[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M75BJQKXWGR2HHS1RTY7BPVB":3,"skill-same:01M75BJQKXWGR2HHS1RTY7BPVB":58},{"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":24,"commitSha":25,"skillDirectory":26,"forksCount":14,"repositoryHtmlUrl":27,"repositoryHomepageUrl":6,"ownerHtmlUrl":28,"ownerBlogUrl":29,"ownerDescription":30,"updatedAt":31,"install":32,"resources":45},"01M75BJQKXWGR2HHS1RTY7BPVB","a-share-data",null,"Fetch A-share quotes, K-lines, and filings. Use when the user asks for A-share market data.","Yaphet2015\u002Fya-skills","Yaphet2015","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F17684609?v=4","01M75BHXC36T9EZJ2Y3DRRRH1E","Yaphet Y","01M75BHXCMYQ20CST1Z22JV099",0,"MIT","https:\u002F\u002Fgithub.com\u002FYaphet2015\u002Fya-skills\u002Fblob\u002Fmain\u002Fskills\u002Fa-share-data\u002FSKILL.md",[],[],"2026-11-12 13:55:43",false,"---\nname: a-share-data\ndescription: Fetch A-share quotes, K-lines, and filings. Use when the user asks for A-share market data.\n---\n\n# A-share Data Skill\n\nUse this skill when the user asks for A 股数据, Chinese stock quotes, K-line\u002Fhistory, 东方财富 F10 financials, public announcements, news evidence, valuation inputs, or a data pack for later investment analysis.\n\nThis skill is **data acquisition only**. It does not issue investment advice by itself. It prepares timestamped, provenance-rich data that other research or portfolio workflows can analyze.\n\n## Core Policy\n\n1. **Real data only.** Never fabricate prices, financials, valuation ratios, charts, holdings, or news. If an endpoint fails or a field is absent, record it as unavailable.\n2. **Record provenance.** Keep URL\u002Fvendor, fetch timestamp, stock code, market, adjustment mode, date range, and any errors for every source.\n3. **Treat vendor fields cautiously.** Public quote fields can be undocumented or change over time. Preserve raw fields when useful and label derived calculations clearly.\n4. **Do not blindly quote PE fields as static PE.** For A-shares, vendor PE fields may be TTM, dynamic, negative because of loss-making bases, or otherwise vendor-specific. If prior-year attributable net profit and total market cap are both available, compute a rough static PE yourself as `market_cap \u002F prior_year_parent_net_profit` and label it as an estimate.\n5. **Distinguish intraday from close.** Mark intraday quotes with the vendor timestamp. Do not present an intraday quote as a closing price.\n6. **Respect data gaps.** A missing or blocked source is a fact to report, not a reason to invent a substitute.\n\n## One-command workflow\n\nAfter installing the skill with `yk install a-share-data`, run from the installed skill directory:\n\n```sh\npython3 scripts\u002Fa_share_data.py 301236 --market SZ --output \u002Fabsolute\u002Fpath\u002F301236-data.json\n```\n\nCommon variants:\n\n```sh\n# Infer market from code prefix and fetch the default data pack\npython3 scripts\u002Fa_share_data.py 600519\n\n# Fetch only quote and daily K-line data for a date range\npython3 scripts\u002Fa_share_data.py 300750 --items quote,kline --start 2025-01-01 --end 2026-06-30\n\n# Fetch financial\u002Fannouncement evidence only\npython3 scripts\u002Fa_share_data.py 301236 --items financials,cashflow,announcements --limit 10\n```\n\nDefault output is JSON printed to stdout. Use `--output` to save the data pack for downstream reports.\n\n## Data sources covered\n\n| Data need | Primary public source | What to capture | Notes |\n| --- | --- | --- | --- |\n| Real-time quote | Sina `hq.sinajs.cn` | name, open, previous close, current price, high, low, volume, amount, date, time | Requires browser-like headers; usually GB18030. |\n| Quote \u002F valuation fields | Tencent `qt.gtimg.cn` | raw quote fields plus selected price\u002Fchange\u002Fturnover\u002Fmarket-cap\u002FPE\u002FPB-style fields when present | Preserve raw fields; field positions are vendor-specific. |\n| Daily K-line | Tencent `web.ifzq.gtimg.cn\u002Fappstock\u002Fapp\u002Ffqkline\u002Fget` | date, open, close, high, low, volume, amount when available | Use `qfq` by default unless a different adjustment is requested. |\n| Main financial indicators | Eastmoney F10 datacenter | revenue, parent net profit,扣非净利, margins, ROE, leverage, BPS when present | Query by `SECUCODE=\"000000.SZ\u002FSH\u002FBJ\"`; keep raw records. |\n| Cash flow | Eastmoney F10 datacenter | operating cash flow and related fields when present | Useful for checking profit\u002Fcash-flow divergence. |\n| Announcements | Eastmoney announcement API | recent official announcement titles, dates, URLs\u002FIDs when present | Prefer official announcement evidence over rumor\u002Fnews. |\n| News\u002Fsearch | Eastmoney search or other public search endpoints | headline, time, source, URL when body is unavailable | Treat headlines as weak signals unless the body is fetched and verified. |\n\n## Code and market normalization\n\nAccept any of these forms and normalize internally:\n\n- `301236`, `300750`, `600519`, `430047`\n- `sz301236`, `sh600519`, `bj430047`\n- `301236.SZ`, `600519.SH`, `430047.BJ`\n\nMarket inference default:\n\n- `6` \u002F `9` prefix → Shanghai (`SH`)\n- `0` \u002F `2` \u002F `3` prefix → Shenzhen (`SZ`)\n- `4` \u002F `8` prefix → Beijing (`BJ`)\n\nIf inference is ambiguous or wrong for a specific instrument, pass `--market SH|SZ|BJ` explicitly.\n\n## Recommended data-pack shape\n\nWhen saving data for a report, keep this shape:\n\n```json\n{\n  \"subject\": { \"code\": \"301236\", \"market\": \"SZ\", \"secucode\": \"301236.SZ\" },\n  \"fetched_at\": \"2026-06-30T...Z\",\n  \"sources\": {\n    \"sina_quote\": { \"url\": \"...\", \"data\": {}, \"error\": null },\n    \"tencent_quote\": { \"url\": \"...\", \"data\": {}, \"error\": null },\n    \"tencent_kline\": { \"url\": \"...\", \"data\": [], \"error\": null },\n    \"eastmoney_financials\": { \"url\": \"...\", \"data\": [], \"error\": null },\n    \"eastmoney_cashflow\": { \"url\": \"...\", \"data\": [], \"error\": null },\n    \"eastmoney_announcements\": { \"url\": \"...\", \"data\": [], \"error\": null }\n  },\n  \"derived\": [],\n  \"limitations\": []\n}\n```\n\n## Derivation rules\n\nOnly compute derived fields when inputs are present and units are clear enough:\n\n- Rough static PE: `total_market_cap \u002F prior_year_parent_net_profit`.\n- Return \u002F drawdown \u002F moving averages: compute from K-line closes and state adjustment mode (`qfq`, `hfq`, or raw\u002Fbfq).\n- Turnover\u002Fvolume interpretation: preserve vendor units; do not silently convert if units are unclear.\n\nEvery derived field must include:\n\n- formula\n- input fields and source names\n- timestamp\u002Fas-of date\n- limitations\n\n## Verification Checklist\n\nAfter fetching data:\n\n1. Confirm the command exits with status 0.\n2. Confirm each requested source has either non-empty `data` or an explicit `error`.\n3. Confirm quotes include a vendor date\u002Ftime or are labeled as missing\u002Fstale.\n4. Confirm K-line data range and adjustment mode match the request.\n5. Confirm financial records include report dates; do not mix annual and quarterly values without labels.\n6. Confirm all unavailable sources are listed in `limitations` or source-level `error` fields.\n7. Before using valuation ratios in analysis, check whether the ratio is vendor-supplied or self-computed and label it accordingly.\n\n## Common Pitfalls\n\n- Sina\u002FTencent endpoints may require `Referer` and `User-Agent`; retry with browser-like headers before declaring unavailable.\n- Chinese endpoints often use GBK\u002FGB18030 encoding.\n- JSONP endpoints need wrapper stripping before JSON parsing.\n- Eastmoney field names differ by report type and can change. Preserve raw records and map only fields you verify.\n- Recent news headline search is not the same as verified announcement evidence.\n- ETF\u002Ffund data uses different endpoint families; do not assume single-stock fields apply unchanged.\n","# A-share Data Skill\n\nUse this skill when the user asks for A 股数据, Chinese stock quotes, K-line\u002Fhistory, 东方财富 F10 financials, public announcements, news evidence, valuation inputs, or a data pack for later investment analysis.\n\nThis skill is **data acquisition only**. It does not issue investment advice by itself. It prepares timestamped, provenance-rich data that other research or portfolio workflows can analyze.\n\n## Core Policy\n\n1. **Real data only.** Never fabricate prices, financials, valuation ratios, charts, holdings, or news. If an endpoint fails or a field is absent, record it as unavailable.\n2. **Record provenance.** Keep URL\u002Fvendor, fetch timestamp, stock code, market, adjustment mode, date range, and any errors for every source.\n3. **Treat vendor fields cautiously.** Public quote fields can be undocumented or change over time. Preserve raw fields when useful and label derived calculations clearly.\n4. **Do not blindly quote PE fields as static PE.** For A-shares, vendor PE fields may be TTM, dynamic, negative because of loss-making bases, or otherwise vendor-specific. If prior-year attributable net profit and total market cap are both available, compute a rough static PE yourself as `market_cap \u002F prior_year_parent_net_profit` and label it as an estimate.\n5. **Distinguish intraday from close.** Mark intraday quotes with the vendor timestamp. Do not present an intraday quote as a closing price.\n6. **Respect data gaps.** A missing or blocked source is a fact to report, not a reason to invent a substitute.\n\n## One-command workflow\n\nAfter installing the skill with `yk install a-share-data`, run from the installed skill directory:\n\n```sh\npython3 scripts\u002Fa_share_data.py 301236 --market SZ --output \u002Fabsolute\u002Fpath\u002F301236-data.json\n```\n\nCommon variants:\n\n```sh\n# Infer market from code prefix and fetch the default data pack\npython3 scripts\u002Fa_share_data.py 600519\n\n# Fetch only quote and daily K-line data for a date range\npython3 scripts\u002Fa_share_data.py 300750 --items quote,kline --start 2025-01-01 --end 2026-06-30\n\n# Fetch financial\u002Fannouncement evidence only\npython3 scripts\u002Fa_share_data.py 301236 --items financials,cashflow,announcements --limit 10\n```\n\nDefault output is JSON printed to stdout. Use `--output` to save the data pack for downstream reports.\n\n## Data sources covered\n\n| Data need | Primary public source | What to capture | Notes |\n| --- | --- | --- | --- |\n| Real-time quote | Sina `hq.sinajs.cn` | name, open, previous close, current price, high, low, volume, amount, date, time | Requires browser-like headers; usually GB18030. |\n| Quote \u002F valuation fields | Tencent `qt.gtimg.cn` | raw quote fields plus selected price\u002Fchange\u002Fturnover\u002Fmarket-cap\u002FPE\u002FPB-style fields when present | Preserve raw fields; field positions are vendor-specific. |\n| Daily K-line | Tencent `web.ifzq.gtimg.cn\u002Fappstock\u002Fapp\u002Ffqkline\u002Fget` | date, open, close, high, low, volume, amount when available | Use `qfq` by default unless a different adjustment is requested. |\n| Main financial indicators | Eastmoney F10 datacenter | revenue, parent net profit,扣非净利, margins, ROE, leverage, BPS when present | Query by `SECUCODE=\"000000.SZ\u002FSH\u002FBJ\"`; keep raw records. |\n| Cash flow | Eastmoney F10 datacenter | operating cash flow and related fields when present | Useful for checking profit\u002Fcash-flow divergence. |\n| Announcements | Eastmoney announcement API | recent official announcement titles, dates, URLs\u002FIDs when present | Prefer official announcement evidence over rumor\u002Fnews. |\n| News\u002Fsearch | Eastmoney search or other public search endpoints | headline, time, source, URL when body is unavailable | Treat headlines as weak signals unless the body is fetched and verified. |\n\n## Code and market normalization\n\nAccept any of these forms and normalize internally:\n\n- `301236`, `300750`, `600519`, `430047`\n- `sz301236`, `sh600519`, `bj430047`\n- `301236.SZ`, `600519.SH`, `430047.BJ`\n\nMarket inference default:\n\n- `6` \u002F `9` prefix → Shanghai (`SH`)\n- `0` \u002F `2` \u002F `3` prefix → Shenzhen (`SZ`)\n- `4` \u002F `8` prefix → Beijing (`BJ`)\n\nIf inference is ambiguous or wrong for a specific instrument, pass `--market SH|SZ|BJ` explicitly.\n\n## Recommended data-pack shape\n\nWhen saving data for a report, keep this shape:\n\n```json\n{\n  \"subject\": { \"code\": \"301236\", \"market\": \"SZ\", \"secucode\": \"301236.SZ\" },\n  \"fetched_at\": \"2026-06-30T...Z\",\n  \"sources\": {\n    \"sina_quote\": { \"url\": \"...\", \"data\": {}, \"error\": null },\n    \"tencent_quote\": { \"url\": \"...\", \"data\": {}, \"error\": null },\n    \"tencent_kline\": { \"url\": \"...\", \"data\": [], \"error\": null },\n    \"eastmoney_financials\": { \"url\": \"...\", \"data\": [], \"error\": null },\n    \"eastmoney_cashflow\": { \"url\": \"...\", \"data\": [], \"error\": null },\n    \"eastmoney_announcements\": { \"url\": \"...\", \"data\": [], \"error\": null }\n  },\n  \"derived\": [],\n  \"limitations\": []\n}\n```\n\n## Derivation rules\n\nOnly compute derived fields when inputs are present and units are clear enough:\n\n- Rough static PE: `total_market_cap \u002F prior_year_parent_net_profit`.\n- Return \u002F drawdown \u002F moving averages: compute from K-line closes and state adjustment mode (`qfq`, `hfq`, or raw\u002Fbfq).\n- Turnover\u002Fvolume interpretation: preserve vendor units; do not silently convert if units are unclear.\n\nEvery derived field must include:\n\n- formula\n- input fields and source names\n- timestamp\u002Fas-of date\n- limitations\n\n## Verification Checklist\n\nAfter fetching data:\n\n1. Confirm the command exits with status 0.\n2. Confirm each requested source has either non-empty `data` or an explicit `error`.\n3. Confirm quotes include a vendor date\u002Ftime or are labeled as missing\u002Fstale.\n4. Confirm K-line data range and adjustment mode match the request.\n5. Confirm financial records include report dates; do not mix annual and quarterly values without labels.\n6. Confirm all unavailable sources are listed in `limitations` or source-level `error` fields.\n7. Before using valuation ratios in analysis, check whether the ratio is vendor-supplied or self-computed and label it accordingly.\n\n## Common Pitfalls\n\n- Sina\u002FTencent endpoints may require `Referer` and `User-Agent`; retry with browser-like headers before declaring unavailable.\n- Chinese endpoints often use GBK\u002FGB18030 encoding.\n- JSONP endpoints need wrapper stripping before JSON parsing.\n- Eastmoney field names differ by report type and can change. Preserve raw records and map only fields you verify.\n- Recent news headline search is not the same as verified announcement evidence.\n- ETF\u002Ffund data uses different endpoint families; do not assume single-stock fields apply unchanged.\n",{"name":5,"description":7},"main","b3f303dbd37b1f90e6f71e91aadbed231e664844","skills\u002Fa-share-data","https:\u002F\u002Fgithub.com\u002FYaphet2015\u002Fya-skills","https:\u002F\u002Fgithub.com\u002FYaphet2015","https:\u002F\u002Fblog.yaphet.me\u002F","Ex Ant Group, Kwai, Tencent","2026-11-13 15:07:07",{"source":8,"skillName":5,"commands":33,"prompt":43,"zipAvailable":44},[34,37,40],{"tool":35,"command":36},"npx","npx skills add Yaphet2015\u002Fya-skills --skill a-share-data",{"tool":38,"command":39},"bunx","bunx skills add Yaphet2015\u002Fya-skills --skill a-share-data",{"tool":41,"command":42},"pnpm","pnpm dlx skills add Yaphet2015\u002Fya-skills --skill a-share-data","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FYaphet2015\u002Fya-skills\u002Fblob\u002Fmain\u002Fskills\u002Fa-share-data\u002FSKILL.md",true,[46,52],{"path":47,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":50,"sourceHtmlUrl":51},"scripts\u002Fa_share_data.py","SCRIPT","脚本",14159,"https:\u002F\u002Fgithub.com\u002FYaphet2015\u002Fya-skills\u002Fblob\u002Fmain\u002Fskills\u002Fa-share-data\u002Fscripts\u002Fa_share_data.py",{"path":53,"resourceType":54,"resourceTypeDesc":55,"sizeBytes":56,"sourceHtmlUrl":57},"skill.json","REFERENCE","参考文档",141,"https:\u002F\u002Fgithub.com\u002FYaphet2015\u002Fya-skills\u002Fblob\u002Fmain\u002Fskills\u002Fa-share-data\u002Fskill.json",[59,66,73,80,87,95],{"skillNo":60,"name":61,"nameZh":6,"description":62,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":63,"categories":64,"keywords":65,"publishedAt":19},"01M75BMPRNYQBPMNZFTG5CPGN7","video-transcript","Video transcript (captions first, Whisper fallback). Use when the user wants text from a video.","https:\u002F\u002Fgithub.com\u002FYaphet2015\u002Fya-skills\u002Fblob\u002Fmain\u002Fskills\u002Fvideo-transcript\u002FSKILL.md",[],[],{"skillNo":67,"name":68,"nameZh":6,"description":69,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":70,"categories":71,"keywords":72,"publishedAt":19},"01M75BMMA9AHMV0PHXXHJ1SWS6","validator","Deprecated. Plan Completion Standard. Use only when the user invokes \u002Fvalidator after a Plan is complete.","https:\u002F\u002Fgithub.com\u002FYaphet2015\u002Fya-skills\u002Fblob\u002Fmain\u002Fskills\u002Fvalidator\u002FSKILL.md",[],[],{"skillNo":74,"name":75,"nameZh":6,"description":76,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":77,"categories":78,"keywords":79,"publishedAt":19},"01M75BMHVMK6A94MM8FKHGJD9R","ultra-simplify","Use when the user asks for a massive simplification pass","https:\u002F\u002Fgithub.com\u002FYaphet2015\u002Fya-skills\u002Fblob\u002Fmain\u002Fskills\u002Fultra-simplify\u002FSKILL.md",[],[],{"skillNo":81,"name":82,"nameZh":6,"description":83,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":84,"categories":85,"keywords":86,"publishedAt":19},"01M75BMEYYN24G2KKKG09XGD5M","ultra-produce","Deprecated. Coordinate native Planner, Builder and Verifier subagents through implementation and testing, with file-based handoffs, stage hooks and local commits. Use for an end-to-end delegated implementation workflow.","https:\u002F\u002Fgithub.com\u002FYaphet2015\u002Fya-skills\u002Fblob\u002Fmain\u002Fskills\u002Fultra-produce\u002FSKILL.md",[],[],{"skillNo":88,"name":89,"nameZh":6,"description":90,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":91,"licenseFileUrl":6,"sourceHtmlUrl":92,"categories":93,"keywords":94,"publishedAt":19},"01M75BMBF6T4KCH1M6HR8EZCZW","ultra-cr","Coordinate independent code reviewers, architectural impact analysis and finding verification. Use for multi-agent code review or an ultra-cr review against a diff and requirements, with resumable reports.","Apache-2.0","https:\u002F\u002Fgithub.com\u002FYaphet2015\u002Fya-skills\u002Fblob\u002Fmain\u002Fskills\u002Fultra-cr\u002FSKILL.md",[],[],{"skillNo":96,"name":97,"nameZh":6,"description":98,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":99,"categories":100,"keywords":101,"publishedAt":19},"01M75BM7CCFS6WGQ36WGQ03TTA","ui-parity","Align existing UI surfaces or extract shared interactions with baseline regression checks, state comparisons, and rendered evidence. Use for UI parity work.","https:\u002F\u002Fgithub.com\u002FYaphet2015\u002Fya-skills\u002Fblob\u002Fmain\u002Fskills\u002Fui-parity\u002FSKILL.md",[],[]]