一键导入
crawl-api-spec
Crawls exchange API documentation and generates structured markdown specs. Use when integrating a new exchange or updating API specifications.
用 Codex 或 Claude 帮你安装 复制这段 Prompt,粘贴到 Codex、Claude 或其他助手里,让它检查 Skill 页面并帮你完成安装。
菜单
Crawls exchange API documentation and generates structured markdown specs. Use when integrating a new exchange or updating API specifications.
用 Codex 或 Claude 帮你安装 复制这段 Prompt,粘贴到 Codex、Claude 或其他助手里,让它检查 Skill 页面并帮你完成安装。
基于 SOC 职业分类
Generates numbered SQL migration files for tables, indexes, and views. Use when adding or modifying database schema.
Systematically diagnoses build, runtime, DB, API, and frontend errors with classification and fix workflow. Use when encountering errors or test failures.
Commits code changes with automated CHANGELOG and design document updates. Runs build/lint verification before commit. Use after completing a feature, bug fix, or refactoring.
Scaffolds a new API endpoint with router, handler, OpenAPI docs, and TS bindings. Use when adding REST endpoints to trader-api.
Scaffolds a new exchange connector with connector, provider, and trait implementations. Use when integrating a new exchange.
Adds a new trading strategy across 5 locations (mod.rs, routes, backtest, SDUI schema, frontend). Use when implementing a new strategy.
| name | crawl-api-spec |
| description | Crawls exchange API documentation and generates structured markdown specs. Use when integrating a new exchange or updating API specifications. |
| disable-model-invocation | true |
| user-invocable | true |
| argument-hint | <서비스명> <문서URL> [출력파일경로] |
| allowed-tools | mcp__playwright__*, Write, Read |
| context | fork |
$ARGUMENTS 형식: <서비스명> <문서URL> [출력파일경로]
예시:
upbit https://docs.upbit.com/kr/reference docs/exchange/upbit_openapi_spec.mdbithumb https://apidocs.bithumb.com docs/exchange/bithumb_openapi_spec.mdkis https://apiportal.koreainvestment.com docs/exchange/kis_openapi_spec.mdbrowser_navigate로 문서 URL 접속browser_snapshot으로 페이지 구조 확인 (사이드바 네비게이션, API 카테고리)browser_run_code를 사용하여 배치 단위(4~7개 페이지)로 크롤링:
async (page) => {
const pages = ['url1', 'url2', ...];
const results = {};
for (const p of pages) {
await page.goto(p, { waitUntil: 'domcontentloaded', timeout: 15000 });
await page.waitForTimeout(1500);
const content = await page.evaluate(() => {
const article = document.querySelector('article') || document.querySelector('main') || document.body;
return article.innerText.substring(0, 5000);
});
results[p] = content;
}
return JSON.stringify(results);
}
browser_wait_for 사용하여 특정 텍스트 로딩 대기browser_evaluate로 DOM 직접 탐색[크롤링 불가 - 수동 확인 필요]로 표시innerText 기반 추출 후 파싱출력 템플릿은 output-template.md를 참조합니다.
| 상황 | 대응 |
|---|---|
| 사이트 접속 불가 | 3회 재시도 후 실패 보고 |
| 약관/CAPTCHA 차단 | 사용자에게 수동 통과 요청 |
| 내용 누락 | [미확인 - 수동 확인 필요]로 표시 |
| Rate Limit | 배치 간 3초 대기 |