[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7F9QMYY8QE4Z1YN4VT900QK":3,"skill-same:01M7F9QMYY8QE4Z1YN4VT900QK":93},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":16,"categories":17,"keywords":18,"publishedAt":19,"linkOnly":20,"markdownContent":21,"markdownBody":22,"frontMatter":23,"refName":29,"commitSha":30,"skillDirectory":31,"forksCount":32,"repositoryHtmlUrl":33,"repositoryHomepageUrl":6,"ownerHtmlUrl":34,"ownerBlogUrl":6,"ownerDescription":35,"updatedAt":36,"install":37,"resources":50},"01M7F9QMYY8QE4Z1YN4VT900QK","hasdata",null,"Use HasData APIs for web scraping and structured web data extraction.","lza6\u002FArmor-piercing-system-prompts","lza6","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F128880206?v=4","01M7EB3K7WPX5T28EJ2NVHE6EG","Chinese-tingfeng","01M7EB3K97E1KQ16QWKJMFNGX8",11,"MIT","https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F06-前端与设计\u002Fhasdata\u002FSKILL.md",[],[],"2026-11-16 10:05:34",false,"---\nname: hasdata\ndescription: Use HasData APIs for web scraping and structured web data extraction.\nrisk: safe\nsource: official\nsource_type: official\nsource_repo: HasData\u002Fhasdata-cli\nlicense: MIT\nlicense_source: \"https:\u002F\u002Fgithub.com\u002FHasData\u002Fhasdata-cli\u002Fblob\u002Fmain\u002FLICENSE\"\ndate_added: \"2026-06-04\"\n---\n\n# HasData\n\nCloud platform for extracting public web data. One API key, three execution modes. All endpoints sit under `https:\u002F\u002Fapi.hasdata.com` and authenticate with `x-api-key`.\n\n```bash\ncurl -G 'https:\u002F\u002Fapi.hasdata.com\u002Fscrape\u002Fgoogle\u002Fserp' \\\n  --data-urlencode 'q=coffee' \\\n  -H 'x-api-key: \u003Cyour-api-key>'\n```\n\n`401` invalid key, `403` quota exhausted, `429` concurrency cap, `500` server error (retry).\n\n## When to Use\n\nUse this skill when:\n\n- The user needs web scraping.\n- The user needs search engine results.\n- The user needs structured data extraction.\n- The user needs ecommerce, travel, jobs, or local business data.\n- The user explicitly asks about HasData.\n\n## Three execution modes\n\n| Mode | Latency | When | Endpoint |\n|---|---|---|---|\n| **Web Scraping API** | seconds | Arbitrary URL — JS rendering, CSS\u002FAI extraction, screenshots | `POST \u002Fscrape\u002Fweb` |\n| **Scraper APIs** (sync) | seconds | Pre-parsed JSON for known platforms (Google, Amazon, Zillow, …) | `GET \u002Fscrape\u002F\u003Cvertical>\u002F\u003Cresource>` |\n| **Scraper Jobs** (async) | minutes–hours | Bulk extraction, recursive crawling, webhook fan-out | `POST \u002Fscrapers\u002F\u003Cslug>\u002Fjobs` |\n\n**Decision rule.** Default to a **Scraper API** when one exists for the platform (pre-parsed JSON, no selector maintenance). Use **Web Scraping** for arbitrary URLs not covered by an API. Reach for a **Scraper Job** only when no API equivalent exists — `crawler`, `contacts`, `sec-edgar`, `amazon-bestsellers`, `amazon-product-reviews` — *or* when async fan-out + webhooks save engineering time over a paginated client loop.\n\n## Always-true response shape\n\n```json\n{ \"requestMetadata\": { \"id\": \"…\", \"status\": \"ok\", \"url\": \"…\" }, \"...\": \"endpoint-specific\" }\n```\n\nTreat data as valid only if `requestMetadata.status === \"ok\"`. HTTP 200 alone isn't enough.\n\n## High-leverage patterns\n\n- **SERP-first enrichment.** Google SERP can surface public snippets for company and professional-profile lookup. Use it for business or authorized research, avoid unnecessary direct scraping, and treat personal email\u002Fphone lookup as allowed only with a legitimate purpose and user authorization.\n- **AI Mode + verify.** `\u002Fscrape\u002Fgoogle\u002Fai-mode` for the answer + references → `\u002Fscrape\u002Fweb` (markdown) on each reference URL → cited RAG context, no vector DB.\n- **Maps → leads.** `\u002Fscrape\u002Fgoogle-maps\u002Fsearch` returns business websites and phones; collect contact details only from public, permitted sources and apply opt-out, rate, and privacy-law constraints before any outreach use.\n- **Crawler → corpus.** `crawler` Scraper Job with `outputFormat: [\"markdown\"]` + `includePaths: \"\u002Fdocs\u002F.+\"` produces an LLM-ready corpus in one submission.\n- **Pre-extracted via SERP rich snippets.** `knowledgeGraph`, `localResults`, `inlineShoppingResults`, `relatedQuestions` carry pre-parsed public facts. Always check them before considering direct page access.\n\n## When to call from code (the wiring)\n\n- **Auth:** `x-api-key` header on every request. Read from `HASDATA_API_KEY` env. Never hardcode, never log.\n- **Timeouts:** **set client timeout ≥ 300 s.** HasData's own deadline is 300 s; shorter clients produce phantom failures while still being billed on completion.\n- **Retries:** `429` and `5xx` only — exponential backoff, jitter. Never retry `4xx` (auth, validation).\n- **Concurrency:** cap at your plan limit. The free tier is 1; anything higher just generates `429`s.\n- **Async jobs:** the submit response handle is `body.id` (integer), **not `jobId`**. Persist it immediately. Poll `GET \u002Fscrapers\u002Fjobs\u002F\u003Cid>` every 10–30 s with backoff; treat webhooks as best-effort and always pair with polling. On `finished` the status carries `data: {csv, json, xlsx}` short-lived URLs — download immediately.\n\nSee `references\u002Fcode-recipes.md` for ready-to-paste Python and TypeScript clients with retry, backoff, bounded concurrency, and the full job lifecycle.\n\n## Common gotchas\n\n- **300 s server deadline.** Match client timeout.\n- **Disable `jsRendering` first**, enable only if the page needs it — most static pages parse fine without a headless browser.\n- **No `cookies` parameter** — cookies go through `headers[\"Cookie\"]`.\n- **`includePaths` regex is case-sensitive.** `\u002Fblog\u002F.+` won't match `\u002FBlog\u002F...`.\n- **Scraper Job `data` is double-wrapped.** Each row is `body.data[i].data`; outer wraps with `id`, `jobId`, `dataId`, `createdAt`, `updatedAt`.\n- **`requestMetadata.status === \"ok\"` is the only success signal.** HTTP 200 alone isn't enough.\n- **Webhooks are best-effort with 3 retries.** Always have a polling fallback.\n\n## References\n\n- [`references\u002Fweb-scraping.md`](references\u002Fweb-scraping.md) — `POST \u002Fscrape\u002Fweb` parameters, JS scenarios, AI extraction, cookie auth.\n- [`references\u002Fsearch.md`](references\u002Fsearch.md) — Google SERP \u002F Light \u002F AI Mode \u002F News \u002F Shopping \u002F Bing \u002F Trends + pagination.\n- [`references\u002Fecommerce.md`](references\u002Fecommerce.md) — Amazon (product, search, seller, seller-products) and Shopify.\n- [`references\u002Freal-estate.md`](references\u002Freal-estate.md) — Zillow, Redfin (bracketed filters).\n- [`references\u002Ftravel.md`](references\u002Ftravel.md) — Airbnb, Booking, Google Flights (occupancy rules, token pagination, IATA codes).\n- [`references\u002Flocal-business.md`](references\u002Flocal-business.md) — Maps (search\u002Fplace\u002Freviews\u002Fphotos\u002Fposts), Yelp, YellowPages.\n- [`references\u002Fjobs.md`](references\u002Fjobs.md) — Indeed and Glassdoor.\n- [`references\u002Fyoutube.md`](references\u002Fyoutube.md) — YouTube search \u002F video \u002F channel \u002F transcript.\n- [`references\u002Fscraper-jobs.md`](references\u002Fscraper-jobs.md) — async submit\u002Fpoll\u002Fresults, Crawler, Contacts, SEC EDGAR, webhook receiver.\n- [`references\u002Fcode-recipes.md`](references\u002Fcode-recipes.md) — Python \u002F TypeScript clients with retry, backoff, concurrency, polling.\n\n## Resources\n\n- Sitemap: \u003Chttps:\u002F\u002Fdocs.hasdata.com\u002Fllms.txt>\n- API status codes: \u003Chttps:\u002F\u002Fdocs.hasdata.com\u002Fapi-codes>\n- Credits & concurrency: \u003Chttps:\u002F\u002Fdocs.hasdata.com\u002Fcredits-and-concurrency>\n- Dashboard: \u003Chttps:\u002F\u002Fapp.hasdata.com>\n\n## Limitations\n\n* Requires access to HasData services and valid credentials.\n* Data quality and available fields depend on the target website and extraction method used.\n* JavaScript-heavy websites may require rendering, which can affect performance and cost.\n* Use only for public data or content the user is authorized to access; respect site terms, robots\u002Faccess controls, privacy law, and rate limits.\n* Rate limits, quotas, and account restrictions may apply depending on the endpoint and subscription plan.\n","# HasData\n\nCloud platform for extracting public web data. One API key, three execution modes. All endpoints sit under `https:\u002F\u002Fapi.hasdata.com` and authenticate with `x-api-key`.\n\n```bash\ncurl -G 'https:\u002F\u002Fapi.hasdata.com\u002Fscrape\u002Fgoogle\u002Fserp' \\\n  --data-urlencode 'q=coffee' \\\n  -H 'x-api-key: \u003Cyour-api-key>'\n```\n\n`401` invalid key, `403` quota exhausted, `429` concurrency cap, `500` server error (retry).\n\n## When to Use\n\nUse this skill when:\n\n- The user needs web scraping.\n- The user needs search engine results.\n- The user needs structured data extraction.\n- The user needs ecommerce, travel, jobs, or local business data.\n- The user explicitly asks about HasData.\n\n## Three execution modes\n\n| Mode | Latency | When | Endpoint |\n|---|---|---|---|\n| **Web Scraping API** | seconds | Arbitrary URL — JS rendering, CSS\u002FAI extraction, screenshots | `POST \u002Fscrape\u002Fweb` |\n| **Scraper APIs** (sync) | seconds | Pre-parsed JSON for known platforms (Google, Amazon, Zillow, …) | `GET \u002Fscrape\u002F\u003Cvertical>\u002F\u003Cresource>` |\n| **Scraper Jobs** (async) | minutes–hours | Bulk extraction, recursive crawling, webhook fan-out | `POST \u002Fscrapers\u002F\u003Cslug>\u002Fjobs` |\n\n**Decision rule.** Default to a **Scraper API** when one exists for the platform (pre-parsed JSON, no selector maintenance). Use **Web Scraping** for arbitrary URLs not covered by an API. Reach for a **Scraper Job** only when no API equivalent exists — `crawler`, `contacts`, `sec-edgar`, `amazon-bestsellers`, `amazon-product-reviews` — *or* when async fan-out + webhooks save engineering time over a paginated client loop.\n\n## Always-true response shape\n\n```json\n{ \"requestMetadata\": { \"id\": \"…\", \"status\": \"ok\", \"url\": \"…\" }, \"...\": \"endpoint-specific\" }\n```\n\nTreat data as valid only if `requestMetadata.status === \"ok\"`. HTTP 200 alone isn't enough.\n\n## High-leverage patterns\n\n- **SERP-first enrichment.** Google SERP can surface public snippets for company and professional-profile lookup. Use it for business or authorized research, avoid unnecessary direct scraping, and treat personal email\u002Fphone lookup as allowed only with a legitimate purpose and user authorization.\n- **AI Mode + verify.** `\u002Fscrape\u002Fgoogle\u002Fai-mode` for the answer + references → `\u002Fscrape\u002Fweb` (markdown) on each reference URL → cited RAG context, no vector DB.\n- **Maps → leads.** `\u002Fscrape\u002Fgoogle-maps\u002Fsearch` returns business websites and phones; collect contact details only from public, permitted sources and apply opt-out, rate, and privacy-law constraints before any outreach use.\n- **Crawler → corpus.** `crawler` Scraper Job with `outputFormat: [\"markdown\"]` + `includePaths: \"\u002Fdocs\u002F.+\"` produces an LLM-ready corpus in one submission.\n- **Pre-extracted via SERP rich snippets.** `knowledgeGraph`, `localResults`, `inlineShoppingResults`, `relatedQuestions` carry pre-parsed public facts. Always check them before considering direct page access.\n\n## When to call from code (the wiring)\n\n- **Auth:** `x-api-key` header on every request. Read from `HASDATA_API_KEY` env. Never hardcode, never log.\n- **Timeouts:** **set client timeout ≥ 300 s.** HasData's own deadline is 300 s; shorter clients produce phantom failures while still being billed on completion.\n- **Retries:** `429` and `5xx` only — exponential backoff, jitter. Never retry `4xx` (auth, validation).\n- **Concurrency:** cap at your plan limit. The free tier is 1; anything higher just generates `429`s.\n- **Async jobs:** the submit response handle is `body.id` (integer), **not `jobId`**. Persist it immediately. Poll `GET \u002Fscrapers\u002Fjobs\u002F\u003Cid>` every 10–30 s with backoff; treat webhooks as best-effort and always pair with polling. On `finished` the status carries `data: {csv, json, xlsx}` short-lived URLs — download immediately.\n\nSee `references\u002Fcode-recipes.md` for ready-to-paste Python and TypeScript clients with retry, backoff, bounded concurrency, and the full job lifecycle.\n\n## Common gotchas\n\n- **300 s server deadline.** Match client timeout.\n- **Disable `jsRendering` first**, enable only if the page needs it — most static pages parse fine without a headless browser.\n- **No `cookies` parameter** — cookies go through `headers[\"Cookie\"]`.\n- **`includePaths` regex is case-sensitive.** `\u002Fblog\u002F.+` won't match `\u002FBlog\u002F...`.\n- **Scraper Job `data` is double-wrapped.** Each row is `body.data[i].data`; outer wraps with `id`, `jobId`, `dataId`, `createdAt`, `updatedAt`.\n- **`requestMetadata.status === \"ok\"` is the only success signal.** HTTP 200 alone isn't enough.\n- **Webhooks are best-effort with 3 retries.** Always have a polling fallback.\n\n## References\n\n- [`references\u002Fweb-scraping.md`](references\u002Fweb-scraping.md) — `POST \u002Fscrape\u002Fweb` parameters, JS scenarios, AI extraction, cookie auth.\n- [`references\u002Fsearch.md`](references\u002Fsearch.md) — Google SERP \u002F Light \u002F AI Mode \u002F News \u002F Shopping \u002F Bing \u002F Trends + pagination.\n- [`references\u002Fecommerce.md`](references\u002Fecommerce.md) — Amazon (product, search, seller, seller-products) and Shopify.\n- [`references\u002Freal-estate.md`](references\u002Freal-estate.md) — Zillow, Redfin (bracketed filters).\n- [`references\u002Ftravel.md`](references\u002Ftravel.md) — Airbnb, Booking, Google Flights (occupancy rules, token pagination, IATA codes).\n- [`references\u002Flocal-business.md`](references\u002Flocal-business.md) — Maps (search\u002Fplace\u002Freviews\u002Fphotos\u002Fposts), Yelp, YellowPages.\n- [`references\u002Fjobs.md`](references\u002Fjobs.md) — Indeed and Glassdoor.\n- [`references\u002Fyoutube.md`](references\u002Fyoutube.md) — YouTube search \u002F video \u002F channel \u002F transcript.\n- [`references\u002Fscraper-jobs.md`](references\u002Fscraper-jobs.md) — async submit\u002Fpoll\u002Fresults, Crawler, Contacts, SEC EDGAR, webhook receiver.\n- [`references\u002Fcode-recipes.md`](references\u002Fcode-recipes.md) — Python \u002F TypeScript clients with retry, backoff, concurrency, polling.\n\n## Resources\n\n- Sitemap: \u003Chttps:\u002F\u002Fdocs.hasdata.com\u002Fllms.txt>\n- API status codes: \u003Chttps:\u002F\u002Fdocs.hasdata.com\u002Fapi-codes>\n- Credits & concurrency: \u003Chttps:\u002F\u002Fdocs.hasdata.com\u002Fcredits-and-concurrency>\n- Dashboard: \u003Chttps:\u002F\u002Fapp.hasdata.com>\n\n## Limitations\n\n* Requires access to HasData services and valid credentials.\n* Data quality and available fields depend on the target website and extraction method used.\n* JavaScript-heavy websites may require rendering, which can affect performance and cost.\n* Use only for public data or content the user is authorized to access; respect site terms, robots\u002Faccess controls, privacy law, and rate limits.\n* Rate limits, quotas, and account restrictions may apply depending on the endpoint and subscription plan.\n",{"name":5,"risk":24,"source":25,"license":15,"date_added":26,"description":7,"source_repo":27,"source_type":25,"license_source":28},"safe","official","2026-06-04","HasData\u002Fhasdata-cli","https:\u002F\u002Fgithub.com\u002FHasData\u002Fhasdata-cli\u002Fblob\u002Fmain\u002FLICENSE","main","d69096e239f2a89aabc2cd078c47664a9d3b1e11","06-前端与设计\u002Fhasdata",3,"https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts","https:\u002F\u002Fgithub.com\u002Flza6","个人vx：Tf00798\r\n个人✈：@TFGY999","2026-10-08 14:29:22",{"source":8,"skillName":5,"commands":38,"prompt":48,"zipAvailable":49},[39,42,45],{"tool":40,"command":41},"npx","npx skills add lza6\u002FArmor-piercing-system-prompts --skill hasdata",{"tool":43,"command":44},"bunx","bunx skills add lza6\u002FArmor-piercing-system-prompts --skill hasdata",{"tool":46,"command":47},"pnpm","pnpm dlx skills add lza6\u002FArmor-piercing-system-prompts --skill hasdata","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F06-前端与设计\u002Fhasdata\u002FSKILL.md",true,[51,57,61,65,69,73,77,81,85,89],{"path":52,"resourceType":53,"resourceTypeDesc":54,"sizeBytes":55,"sourceHtmlUrl":56},"references\u002Fcode-recipes.md","REFERENCE","参考文档",5523,"https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F06-前端与设计\u002Fhasdata\u002Freferences\u002Fcode-recipes.md",{"path":58,"resourceType":53,"resourceTypeDesc":54,"sizeBytes":59,"sourceHtmlUrl":60},"references\u002Fecommerce.md",4134,"https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F06-前端与设计\u002Fhasdata\u002Freferences\u002Fecommerce.md",{"path":62,"resourceType":53,"resourceTypeDesc":54,"sizeBytes":63,"sourceHtmlUrl":64},"references\u002Fjobs.md",3151,"https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F06-前端与设计\u002Fhasdata\u002Freferences\u002Fjobs.md",{"path":66,"resourceType":53,"resourceTypeDesc":54,"sizeBytes":67,"sourceHtmlUrl":68},"references\u002Flocal-business.md",5492,"https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F06-前端与设计\u002Fhasdata\u002Freferences\u002Flocal-business.md",{"path":70,"resourceType":53,"resourceTypeDesc":54,"sizeBytes":71,"sourceHtmlUrl":72},"references\u002Freal-estate.md",2742,"https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F06-前端与设计\u002Fhasdata\u002Freferences\u002Freal-estate.md",{"path":74,"resourceType":53,"resourceTypeDesc":54,"sizeBytes":75,"sourceHtmlUrl":76},"references\u002Fscraper-jobs.md",8649,"https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F06-前端与设计\u002Fhasdata\u002Freferences\u002Fscraper-jobs.md",{"path":78,"resourceType":53,"resourceTypeDesc":54,"sizeBytes":79,"sourceHtmlUrl":80},"references\u002Fsearch.md",5307,"https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F06-前端与设计\u002Fhasdata\u002Freferences\u002Fsearch.md",{"path":82,"resourceType":53,"resourceTypeDesc":54,"sizeBytes":83,"sourceHtmlUrl":84},"references\u002Ftravel.md",8348,"https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F06-前端与设计\u002Fhasdata\u002Freferences\u002Ftravel.md",{"path":86,"resourceType":53,"resourceTypeDesc":54,"sizeBytes":87,"sourceHtmlUrl":88},"references\u002Fweb-scraping.md",6741,"https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F06-前端与设计\u002Fhasdata\u002Freferences\u002Fweb-scraping.md",{"path":90,"resourceType":53,"resourceTypeDesc":54,"sizeBytes":91,"sourceHtmlUrl":92},"references\u002Fyoutube.md",7144,"https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F06-前端与设计\u002Fhasdata\u002Freferences\u002Fyoutube.md",[94,101,106,113,120,127],{"skillNo":95,"name":96,"nameZh":6,"description":97,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":98,"categories":99,"keywords":100,"publishedAt":19},"01M7FFG485KY83TD6HSC4YPCMC","obsidian-clipper-template-creator","Guide for creating templates for the Obsidian Web Clipper. Use when you want to create a new clipping template, understand available variables, or format clipped content.","https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F07-后端与架构\u002Fobsidian-clipper-template-creator\u002FSKILL.md",[],[],{"skillNo":102,"name":96,"nameZh":6,"description":97,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":103,"categories":104,"keywords":105,"publishedAt":19},"01M7FFG0T6AZ0STEJPSB3CX84K","https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F07-后端与架构\u002Fobsidian-clipper-template-creator-antigravity-awesome-skills-main\u002FSKILL.md",[],[],{"skillNo":107,"name":108,"nameZh":6,"description":109,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":110,"categories":111,"keywords":112,"publishedAt":19},"01M7FFFY0QEM14SKWPDYGMXM2P","python-api","Programmatic Object-Detection-Metrics API guidance for BoundingBox, BoundingBoxes, Evaluator, enums, coordinate conversion, AP\u002FmAP semantics, and source-style import diagnostics.","https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F07-后端与架构\u002Fobject-detection-metrics\u002Fsub-skills\u002Fpython-api\u002FSKILL.md",[],[],{"skillNo":114,"name":115,"nameZh":6,"description":116,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":117,"categories":118,"keywords":119,"publishedAt":19},"01M7FFFVZQZ2GJ0C0TGP7JHD20","file-evaluation","Folder-based PASCAL VOC AP\u002FmAP evaluation from ground-truth and detection text files.","https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F07-后端与架构\u002Fobject-detection-metrics\u002Fsub-skills\u002Ffile-evaluation\u002FSKILL.md",[],[],{"skillNo":121,"name":122,"nameZh":6,"description":123,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":124,"categories":125,"keywords":126,"publishedAt":19},"01M7FFFSFNYSE77SJ6PE1CK2DA","object-detection-metrics","Guides legacy Object-Detection-Metrics PASCAL VOC AP\u002FmAP evaluation from detection text folders and direct Python API classes.","https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F07-后端与架构\u002Fobject-detection-metrics\u002FSKILL.md",[],[],{"skillNo":128,"name":129,"nameZh":6,"description":130,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":131,"categories":132,"keywords":133,"publishedAt":19},"01M7FFFP0GCK1RVXBCPQ8APBMT","nx-workspace-patterns","Configure and optimize Nx monorepo workspaces. Use when setting up Nx, configuring project boundaries, optimizing build caching, or implementing affected commands.","https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F07-后端与架构\u002Fnx-workspace-patterns\u002FSKILL.md",[],[]]