL.md.
Read from SKILL.md and the folder at commit e5199b5. It shows what the files ask for, not the result of running them.
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.
Ships script files (JavaScript), which the agent can run.
Shell commands in SKILL.md call:
bunnodecurlnpmFrom the folder's file list and the shell code blocks in SKILL.md.
Hosts in commands or code, which the agent is likely to contact:
europepmc.orgapi.minimaxi.comFrom URLs in SKILL.md, links to its own repository left out.
Names these keys or tokens, usually read from environment variables:
MINIMAX_API_KEYSERPER_API_KEYFrom names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Scholargraph Fusion Genes loads about 3.2k tokens when it runs. Until then it costs about 26 tokens; SKILL.md has 445 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.
The automated check noted patterns worth knowing about, such as sudo or a known installer.
在 `ScholarGraph/.env` 文件中配置: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.
The full file from LeoYeAI/openclaw-master-skills at commit e5199b5, republished under its MIT licence (© LeoYeAI). 445 words, ~3,224 tokens.
.claude/skills/scholargraph-fusion-genes/SKILL.md (or your agent's skills folder). This skill also uses 4 other files; get the full folder from GitHub.本技能提供癌症融合基因文献调研的完整流程,使用 ScholarGraph v1.4 及以上版本 进行系统性搜索、分析和整理。支持多轮搜索、合并去重、生成含完整参考文献的 Excel 表格。
# 1. 进入 ScholarGraph 目录
cd /root/.openclaw/workspace/skills/ScholarGraph
# 2. 配置 MiniMax API Key (或使用其他 provider)
export AI_PROVIDER=minimax
export MINIMAX_API_KEY="your-api-key"
# 3. 验证配置
~/.bun/bin/bun run cli.ts --help# 创建工作目录
mkdir -p /workspace/research/fusion/review
mkdir -p /workspace/research/fusion/reports
# 第一轮: 搜索各癌种融合基因 review
~/.bun/bin/bun run cli.ts search "lung cancer fusion gene review" --limit 10
~/.bun/bin/bun run cli.ts search "breast cancer fusion gene review" --limit 10
~/.bun/bin/bun run cli.ts search "colorectal cancer fusion gene review" --limit 10
~/.bun/bin/bun run cli.ts search "solid tumor fusion gene review" --limit 10# 搜索特定基因的融合信息 (并行执行)
~/.bun/bin/bun run cli.ts search "EML4-ALK fusion variant V1 V2 V3 breakpoint" --limit 10
~/.bun/bin/bun run cli.ts search "ROS1 fusion partner CD74 SDC4 TPM3" --limit 10
~/.bun/bin/bun run cli.ts search "RET fusion KIF5B CCDC6 NCOA4 breakpoint" --limit 10
~/.bun/bin/bun run cli.ts search "NTRK1 NTRK2 NTRK3 fusion partner ETV6" --limit 10
~/.bun/bin/bun run cli.ts search "FGFR fusion partner TACC3 BICC1" --limit 10
~/.bun/bin/bun run cli.ts search "NRG1 fusion CD74 SDC4 cancer" --limit 10# 使用 Europe PMC 下载免费文献 (推荐)
# 搜索 PMID 后访问: https://europepmc.org/articles/PMC[ID]?pdf=render
curl -L -o "/workspace/research/fusion/review/filename.pdf" "https://europepmc.org/articles/PMC[ID]?pdf=render"
# 或使用 ScholarGraph download (需配置 SERPER_API_KEY)
~/.bun/bin/bun run cli.ts download "RET fusion cancer review" --limit 3 --output /workspace/research/fusion/review# 补充搜索可能遗漏的融合基因
~/.bun/bin/bun run cli.ts search "EGFRvIII glioma fusion deletion" --limit 5
~/.bun/bin/bun run cli.ts search "ESR1 fusion breast cancer endocrine resistance" --limit 5
~/.bun/bin/bun run cli.ts search "BRAF fusion KIAA1549 melanoma" --limit 5
~/.bun/bin/bun run cli.ts search "MET fusion CAPZA2 LAYN lung cancer" --limit 5
~/.bun/bin/bun run cli.ts search "ALK fusion HIP1 KIF5B non-EML4" --limit 5将多轮搜索结果保存到 JSON 文件,然后进行合并去重:
// merge_results.js
const fs = require('fs');
// 假设有两轮搜索结果
const round1 = require('./round1.json');
const round2 = require('./round2.json');
// 合并去重函数
function mergeAndDeduplicate(results1, results2) {
const seen = new Map();
const merged = [];
for (const item of [...results1, ...results2]) {
// 根据基因+融合伙伴作为唯一标识
const key = `${item.gene}-${item.fusion}`;
if (!seen.has(key)) {
seen.set(key, true);
merged.push(item);
}
}
return merged;
}
const merged = mergeAndDeduplicate(round1, round2);
fs.writeFileSync('./merged_results.json', JSON.stringify(merged, null, 2));
console.log(`Merged: ${merged.length} unique records`);# 安装 xlsx 库
npm install xlsx创建 generate_excel.js:
const XLSX = require('xlsx');
// ========== 辅助函数 ==========
// 频率级别标签逻辑
function getFreqLabel(freq) {
// 特殊情况: EGFR扩增等
if (freq.includes('EGFR扩增')) return '-';
// 提取所有数字
const nums = freq.match(/\d+/g)?.map(Number) || [];
if (nums.length === 0) return '-';
// 取最大值进行判断
const maxVal = Math.max(...nums);
// 频率级别判断
if (maxVal >= 25) return '高'; // ≥25%: 高频率
if (maxVal >= 10) return '中'; // 10-24%: 中频率
if (maxVal >= 3) return '低'; // 3-9%: 低频率
return '极低'; // <3%: 极低频率
}
// 参考文献数量统计
function countSources(ref) {
if (!ref) return 0;
const sources = ref.split(/;\s*/).filter(s => s.trim().length > 0);
return sources.length;
}
// 标准转录本映射
const transcriptMap = {
'ALK': 'NM_004935',
'ROS1': 'NM_002944',
'RET': 'NM_020975',
'NTRK1': 'NM_002529',
'NTRK2': 'NM_006180',
'NTRK3': 'NM_002449',
'MET': 'NM_000245',
'FGFR1': 'NM_023110',
'FGFR2': 'NM_000141',
'FGFR3': 'NM_001142',
'NRG1': 'NM_013962',
'BRAF': 'NM_004333',
'EGFR': 'NM_005228',
'ESR1': 'NM_000125',
};
// ============================
// 完整数据格式 - 每行独立完整
// 字段: 基因, 融合类型, 变体, 融合转录本, 参考基因组, 5'基因, 5'基因断裂位置, 3'基因, 3'基因断裂位置, 频率, 癌种, 临床意义, 靶向药物, 参考文献
const fusionData = [
// 示例:
{
"基因": "ALK",
"融合类型": "EML4-ALK",
"变体": "V1",
"融合转录本": "NM_004935",
"参考基因组": "GRCh37",
"5'基因": "EML4",
"5'基因断裂位置": "exon 13",
"3'基因": "ALK",
"3'基因断裂位置": "exon 20",
"频率": "~33%",
"癌种": "肺癌",
"临床意义": "标准型",
"靶向药物": "Crizotinib; Alectinib",
"参考文献": "Zhang SS, et al. Going beneath the tip of the iceberg... Lung Cancer. 2021; PMID: 34175504"
},
// ... 更多记录
];
// 添加频率级别和参考文献数
const enrichedData = fusionData.map(item => ({
...item,
"频率级别": getFreqLabel(item["频率"]),
"参考文献数": countSources(item["参考文献"])
}));
const wb = XLSX.utils.book_new();
// Sheet 1: 融合基因汇总
const mainSheet = XLSX.utils.json_to_sheet(enrichedData);
XLSX.utils.book_append_sheet(wb, mainSheet, "融合基因汇总");
// Sheet 2: 探针设计推荐
const probeData = [
{ "基因": "ALK", "DNA探针区域": "intron 19", "RNA探针区域": "exon 18-21", "探针长度": "300-500bp", "备注": "覆盖所有变体" },
{ "基因": "ROS1", "DNA探针区域": "intron 31-35", "RNA探针区域": "exon 32-36", "探针长度": "400-600bp", "备注": "覆盖常见融合伙伴" },
// ...
];
const probeSheet = XLSX.utils.json_to_sheet(probeData);
XLSX.utils.book_append_sheet(wb, probeSheet, "探针设计推荐");
// Sheet 3: 分癌种汇总
const cancerSummary = [
{ "癌种": "肺癌", "融合数": 15, "主要基因": "ALK, ROS1, RET, MET" },
{ "癌种": "乳腺癌", "融合数": 3, "主要基因": "ESR1, NTRK" },
// ...
];
const cancerSheet = XLSX.utils.json_to_sheet(cancerSummary);
XLSX.utils.book_append_sheet(wb, cancerSheet, "分癌种汇总");
// 保存文件
XLSX.writeFile(wb, '/workspace/research/fusion/reports/fusion_genes_report.xlsx');运行生成:
node generate_excel.js⚠️ 重要: 每行必须包含独立完整的频率级别,不依赖其他行
// 频率级别判断函数
function getFreqLabel(freq) {
// 特殊情况: EGFR扩增等
if (freq.includes('EGFR扩增')) return '-';
// 提取所有数字
const nums = freq.match(/\d+/g)?.map(Number) || [];
if (nums.length === 0) return '-';
// 取最大值进行判断
const maxVal = Math.max(...nums);
// 频率级别判断
if (maxVal >= 25) return '高'; // ≥25%: 高频率
if (maxVal >= 10) return '中'; // 10-24%: 中频率
if (maxVal >= 3) return '低'; // 3-9%: 低频率
return '极低'; // <3%: 极低频率
}| 频率级别 | 阈值范围 | 示例 |
|---|---|---|
| 高 | ≥25% | ~33%, ~29%, ~50%, ~70% |
| 中 | 10-24% | ~15%, ~10%, ~20% |
| 低 | 3-9% | ~5%, ~8%, ~3% |
| 极低 | <3% | <1%, ~2% |
| - | 特殊 | EGFRvIII (~50% EGFR扩增) |
⚠️ 重要: 每行参考文献必须独立完整,不依赖其他行信息
✅ 正确格式:
参考文献: Zhang SS, et al. Going beneath the tip of the iceberg: Identifying and understanding EML4-ALK variants and TP53 mutations. Lung Cancer. 2021; PMID: 34175504; Christopoulos P, et al. EML4-ALK fusion variant V3 is a high-risk feature. Clin Cancer Res. 2018❌ 错误格式 (依赖其他行):
参考文献: 同上
参考文献: 同V3a| 字段 | 说明 | 示例 |
|---|---|---|
| 基因 | 融合基因名称 | ALK, ROS1, RET |
| 融合类型 | 完整融合名称 | EML4-ALK, CD74-ROS1 |
| 变体 | 变体信息 (如V1/V3) | V1, V3a, - |
| 融合转录本 | 标准转录本ID | NM_004935 |
| 参考基因组 | 基因组版本 | GRCh37 |
| 5'基因 | 5'端伙伴基因 | EML4, CD74 |
| 5'基因断裂位置 | 断裂位置(必须包含exon/intron) | exon 13, intron 6 |
| 3'基因 | 3'端基因 | ALK, ROS1 |
| 3'基因断裂位置 | 断裂位置(必须包含exon/intron) | exon 20, intron 31 |
| 频率 | 发生频率 | ~33%, ~10-15% |
| 频率级别 | 自动计算 | 高/中/低/极低 |
| 癌种 | 关联癌种 | 肺癌, 泛癌种 |
| 临床意义 | 临床意义描述 | 最常见, 耐药 |
| 靶向药物 | 靶向药物 (分号分隔) | Crizotinib; Alectinib |
| 参考文献 | 完整引用 (作者; 作者; 期刊. 年份; PMID) | 见格式规范 |
| 参考文献数 | 自动统计来源数量 | 1, 2 |
| 癌种 | 关联癌种 | 肺癌, 泛癌种 |
| 临床意义 | 临床意义描述 | 最常见, 耐药 |
| 靶向药物 | 靶向药物 | Crizotinib; Alectinib |
| 参考文献 | 完整引用信息 | 见上文格式 |
| 功能 | 命令 |
|---|---|
| 搜索文献 | bun run cli.ts search "关键词" --limit 10 |
| 下载 PDF | bun run cli.ts download "关键词" --limit 5 --output ./downloads |
| 学习概念 | bun run cli.ts learn "概念" --depth intermediate |
| 分析论文 | bun run cli.ts analyze "论文URL" --mode deep |
| 构建知识图谱 | bun run cli.ts graph 概念1 概念2 --format mermaid |
| 生成 Excel | node generate_excel.js |
在 ScholarGraph/.env 文件中配置:
AI_PROVIDER=minimax
MINIMAX_API_KEY=sk-cp-xxx
MINIMAX_BASE_URL=https://api.minimaxi.com/v1
MINIMAX_MODEL=MiniMax-M2.5/workspace/research/fusion/
├── review/ # PDF 文献
│ ├── 01_Drug_resistance_2021.pdf
│ ├── 02_TNBC_molecular_mechanisms_2022.pdf
│ └── ...
├── reports/ # 分析报告
│ ├── fusion_probe_design_report_v2.md
│ ├── detection_methods_report.md
│ └── fusion_genes_report.xlsx # 主输出
├── round1.json # 第一轮搜索结果
├── round2.json # 第二轮搜索结果
├── merged_results.json # 合并去重后结果
└── generate_excel.js # Excel 生成脚本A: 检查 API Key 是否正确配置,或尝试使用其他 provider
A: 大多数期刊需要订阅,使用 Europe PMC 作为备选
A: 使用 --source pubmed 或 --source openalex 绕过
A: 确保每行独立完整,不使用"同上"或"同V3a"等依赖表述
教授级搜索不仅是找文献,而是系统性构建知识体系。核心原则:
根据研究目的确定重点癌种:
| 优先级 | 癌种 | 常见融合基因 |
|---|---|---|
| 高 | 肺癌 | EML4-ALK, ROS1融合, RET, MET, NTRK |
| 高 | 结直肠癌 | RSPO融合, NTRK, ALK |
| 高 | 乳腺癌 | ESR1, NTRK, ETV6-NTRK3 |
| 中 | 胆管癌 | FGFR2融合, TFG-MET |
| 中 | 胃肠道间质瘤 | KIT, PDGFRA, NTRK |
| 泛癌 | 实体瘤 | NTRK1/2/3, BRAF, NRG1 |
每个癌种执行深度搜索:
# 肺癌融合基因深度搜索
~/.bun/bin/bun run cli.ts search "lung cancer fusion gene 2024 2025" --limit 20
~/.bun/bin/bun run cli.ts search "ROS1 CD74 fusion lung cancer clinical" --limit 10
~/.bun/bin/bun run cli.ts search "EML4-ALK variant V1 V3 breakpoint" --limit 10
# 结直肠癌融合基因
~/.bun/bin/bun run cli.ts search "colorectal cancer fusion gene RSPO Wnt" --limit 15
# 乳腺癌融合基因
~/.bun/bin/bun run cli.ts search "breast cancer fusion gene NTRK ESR1" --limit 15
# 胆管癌/胆囊癌融合
~/.bun/bin/bun run cli.ts search "biliary cancer FGFR2 fusion MET" --limit 15
# 胃肠道间质瘤
~/.bun/bin/bun run cli.ts search "GIST KIT PDGFRA NTRK fusion" --limit 15
# 泛癌种/罕见实体瘤
~/.bun/bin/bun run cli.ts search "solid tumor NTRK fusion basket trial" --limit 15
~/.bun/bin/bun run cli.ts search "NUT carcinoma fusion gene" --limit 10针对每个发现的融合,搜索其临床意义:
# 靶向治疗响应
~/.bun/bin/bun run cli.ts search "[融合名] TKI response targeted therapy" --limit 5
# 耐药机制
~/.bun/bin/bun run cli.ts search "[融合名] resistance crizotinib alectinib" --limit 5
# 诊断价值
~/.bun/bin/bun run cli.ts search "[融合名] diagnostic biomarker" --limit 5
# 预后意义
~/.bun/bin/bun run cli.ts search "[融合名] prognosis survival" --limit 5教授级搜索结果必须采用以下格式:
## [癌种名称] (英文)
| 融合 | 临床意义 | PMID |
| ---- | -------- | ---- |
| [融合名称1] | [具体临床意义描述] | [PMID1] |
| [融合名称2] | [具体临床意义描述] | [PMID2] |肺癌 (Lung Cancer)
| 融合 | 临床意义 | PMID |
| ----------- | --------------------- | -------- |
| ROS1-CD74 | 新融合伙伴,部分TKI有效 | 36387218 |
| HIPK2::YAP1 | 肺纤维瘤病新实体 | 38714933 |
| BRAF融合变异体 | DNA+RNA测序揭示结构 | 40253487 |
| ETV6::NTRK3 | 非典型类癌,repotrectinib有效 | 38113652 |
结直肠癌 (Colorectal Cancer)
| 融合 | 临床意义 | PMID |
| ------ | ------- | -------- |
| RSPO融合 | Wnt通路激活 | 35715628 |
| 新型结构变异 | 长读测序发现 | 36812239 |在输出最终结果前,检查以下要点:
| 维度 | 传统搜索 | 教授级搜索 |
|---|---|---|
| 组织方式 | 按基因 | 按癌种/临床场景 |
| 信息深度 | 基因+频率 | 融合+临床意义+药物 |
| 证据追溯 | 可选 | 必含PMID |
| 时间维度 | 无要求 | 优先新发现 |
| 输出格式 | 自由文本 | 标准化表格 |
© LeoYeAI, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
SKILL.md and 4 other files in skills/scholargraph-cancer-fusiongenes-research-flow of LeoYeAI/openclaw-master-skills.
Open the folder on GitHubat commit e5199b5
Scholargraph Fusion Genes 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 |
|---|---|---|---|---|---|---|
| Scholargraph Fusion Genes this skillLeoYeAI/openclaw-master-skills | 2.2k | — | ~3.2k | Automated safety check: Notes | MIT | |
| MarkitdownImCa0/just-laws | 781 | 14 repos | ~3.2k | Automated safety check: Notes | MIT | |
| Data Table Managern8n-io/n8n | 207k | — | ~2.3k | Automated safety check: Pass | Custom licence | |
| Docx4jplutext/docx4j | 2.4k | — | ~2.5k | Automated safety check: Pass | None | |
| Instrument Data To Allotropeaws-samples/amazon-bedrock-agents-healthcare-lifesciences | 274 | 2 repos | ~2.7k | Automated safety check: Pass | Apache-2.0 | |
| Cyber Pptcrazyykhllc-bit/CyberPPT | 1.8k | — | ~10k | Automated safety check: Pass | MIT |
ImCa0/just-laws
Convert files and office documents to Markdown. An agent skill from ImCa0/just-laws.
n8n-io/n8n
Load before calling data-tables or parse-file. An agent skill from n8n-io/n8n.
plutext/docx4j
A skill your agent uses when writing Java code that creates, reads or edits Word (.docx), PowerPoint (.pptx) or Excel (.xlsx) files with docx4j — including generating documents, editing existing…
aws-samples/amazon-bedrock-agents-healthcare-lifesciences
Convert laboratory instrument output files (PDF, CSV, Excel, TXT) to Allotrope Simple Model (ASM) JSON format or flattened 2D CSV.
crazyykhllc-bit/CyberPPT
当用户需要把 DOCX、PDF、TXT、XLSX、研究报告、业务材料或原始数据转成高密度、可编辑、咨询风格 PPTX 时使用;也适用于需要 SCR 论证、视觉风格探索、详细图表和渲染质检的 PPT。
zai-org/ZCode
Professional PDF toolkit covering four production workflows: reports, creative visuals, academic LaTeX, and existing PDF processing.
LeoYeAI/openclaw-master-skills
Manages pipelines on a DevOps quality and efficiency platform through its OpenAPI: list workspaces and templates, create, update, run and cancel pipelines, and read run records.
LeoYeAI/openclaw-master-skills
Patches OpenClaw's Feishu extension so an edited document triggers an isolated agent session that reads the doc and replies inline, turning it into a live chat space.
LeoYeAI/openclaw-master-skills
Multi-context memory management system for OpenClaw agents with group-isolated storage, global shared memory, workspace organization, and group-specific skills isolation.
LeoYeAI/openclaw-master-skills
Runs a brand's AI-search visibility work end to end: diagnosing how AI platforms represent it, repositioning it, producing AI-optimized content and monitoring ongoing mentions.
LeoYeAI/openclaw-master-skills
Installs and authenticates the gws CLI, then automates Gmail, Drive, Sheets, Calendar, Docs, Chat and Tasks with ready-made recipes, persona bundles and security audits.
LeoYeAI/openclaw-master-skills
Runs four advisor roles, a fitness coach, nutritionist, data analyst and TCM practitioner, to build a health profile and track workouts, diet and wellness over time.
Works with
Categories
使用 ScholarGraph v1.4 及以上版本 进行癌症融合基因文献调研的全流程技能。包括搜索、多轮合并去重、提取信息、生成报告和 Excel 表格。. Scholargraph Fusion Genes is an agent skill from LeoYeAI/openclaw-master-skills.
Scholargraph Fusion Genes fits situations like: tasks that involve Excel spreadsheets.
Run `npx skills add LeoYeAI/openclaw-master-skills --skill scholargraph-fusion-genes -a claude-code`. Or copy the skill folder (skills/scholargraph-cancer-fusiongenes-research-flow in LeoYeAI/openclaw-master-skills) into .claude/skills/scholargraph-fusion-genes in your project. Claude Code loads it when a task matches its description.
Run `npx skills add LeoYeAI/openclaw-master-skills --skill scholargraph-fusion-genes -a codex`. Or copy the skill folder (skills/scholargraph-cancer-fusiongenes-research-flow in LeoYeAI/openclaw-master-skills) into .agents/skills/scholargraph-fusion-genes in your project. Codex loads it when a task matches its description.
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add LeoYeAI/openclaw-master-skills --skill scholargraph-fusion-genes -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/scholargraph-fusion-genes, .gemini/skills/scholargraph-fusion-genes, .github/skills/scholargraph-fusion-genes and .opencode/skills/scholargraph-fusion-genes in your project.
Going by SKILL.md and its folder, Scholargraph Fusion Genes needs JavaScript for the scripts in its folder, the command-line tools its instructions call (bun, node, curl and npm) and credentials named MINIMAX_API_KEY and SERPER_API_KEY. Our summary lists: Node.js; A credential in MINIMAX_API_KEY; A credential in SERPER_API_KEY.
SKILL.md names 2 domains. In commands or code: europepmc.org and api.minimaxi.com; the agent is likely to contact these when it follows the instructions. This is read from the text; nothing was executed.
Our automated static check of SKILL.md found notes only (mentions a .env file), nothing it rates as a warning. It is not a guarantee. Review the folder before installing.
Scholargraph Fusion Genes is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
About 3.2k tokens (SKILL.md is roughly 13k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.
Skills that share tags, products or a category with Scholargraph Fusion Genes: Markitdown (ImCa0/just-laws, 781 stars), Data Table Manager (n8n-io/n8n, 207k stars), Docx4j (plutext/docx4j, 2.4k stars) and Instrument Data To Allotrope (aws-samples/amazon-bedrock-agents-healthcare-lifesciences, 274 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
LeoYeAI (a GitHub user) maintains it in LeoYeAI/openclaw-master-skills, which has 2,161 GitHub stars. The repository holds 1,235 skills in this directory. The repository was last updated on July 20, 2026.
Source: LeoYeAI/openclaw-master-skills on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.