{"id":"6e048ea1-0009-4c5c-ae5a-bbcf472cae5e","entityType":"agent","slug":"clawhub-kylinmountain-tradingagents-analysis","name":"A股多智能体投研-15 AI 分析师","canonicalUrl":"https://www.xpersona.co/agent/clawhub-kylinmountain-tradingagents-analysis","canonicalPath":"/agent/clawhub-kylinmountain-tradingagents-analysis","generatedAt":"2026-10-09T12:24:33.971Z","source":"CLAWHUB","claimStatus":"UNCLAIMED","verificationTier":"NONE","summary":{"evidence":{"source":"editorial-content","verified":true,"confidence":"high","updatedAt":"2026-10-09T05:21:20.882Z","emptyReason":null},"description":"A股多智能体 AI 投研分析工具 — 15 名 AI 分析师协作完成技术分析、基本面分析、 市场情绪研判、资金流向追踪（北向资金/主力资金）、宏观经济分析及博弈论推演， 输出结构化买卖建议与风险评估。支持沪深 A 股股票代码和中文名称。 Multi-agent AI stock analysis for Chin... Skill: A股多智能体投研-15 AI 分析师 Owner: kylinmountain Summary: A股多智能体 AI 投研分析工具 — 15 名 AI 分析师协作完成技术分析、基本面分析、 市场情绪研判、资金流向追踪（北向资金/主力资金）、宏观经济分析及博弈论推演， 输出结构化买卖建议与风险评估。支持沪深 A 股股票代码和中文名称。 Multi-agent AI stock analysis for Chin... Tags: A-Share:0.5.0, Agent:0.5.0, a-share:0.4.0, finance:0.5.0, investment:0.4.0, latest:0.6.2, multi-agent:0.4.0, stock:0.5.0, stocks:0.4.0 Version history: v0.6.2 | 2026-03-29T01:48:41.096Z | user Vers","descriptionLabel":"Technical summary","evidenceSummary":"Capability contract not published. No trust telemetry is available yet. 4.5K downloads reported by the source. Last updated 10/9/2026.","installCommand":"clawhub skill install s17be26ny652mmq9k9qhwkjb7d83g3bw:tradingagents-analysis","sourceUrl":"https://clawhub.ai/kylinmountain/tradingagents-analysis","homepage":"https://clawhub.ai/kylinmountain/skills/tradingagents-analysis","primaryLinks":[{"label":"View on ClawHub","url":"https://clawhub.ai/kylinmountain/tradingagents-analysis","kind":"source"},{"label":"Homepage","url":"https://clawhub.ai/kylinmountain/skills/tradingagents-analysis","kind":"homepage"}],"safetyScore":84,"overallRank":62,"popularityScore":57,"trustScore":null,"claimedByName":null,"isOwner":false,"seoDescription":"A股多智能体 AI 投研分析工具 — 15 名 AI 分析师协作完成技术分析、基本面分析、 市场情绪研判、资金流向追踪（北向资金/主力资金）、宏观经济分析及博弈论推演， 输出结构化买卖建议与风险评估。支持沪深 A 股股票代码和中文名称。 Multi-agent AI stock analysis for Chin..."},"coverage":{"evidence":{"source":"public-profile","verified":false,"confidence":"medium","updatedAt":"2026-10-09T05:21:20.882Z","emptyReason":null},"protocols":[{"protocol":"OPENCLEW","label":"OpenClaw","status":"self-declared","notes":"Declared in the public agent profile."}],"capabilities":[],"verifiedCount":0,"selfDeclaredCount":1,"capabilityMatrix":{"rows":[{"key":"OPENCLEW","type":"protocol","support":"unknown","confidenceSource":"profile","notes":"Listed on profile"}],"flattenedTokens":"protocol:OPENCLEW|unknown|profile"}},"adoption":{"evidence":{"source":"CLAWHUB","verified":false,"confidence":"medium","updatedAt":"2026-10-09T05:21:20.882Z","emptyReason":null},"stars":null,"forks":null,"downloads":4469,"packageName":null,"latestVersion":"0.6.2","tractionLabel":"4.5K downloads"},"release":{"evidence":{"source":"CLAWHUB","verified":false,"confidence":"medium","updatedAt":"2026-10-09T05:21:20.882Z","emptyReason":null},"lastUpdatedAt":"2026-10-09T05:21:20.882Z","lastCrawledAt":"2026-10-09T05:21:20.882Z","lastIndexedAt":null,"nextCrawlAt":"2026-10-10T05:21:20.882Z","lastVerifiedAt":null,"highlights":[{"version":"0.6.2","createdAt":"2026-03-29T01:48:41.096Z","changelog":"Version 0.6.1 - Added explicit OpenClaw metadata: now declares required environment variables and dependencies (curl, python3, bash) under `metadata.openclaw`. - Specifies `TRADINGAGENTS_TOKEN` as the primary environment variable in the metadata for improved integration and credential management. - No changes to core functionality or code; documentation/metadata update only.","fileCount":4,"zipByteSize":9556},{"version":"0.6.1","createdAt":"2026-03-29T01:41:20.075Z","changelog":"- Added explicit environment and binary requirements under metadata for OpenClaw compatibility. - Declared TRADINGAGENTS_TOKEN as the primary credential via metadata.openclaw. - No application logic or behavior changes; documentation updated for clarity on credential metadata and requirements. - Version number remains at 0.6.0 in SKILL.md (no functional version bump).","fileCount":3,"zipByteSize":7987},{"version":"0.6.0","createdAt":"2026-03-29T01:34:39.146Z","changelog":"**tradingagents-analysis 0.5.1 → 0.6.0 — Major Update** - Expanded description with clearer Chinese/English summary and explicit A股 (A-share) focus. - Tags list greatly extended for improved discoverability (包括A股、主力资金、K线、风险评估等). - Clarified market scope: now officially supports only China A-shares, dropping US stocks/crypto mentions. - Environment variable specifications improved; `TRADINGAGENTS_TOKEN` now clearly marked as primary and required. - Usage instructions reorganized for easier onboarding, with separate sections for cloud and self-host deployment. - Updated documentation and examples to reflect A股-only coverage and the latest workflow best practices.","fileCount":3,"zipByteSize":8014},{"version":"0.5.0","createdAt":"2026-03-23T02:16:58.197Z","changelog":"- Added a unified Bash script (`scripts/analyze.sh`) for streamlined task submission, polling, and result retrieval (supports both single and batch stock analysis). - Updated documentation to recommend using the new analyze.sh script for all typical workflows, replacing manual curl polling instructions. - Described script usage, batch processing, timeout, and environment variables for customization. - Clarified that the script should be used instead of manual polling for job status/results.","fileCount":3,"zipByteSize":7679},{"version":"0.4.4","createdAt":"2026-03-15T14:21:15.344Z","changelog":"trading-agents-analysis 0.4.4 - update display name - No file changes detected in this version. - Functionality and documentation remain unchanged from the previous release.","fileCount":2,"zipByteSize":4673},{"version":"0.4.3","createdAt":"2026-03-15T04:17:04.706Z","changelog":"- Expanded tags to include 研报, 资金流向, 技术分析, 基本面分析 for better discoverability. - Added quick start guide with sample input phrases for easier onboarding. - Clarified the data privacy policy, explicitly stating only extracted symbols/dates/parameters are transmitted—not raw conversation text. - Strengthened documentation on credential management and security best practices. - Introduced application scenarios (“适用/不适用场景”) for clearer user guidance. - Provided reminders on not pasting sensitive content and reaffirmed the authoritative env var configuration.","fileCount":2,"zipByteSize":4673},{"version":"0.4.2","createdAt":"2026-03-15T04:03:30.309Z","changelog":"**Expanded multi-agent architecture and feature set** - Upgraded from 12 to 15 AI analyst agents, adding a five-stage collaborative research process. - Full bilingual documentation: enhanced Chinese and English instructions, usage, and examples. - Added explicit support for both A-share (A股) and US stock tickers. - Detailed system architecture description with breakdown of agent roles in each phase. - New output examples and risk metrics, plus documented \"short-term\" (短线) analysis mode. - Improved privacy, security, and self-hosting instructions.","fileCount":2,"zipByteSize":3375},{"version":"0.4.1","createdAt":"2026-03-14T01:55:24.303Z","changelog":"Version 0.4.1 - Major rewrite of documentation for clarity and completeness. - Clearly describes privacy, security, and self-hosting options. - Updates usage instructions to highlight the POST /v1/analyze endpoint. - Details multi-agent workflow, polling intervals, result structure, and expected analysis time. - Lists supported input formats and provides concrete API examples.","fileCount":2,"zipByteSize":2124}]},"execution":{"evidence":{"source":"CLAWHUB","verified":false,"confidence":"low","updatedAt":null,"emptyReason":"No published capability contract is available yet."},"installCommand":"clawhub skill install s17be26ny652mmq9k9qhwkjb7d83g3bw:tradingagents-analysis","setupComplexity":"low","setupSteps":["Setup complexity is classified as HIGH. You must provision dedicated cloud infrastructure or an isolated VM. Do not run this directly on your local workstation.","Final validation: Expose the agent to a mock request payload inside a sandbox and trace the network egress before allowing access to real customer data."],"contract":{"contractStatus":"missing","authModes":[],"requires":[],"forbidden":[],"supportsMcp":false,"supportsA2a":false,"supportsStreaming":false,"inputSchemaRef":null,"outputSchemaRef":null,"dataRegion":null,"contractUpdatedAt":null,"sourceUpdatedAt":null,"freshnessSeconds":null},"invocationGuide":{"preferredApi":{"snapshotUrl":"https://www.xpersona.co/api/v1/agents/clawhub-kylinmountain-tradingagents-analysis/snapshot","contractUrl":"https://www.xpersona.co/api/v1/agents/clawhub-kylinmountain-tradingagents-analysis/contract","trustUrl":"https://www.xpersona.co/api/v1/agents/clawhub-kylinmountain-tradingagents-analysis/trust"},"curlExamples":["curl -s \"https://www.xpersona.co/api/v1/agents/clawhub-kylinmountain-tradingagents-analysis/snapshot\"","curl -s \"https://www.xpersona.co/api/v1/agents/clawhub-kylinmountain-tradingagents-analysis/contract\"","curl -s \"https://www.xpersona.co/api/v1/agents/clawhub-kylinmountain-tradingagents-analysis/trust\""],"jsonRequestTemplate":{"query":"summarize this repo","constraints":{"maxLatencyMs":2000,"protocolPreference":["OPENCLEW"]}},"jsonResponseTemplate":{"ok":true,"result":{"summary":"...","confidence":0.9},"meta":{"source":"CLAWHUB","generatedAt":"2026-10-09T12:24:33.970Z"}},"retryPolicy":{"maxAttempts":3,"backoffMs":[500,1500,3500],"retryableConditions":["HTTP_429","HTTP_503","NETWORK_TIMEOUT"]}},"endpoints":{"dossierUrl":"https://www.xpersona.co/api/v1/agents/clawhub-kylinmountain-tradingagents-analysis/dossier","snapshotUrl":"https://www.xpersona.co/api/v1/agents/clawhub-kylinmountain-tradingagents-analysis/snapshot","contractUrl":"https://www.xpersona.co/api/v1/agents/clawhub-kylinmountain-tradingagents-analysis/contract","trustUrl":"https://www.xpersona.co/api/v1/agents/clawhub-kylinmountain-tradingagents-analysis/trust"}},"reliability":{"evidence":{"source":"runtime-metrics","verified":false,"confidence":"low","updatedAt":null,"emptyReason":"No trust, reliability, or runtime telemetry is available."},"trust":{"status":"unavailable","handshakeStatus":"UNKNOWN","verificationFreshnessHours":null,"reputationScore":null,"p95LatencyMs":null,"successRate30d":null,"fallbackRate":null,"attempts30d":null,"trustUpdatedAt":null,"trustConfidence":"unknown","sourceUpdatedAt":null,"freshnessSeconds":null},"decisionGuardrails":{"doNotUseIf":["Contract metadata is missing or unavailable for deterministic execution."],"safeUseWhen":[],"riskFlags":["missing_or_unavailable_contract","trust_data_unavailable","schema_references_missing"],"operationalConfidence":"low"},"executionMetrics":{"observedLatencyMsP50":null,"observedLatencyMsP95":null,"estimatedCostUsd":null,"uptime30d":null,"rateLimitRpm":null,"rateLimitBurst":null,"lastVerifiedAt":null,"verificationSource":null},"runtimeMetrics":{"successRate":null,"avgLatencyMs":null,"avgCostUsd":null,"hallucinationRate":null,"retryRate":null,"disputeRate":null,"p50Latency":null,"p95Latency":null,"lastUpdated":null}},"benchmarks":{"evidence":{"source":"no-benchmark-data","verified":false,"confidence":"low","updatedAt":null,"emptyReason":"No benchmark suites or observed failure patterns are available."},"suites":[],"failurePatterns":[]},"artifacts":{"evidence":{"source":"CLAWHUB","verified":false,"confidence":"high","updatedAt":"2026-10-09T05:21:20.882Z","emptyReason":null},"readme":"Skill: A股多智能体投研-15 AI 分析师\n\nOwner: kylinmountain\n\nSummary: A股多智能体 AI 投研分析工具 — 15 名 AI 分析师协作完成技术分析、基本面分析、 市场情绪研判、资金流向追踪（北向资金/主力资金）、宏观经济分析及博弈论推演， 输出结构化买卖建议与风险评估。支持沪深 A 股股票代码和中文名称。 Multi-agent AI stock analysis for Chin...\n\nTags: A-Share:0.5.0, Agent:0.5.0, a-share:0.4.0, finance:0.5.0, investment:0.4.0, latest:0.6.2, multi-agent:0.4.0, stock:0.5.0, stocks:0.4.0\n\nVersion history:\n\nv0.6.2 | 2026-03-29T01:48:41.096Z | user\n\nVersion 0.6.1\n\n- Added explicit OpenClaw metadata: now declares required environment variables and dependencies (curl, python3, bash) under `metadata.openclaw`.\n- Specifies `TRADINGAGENTS_TOKEN` as the primary environment variable in the metadata for improved integration and credential management.\n- No changes to core functionality or code; documentation/metadata update only.\n\nv0.6.1 | 2026-03-29T01:41:20.075Z | user\n\n- Added explicit environment and binary requirements under metadata for OpenClaw compatibility.\n- Declared TRADINGAGENTS_TOKEN as the primary credential via metadata.openclaw.\n- No application logic or behavior changes; documentation updated for clarity on credential metadata and requirements.\n- Version number remains at 0.6.0 in SKILL.md (no functional version bump).\n\nv0.6.0 | 2026-03-29T01:34:39.146Z | user\n\n**tradingagents-analysis 0.5.1 → 0.6.0 — Major Update**\n\n- Expanded description with clearer Chinese/English summary and explicit A股 (A-share) focus.\n- Tags list greatly extended for improved discoverability (包括A股、主力资金、K线、风险评估等).\n- Clarified market scope: now officially supports only China A-shares, dropping US stocks/crypto mentions.\n- Environment variable specifications improved; `TRADINGAGENTS_TOKEN` now clearly marked as primary and required.\n- Usage instructions reorganized for easier onboarding, with separate sections for cloud and self-host deployment.\n- Updated documentation and examples to reflect A股-only coverage and the latest workflow best practices.\n\nv0.5.0 | 2026-03-23T02:16:58.197Z | auto\n\n- Added a unified Bash script (`scripts/analyze.sh`) for streamlined task submission, polling, and result retrieval (supports both single and batch stock analysis).\n- Updated documentation to recommend using the new analyze.sh script for all typical workflows, replacing manual curl polling instructions.\n- Described script usage, batch processing, timeout, and environment variables for customization.\n- Clarified that the script should be used instead of manual polling for job status/results.\n\nv0.4.4 | 2026-03-15T14:21:15.344Z | user\n\ntrading-agents-analysis 0.4.4\n\n- update display name\n- No file changes detected in this version.\n- Functionality and documentation remain unchanged from the previous release.\n\nv0.4.3 | 2026-03-15T04:17:04.706Z | auto\n\n- Expanded tags to include 研报, 资金流向, 技术分析, 基本面分析 for better discoverability.\n- Added quick start guide with sample input phrases for easier onboarding.\n- Clarified the data privacy policy, explicitly stating only extracted symbols/dates/parameters are transmitted—not raw conversation text.\n- Strengthened documentation on credential management and security best practices.\n- Introduced application scenarios (“适用/不适用场景”) for clearer user guidance.\n- Provided reminders on not pasting sensitive content and reaffirmed the authoritative env var configuration.\n\nv0.4.2 | 2026-03-15T04:03:30.309Z | auto\n\n**Expanded multi-agent architecture and feature set**\n\n- Upgraded from 12 to 15 AI analyst agents, adding a five-stage collaborative research process.\n- Full bilingual documentation: enhanced Chinese and English instructions, usage, and examples.\n- Added explicit support for both A-share (A股) and US stock tickers.\n- Detailed system architecture description with breakdown of agent roles in each phase.\n- New output examples and risk metrics, plus documented \"short-term\" (短线) analysis mode.\n- Improved privacy, security, and self-hosting instructions.\n\nv0.4.1 | 2026-03-14T01:55:24.303Z | auto\n\nVersion 0.4.1\n\n- Major rewrite of documentation for clarity and completeness.\n- Clearly describes privacy, security, and self-hosting options.\n- Updates usage instructions to highlight the POST /v1/analyze endpoint.\n- Details multi-agent workflow, polling intervals, result structure, and expected analysis time.\n- Lists supported input formats and provides concrete API examples.\n\nv0.4.0 | 2026-03-13T13:04:57.501Z | user\n\nInitial release of tradingagents-analysis.\n\n- Analyze stocks, research market trends, and answer investment-related questions using natural language.\n- Automatically detects user intent and starts multi-agent stock analysis jobs.\n- Notifies users when an investigation begins; deep analysis may take 1 to 5 minutes.\n- Polls for job completion and summarizes expert insights upon analysis completion.\n- Supports Chinese company names and six-digit codes, with suffixes recommended for accuracy.\n\nArchive index:\n\nArchive v0.6.2: 4 files, 9556 bytes\n\nFiles: scripts/analyze.sh (6421b), skill-card.md (2841b), SKILL.md (10030b), _meta.json (141b)\n\nFile v0.6.2:SKILL.md\n\n---\nname: tradingagents-analysis\nversion: 0.6.1\ndescription: >-\n  A股多智能体 AI 投研分析工具 — 15 名 AI 分析师协作完成技术分析、基本面分析、\n  市场情绪研判、资金流向追踪（北向资金/主力资金）、宏观经济分析及博弈论推演，\n  输出结构化买卖建议与风险评估。支持沪深 A 股股票代码和中文名称。\n  Multi-agent AI stock analysis for China A-shares.\n  15 specialized analysts collaborate across technical analysis, fundamental analysis,\n  sentiment analysis, smart money flow tracking, macro economics, and game theory\n  to deliver structured buy/sell/hold recommendations with risk assessment.\nhomepage: https://app.510168.xyz\nrepository: https://github.com/KylinMountain/TradingAgents-AShare\ntags:\n  - stock-analysis\n  - A-share\n  - A股\n  - 股票分析\n  - 股票\n  - 炒股\n  - 选股\n  - 荐股\n  - trading\n  - investment\n  - 投资\n  - 投研\n  - 量化投研\n  - 研报\n  - 盘后分析\n  - 复盘\n  - multi-agent\n  - 多智能体\n  - AI分析\n  - AI炒股\n  - technical-analysis\n  - 技术分析\n  - K线\n  - fundamental-analysis\n  - 基本面分析\n  - sentiment-analysis\n  - 市场情绪\n  - smart-money\n  - 资金流向\n  - 北向资金\n  - 主力资金\n  - 龙虎榜\n  - finance\n  - 金融\n  - China\n  - 中国股市\n  - 沪深\n  - 上证\n  - 深证\n  - quant\n  - risk-assessment\n  - 风险评估\n  - 买卖建议\n  - claude-code\n  - openclaw\nmetadata:\n  openclaw:\n    requires:\n      env:\n        - TRADINGAGENTS_TOKEN\n        - TRADINGAGENTS_API_URL\n      bins:\n        - curl\n        - python3\n        - bash\n    primaryEnv: TRADINGAGENTS_TOKEN\n    emoji: \"📈\"\n    homepage: https://app.510168.xyz\n---\n\n# TradingAgents 多智能体 A 股投研分析\n\n使用 TradingAgents API，让 **15 名专业 AI 分析师**对 A 股进行五阶段深度协作研判，输出结构化投资建议。\n\n## 🎯 快速上手\n\n**直接对我说：**\n- \"帮我分析一下贵州茅台\"\n- \"宁德时代值得买入吗\"\n- \"分析一下 600519 的技术面\"\n- \"比亚迪最近资金流向怎么样\"\n\n**我会调用 15 个 AI 分析师，从市场、技术、基本面、情绪、资金五个维度深度分析，给你专业的投资建议。**\n\n---\n\n## 🤖 系统架构：五阶段 15 智能体\n\n| 阶段 | 智能体 | 职责 |\n|------|--------|------|\n| 1. 分析团队 | 市场/新闻/情绪/基本面/宏观/聪明钱 | 多维度原始数据解读 |\n| 2. 博弈裁判 | 博弈论管理者 | 主力与散户预期差分析 |\n| 3. 多空辩论 | 多头/空头研究员 + 裁判 | 对立观点激烈博弈 |\n| 4. 执行决策 | 交易员 | 综合研判生成操作建议 |\n| 5. 风险管控 | 激进/中性/保守分析师 + 组合经理 | 多维度风控审核 |\n\n---\n\n# TradingAgents Multi-Agent Investment Research\n\nUse the TradingAgents API to let **15 specialized AI analysts** conduct deep, five-stage collaborative research on A-Share stocks, delivering structured trading recommendations.\n\n## 🤖 System Architecture: 5 Stages · 15 Agents\n\n| Stage | Agents | Role |\n|-------|--------|------|\n| 1. Analyst Team | Market / News / Sentiment / Fundamentals / Macro / Smart Money | Multi-dimensional raw data analysis |\n| 2. Game Theory | Game Theory Manager | Main-force vs. retail expectation gap |\n| 3. Bull/Bear Debate | Bull & Bear Researchers + Judge | Adversarial viewpoint debate |\n| 4. Trade Execution | Trader | Synthesize research into actionable decision |\n| 5. Risk Control | Aggressive / Neutral / Conservative + Portfolio Manager | Multi-layer risk review |\n\n## 📋 适用场景\n\n✅ **适合使用：**\n- 个股深度分析（技术面 + 基本面）\n- 投资决策参考\n- 盘后复盘分析\n- 持仓标的风险评估\n- 资金流向与市场情绪研判\n\n❌ **不适合：**\n- 盘中实时盯盘（分析需要 1-5 分钟）\n- 超短线交易（分钟级决策）\n- 加密货币、美股等非 A 股市场\n\n## 🔒 隐私与安全\n\n- **发送范围**：本技能**仅**从对话中提取股票名称/代码、分析日期、分析视角等参数，将其作为 `symbol`/`trade_date`/`horizons` 字段发送至后端 API。**不发送对话原文、不读取本地文件、不上传任何其他隐私数据。**\n- **令牌安全**：`TRADINGAGENTS_TOKEN`（格式 `ta-sk-*`）是访问后端的唯一凭证，请使用最小权限令牌，如怀疑泄露请立即在 [app.510168.xyz](https://app.510168.xyz) 吊销并重新生成。\n- **敏感内容提示**：请勿在分析请求中粘贴个人账户信息、真实持仓或其他敏感内容，本技能无法阻止用户主动提交这些内容。\n- **自托管**：如需完全掌控数据流向，可参考 [GitHub 文档](https://github.com/KylinMountain/TradingAgents-AShare) 自行部署后端，并将 `TRADINGAGENTS_API_URL` 指向自建服务器。\n\n> **关于凭证元数据**：本技能的 frontmatter 在 `metadata.openclaw` 中声明了 `TRADINGAGENTS_TOKEN` 为 `primaryEnv`，并列入 `requires.env`。\n\n## 🔒 Privacy & Data Transmission\n\n- **What is sent**: Only the extracted stock symbol, trade date, and analysis parameters (`symbol`, `trade_date`, `horizons`) are transmitted to the backend. The raw conversation text is **never** forwarded.\n- **Token**: `TRADINGAGENTS_TOKEN` (pattern `ta-sk-*`) is the sole credential. Use a minimal-privilege token and rotate it immediately if compromised.\n- **Sensitive content**: Do not paste personal account data, real positions, or other sensitive information into analysis requests.\n- **Self-hosting**: For full data sovereignty, deploy the backend yourself and set `TRADINGAGENTS_API_URL` to your server. See the [GitHub repo](https://github.com/KylinMountain/TradingAgents-AShare).\n\n> **Credential metadata**: This skill's frontmatter declares `TRADINGAGENTS_TOKEN` as `primaryEnv` under `metadata.openclaw.requires.env`.\n\n## ⚙️ 快速配置\n\n**方式一：使用官方托管服务（零部署，开箱即用）**\n\n1. 登录 [https://app.510168.xyz](https://app.510168.xyz)\n2. 进入 **Settings → API Tokens** 创建令牌\n3. 配置环境变量：\n```bash\nexport TRADINGAGENTS_TOKEN=\"ta-sk-your_key_here\"\n```\n\n**方式二：私有化部署（数据完全自主可控）**\n\n如对数据隐私有要求，可自行部署后端，所有分析数据仅在你自己的服务器上处理：\n\n```bash\n# 1. 部署后端，参考 https://github.com/KylinMountain/TradingAgents-AShare\n# 2. 将 API 地址指向自建服务\nexport TRADINGAGENTS_API_URL=\"http://your-server:8000\"\nexport TRADINGAGENTS_TOKEN=\"ta-sk-your_key_here\"\n```\n\n## 🚀 常用操作\n\n**推荐方式：使用一体化脚本**（自动提交 → 轮询 → 获取结果）\n\n```bash\n# 脚本路径（相对于技能目录）\nbash scripts/analyze.sh <symbol[,symbol2,...]> [trade_date] [horizons]\n\n# 单个分析\nbash scripts/analyze.sh 贵州茅台\nbash scripts/analyze.sh 600519.SH 2026-03-22\nbash scripts/analyze.sh 600519.SH 2026-03-22 medium\n\n# 批量分析（逗号分隔，并行提交，统一等待）\nbash scripts/analyze.sh 贵州茅台,比亚迪,宁德时代\nbash scripts/analyze.sh 600519.SH,002594.SZ,300750.SZ 2026-03-22\n```\n\n脚本会自动完成：提交任务 → 每 15 秒轮询状态 → 完成后输出 JSON 结果。\n批量模式下所有任务并行提交，统一轮询，最后汇总输出。超时默认 600 秒。\n\n可通过环境变量调整行为：\n- `POLL_INTERVAL` — 轮询间隔秒数（默认 15）\n- `POLL_TIMEOUT` — 最大等待秒数（默认 600）\n\n**手动分步操作**（如需单独调用某一步）\n\n所有请求使用 `$TRADINGAGENTS_TOKEN` 作为 Bearer 令牌。\n\n1. 提交分析任务\n```bash\ncurl -X POST \"${TRADINGAGENTS_API_URL:-https://api.510168.xyz}/v1/analyze\" \\\n  -H \"Authorization: Bearer $TRADINGAGENTS_TOKEN\" \\\n  -H \"Content-Type: application/json\" \\\n  -d '{\"symbol\": \"贵州茅台\"}'\n```\n\n2. 查询任务状态\n```bash\ncurl \"${TRADINGAGENTS_API_URL:-https://api.510168.xyz}/v1/jobs/{job_id}\" \\\n  -H \"Authorization: Bearer $TRADINGAGENTS_TOKEN\"\n```\n\n3. 获取完整分析结果（任务完成后）\n```bash\ncurl \"${TRADINGAGENTS_API_URL:-https://api.510168.xyz}/v1/jobs/{job_id}/result\" \\\n  -H \"Authorization: Bearer $TRADINGAGENTS_TOKEN\"\n```\n\n## 📊 示例输出\n\n```json\n{\n  \"decision\": \"BUY\",\n  \"direction\": \"看多\",\n  \"confidence\": 78,\n  \"target_price\": 1850.0,\n  \"stop_loss_price\": 1680.0,\n  \"risk_items\": [\n    {\"name\": \"估值偏高\", \"level\": \"medium\", \"description\": \"当前 PE 处于历史 75 分位\"},\n    {\"name\": \"外资流出\", \"level\": \"low\",    \"description\": \"近 5 日北向资金小幅净流出\"}\n  ],\n  \"key_metrics\": [\n    {\"name\": \"PE\",   \"value\": \"32.5x\",  \"status\": \"neutral\"},\n    {\"name\": \"ROE\",  \"value\": \"31.2%\",  \"status\": \"good\"},\n    {\"name\": \"毛利率\", \"value\": \"91.5%\", \"status\": \"good\"}\n  ],\n  \"final_trade_decision\": \"综合技术面突破与基本面支撑，建议逢低分批建仓...\"\n}\n```\n\n## 🔄 任务执行流程\n\n深度分析通常耗时 **1 至 5 分钟**：\n\n1. **识别标的**：从对话中**仅**提取股票名称或代码（及可选日期/视角），不发送对话原文\n2. **告知用户**：反馈任务即将提交，预计耗时 1-5 分钟\n3. **执行脚本**：使用 Bash 工具运行 `bash scripts/analyze.sh <symbol> [date] [horizons]`（设置 `run_in_background: true`），脚本自动完成提交、轮询和结果获取\n4. **汇总结论**：脚本输出完成后，解析 JSON 结果，向用户展示决策、方向、目标价、风险点\n\n> **重要**：不要手动编写 curl 轮询循环，直接使用 `scripts/analyze.sh` 脚本。\n\n## 📌 支持标的范围\n\n- **沪深 A 股**：中文名称（如 \"比亚迪\"、\"宁德时代\"）或代码（`002594.SZ`、`601012.SH`）\n\n## 💡 注意事项\n\n- **轮询频率**：每次轮询间隔不低于 15 秒\n- **数据健壮性**：若部分数据源缺失，系统将基于宏观与行业逻辑进行外溢分析\n- **短线模式**：输入\"分析 XX 短线\"时，系统自动切换为 14 天技术面分析，跳过财报数据，速度更快\n\nFile v0.6.2:_meta.json\n\n{\n  \"ownerId\": \"kn7fp71x5ttbnyv3dk5w2dvnen82vkvn\",\n  \"slug\": \"tradingagents-analysis\",\n  \"version\": \"0.6.2\",\n  \"publishedAt\": 1774748921096\n}\n\nFile v0.6.2:skill-card.md\n\n## Description:\n\nA股多智能体 AI 投研分析工具 uses 15 AI analysts to analyze China A-share stocks across technical, fundamental, sentiment, smart-money, macroeconomic, and game-theory perspectives, producing structured buy, sell, or hold recommendations with risk assessment.\n\nThis skill is ready for commercial/non-commercial use.\n\n## Publisher:\n\n[kylinmountain](https://clawhub.ai/user/kylinmountain)\n\n### License/Terms of Use:\n\nMIT-0\n\n## Use Case:\n\nExternal users and investment researchers use this skill to request deep analysis of Shanghai and Shenzhen A-share stocks by symbol or Chinese company name. The skill submits stock-analysis jobs to the TradingAgents API and returns structured decisions, confidence, target and stop-loss prices, key metrics, and risk items.\n\n### Deployment Geography for Use:\n\nGlobal\n\n## Known Risks and Mitigations:\n\nRisk: The skill can send stock-analysis requests and a bearer token to a configurable backend API endpoint.\n\nMitigation: Use the default HTTPS endpoint or an HTTPS self-hosted endpoint, avoid plain HTTP except loopback-only local testing with disposable credentials, and rotate the TradingAgents token if exposed.\n\nRisk: The skill produces investment-analysis recommendations that may be incorrect, stale, or unsuitable for a user's financial situation.\n\nMitigation: Treat outputs as decision support, require user confirmation before submitting jobs, and review recommendations with independent financial judgment before acting.\n\nRisk: Users may include personal account details, actual positions, or other sensitive financial information in prompts even though the skill only needs stock-analysis parameters.\n\nMitigation: Ask users to provide only stock symbols, trade dates, and analysis horizons; do not include account data, holdings, or other sensitive personal information.\n\n## Reference(s):\n\n- [ClawHub skill listing](https://clawhub.ai/kylinmountain/skills/tradingagents-analysis)\n- [TradingAgents application homepage](https://app.510168.xyz)\n- [TradingAgents-AShare self-hosting documentation](https://github.com/KylinMountain/TradingAgents-AShare)\n\n## Skill Output:\n\n**Output Type(s):** [text, markdown, shell commands, configuration, guidance]\n\n**Output Format:** [Markdown guidance with shell commands and JSON analysis results]\n\n**Output Parameters:** [1D]\n\n**Other Properties Related to Output:** [Analysis jobs usually take 1 to 5 minutes; batch mode submits multiple symbols and returns a JSON result summary for completed jobs.]\n\n## Skill Version(s):\n\n0.6.2 (source: server release evidence)\n\n## Ethical Considerations:\n\nUsers should evaluate whether this skill is appropriate for their environment, review any generated or modified files before relying on them, and apply their organization's safety, security, and compliance requirements before deployment.\n\nArchive v0.6.1: 3 files, 7987 bytes\n\nFiles: scripts/analyze.sh (6421b), SKILL.md (10030b), _meta.json (141b)\n\nFile v0.6.1:SKILL.md\n\n---\nname: tradingagents-analysis\nversion: 0.6.0\ndescription: >-\n  A股多智能体 AI 投研分析工具 — 15 名 AI 分析师协作完成技术分析、基本面分析、\n  市场情绪研判、资金流向追踪（北向资金/主力资金）、宏观经济分析及博弈论推演，\n  输出结构化买卖建议与风险评估。支持沪深 A 股股票代码和中文名称。\n  Multi-agent AI stock analysis for China A-shares.\n  15 specialized analysts collaborate across technical analysis, fundamental analysis,\n  sentiment analysis, smart money flow tracking, macro economics, and game theory\n  to deliver structured buy/sell/hold recommendations with risk assessment.\nhomepage: https://app.510168.xyz\nrepository: https://github.com/KylinMountain/TradingAgents-AShare\ntags:\n  - stock-analysis\n  - A-share\n  - A股\n  - 股票分析\n  - 股票\n  - 炒股\n  - 选股\n  - 荐股\n  - trading\n  - investment\n  - 投资\n  - 投研\n  - 量化投研\n  - 研报\n  - 盘后分析\n  - 复盘\n  - multi-agent\n  - 多智能体\n  - AI分析\n  - AI炒股\n  - technical-analysis\n  - 技术分析\n  - K线\n  - fundamental-analysis\n  - 基本面分析\n  - sentiment-analysis\n  - 市场情绪\n  - smart-money\n  - 资金流向\n  - 北向资金\n  - 主力资金\n  - 龙虎榜\n  - finance\n  - 金融\n  - China\n  - 中国股市\n  - 沪深\n  - 上证\n  - 深证\n  - quant\n  - risk-assessment\n  - 风险评估\n  - 买卖建议\n  - claude-code\n  - openclaw\nmetadata:\n  openclaw:\n    requires:\n      env:\n        - TRADINGAGENTS_TOKEN\n        - TRADINGAGENTS_API_URL\n      bins:\n        - curl\n        - python3\n        - bash\n    primaryEnv: TRADINGAGENTS_TOKEN\n    emoji: \"📈\"\n    homepage: https://app.510168.xyz\n---\n\n# TradingAgents 多智能体 A 股投研分析\n\n使用 TradingAgents API，让 **15 名专业 AI 分析师**对 A 股进行五阶段深度协作研判，输出结构化投资建议。\n\n## 🎯 快速上手\n\n**直接对我说：**\n- \"帮我分析一下贵州茅台\"\n- \"宁德时代值得买入吗\"\n- \"分析一下 600519 的技术面\"\n- \"比亚迪最近资金流向怎么样\"\n\n**我会调用 15 个 AI 分析师，从市场、技术、基本面、情绪、资金五个维度深度分析，给你专业的投资建议。**\n\n---\n\n## 🤖 系统架构：五阶段 15 智能体\n\n| 阶段 | 智能体 | 职责 |\n|------|--------|------|\n| 1. 分析团队 | 市场/新闻/情绪/基本面/宏观/聪明钱 | 多维度原始数据解读 |\n| 2. 博弈裁判 | 博弈论管理者 | 主力与散户预期差分析 |\n| 3. 多空辩论 | 多头/空头研究员 + 裁判 | 对立观点激烈博弈 |\n| 4. 执行决策 | 交易员 | 综合研判生成操作建议 |\n| 5. 风险管控 | 激进/中性/保守分析师 + 组合经理 | 多维度风控审核 |\n\n---\n\n# TradingAgents Multi-Agent Investment Research\n\nUse the TradingAgents API to let **15 specialized AI analysts** conduct deep, five-stage collaborative research on A-Share stocks, delivering structured trading recommendations.\n\n## 🤖 System Architecture: 5 Stages · 15 Agents\n\n| Stage | Agents | Role |\n|-------|--------|------|\n| 1. Analyst Team | Market / News / Sentiment / Fundamentals / Macro / Smart Money | Multi-dimensional raw data analysis |\n| 2. Game Theory | Game Theory Manager | Main-force vs. retail expectation gap |\n| 3. Bull/Bear Debate | Bull & Bear Researchers + Judge | Adversarial viewpoint debate |\n| 4. Trade Execution | Trader | Synthesize research into actionable decision |\n| 5. Risk Control | Aggressive / Neutral / Conservative + Portfolio Manager | Multi-layer risk review |\n\n## 📋 适用场景\n\n✅ **适合使用：**\n- 个股深度分析（技术面 + 基本面）\n- 投资决策参考\n- 盘后复盘分析\n- 持仓标的风险评估\n- 资金流向与市场情绪研判\n\n❌ **不适合：**\n- 盘中实时盯盘（分析需要 1-5 分钟）\n- 超短线交易（分钟级决策）\n- 加密货币、美股等非 A 股市场\n\n## 🔒 隐私与安全\n\n- **发送范围**：本技能**仅**从对话中提取股票名称/代码、分析日期、分析视角等参数，将其作为 `symbol`/`trade_date`/`horizons` 字段发送至后端 API。**不发送对话原文、不读取本地文件、不上传任何其他隐私数据。**\n- **令牌安全**：`TRADINGAGENTS_TOKEN`（格式 `ta-sk-*`）是访问后端的唯一凭证，请使用最小权限令牌，如怀疑泄露请立即在 [app.510168.xyz](https://app.510168.xyz) 吊销并重新生成。\n- **敏感内容提示**：请勿在分析请求中粘贴个人账户信息、真实持仓或其他敏感内容，本技能无法阻止用户主动提交这些内容。\n- **自托管**：如需完全掌控数据流向，可参考 [GitHub 文档](https://github.com/KylinMountain/TradingAgents-AShare) 自行部署后端，并将 `TRADINGAGENTS_API_URL` 指向自建服务器。\n\n> **关于凭证元数据**：本技能的 frontmatter 在 `metadata.openclaw` 中声明了 `TRADINGAGENTS_TOKEN` 为 `primaryEnv`，并列入 `requires.env`。\n\n## 🔒 Privacy & Data Transmission\n\n- **What is sent**: Only the extracted stock symbol, trade date, and analysis parameters (`symbol`, `trade_date`, `horizons`) are transmitted to the backend. The raw conversation text is **never** forwarded.\n- **Token**: `TRADINGAGENTS_TOKEN` (pattern `ta-sk-*`) is the sole credential. Use a minimal-privilege token and rotate it immediately if compromised.\n- **Sensitive content**: Do not paste personal account data, real positions, or other sensitive information into analysis requests.\n- **Self-hosting**: For full data sovereignty, deploy the backend yourself and set `TRADINGAGENTS_API_URL` to your server. See the [GitHub repo](https://github.com/KylinMountain/TradingAgents-AShare).\n\n> **Credential metadata**: This skill's frontmatter declares `TRADINGAGENTS_TOKEN` as `primaryEnv` under `metadata.openclaw.requires.env`.\n\n## ⚙️ 快速配置\n\n**方式一：使用官方托管服务（零部署，开箱即用）**\n\n1. 登录 [https://app.510168.xyz](https://app.510168.xyz)\n2. 进入 **Settings → API Tokens** 创建令牌\n3. 配置环境变量：\n```bash\nexport TRADINGAGENTS_TOKEN=\"ta-sk-your_key_here\"\n```\n\n**方式二：私有化部署（数据完全自主可控）**\n\n如对数据隐私有要求，可自行部署后端，所有分析数据仅在你自己的服务器上处理：\n\n```bash\n# 1. 部署后端，参考 https://github.com/KylinMountain/TradingAgents-AShare\n# 2. 将 API 地址指向自建服务\nexport TRADINGAGENTS_API_URL=\"http://your-server:8000\"\nexport TRADINGAGENTS_TOKEN=\"ta-sk-your_key_here\"\n```\n\n## 🚀 常用操作\n\n**推荐方式：使用一体化脚本**（自动提交 → 轮询 → 获取结果）\n\n```bash\n# 脚本路径（相对于技能目录）\nbash scripts/analyze.sh <symbol[,symbol2,...]> [trade_date] [horizons]\n\n# 单个分析\nbash scripts/analyze.sh 贵州茅台\nbash scripts/analyze.sh 600519.SH 2026-03-22\nbash scripts/analyze.sh 600519.SH 2026-03-22 medium\n\n# 批量分析（逗号分隔，并行提交，统一等待）\nbash scripts/analyze.sh 贵州茅台,比亚迪,宁德时代\nbash scripts/analyze.sh 600519.SH,002594.SZ,300750.SZ 2026-03-22\n```\n\n脚本会自动完成：提交任务 → 每 15 秒轮询状态 → 完成后输出 JSON 结果。\n批量模式下所有任务并行提交，统一轮询，最后汇总输出。超时默认 600 秒。\n\n可通过环境变量调整行为：\n- `POLL_INTERVAL` — 轮询间隔秒数（默认 15）\n- `POLL_TIMEOUT` — 最大等待秒数（默认 600）\n\n**手动分步操作**（如需单独调用某一步）\n\n所有请求使用 `$TRADINGAGENTS_TOKEN` 作为 Bearer 令牌。\n\n1. 提交分析任务\n```bash\ncurl -X POST \"${TRADINGAGENTS_API_URL:-https://api.510168.xyz}/v1/analyze\" \\\n  -H \"Authorization: Bearer $TRADINGAGENTS_TOKEN\" \\\n  -H \"Content-Type: application/json\" \\\n  -d '{\"symbol\": \"贵州茅台\"}'\n```\n\n2. 查询任务状态\n```bash\ncurl \"${TRADINGAGENTS_API_URL:-https://api.510168.xyz}/v1/jobs/{job_id}\" \\\n  -H \"Authorization: Bearer $TRADINGAGENTS_TOKEN\"\n```\n\n3. 获取完整分析结果（任务完成后）\n```bash\ncurl \"${TRADINGAGENTS_API_URL:-https://api.510168.xyz}/v1/jobs/{job_id}/result\" \\\n  -H \"Authorization: Bearer $TRADINGAGENTS_TOKEN\"\n```\n\n## 📊 示例输出\n\n```json\n{\n  \"decision\": \"BUY\",\n  \"direction\": \"看多\",\n  \"confidence\": 78,\n  \"target_price\": 1850.0,\n  \"stop_loss_price\": 1680.0,\n  \"risk_items\": [\n    {\"name\": \"估值偏高\", \"level\": \"medium\", \"description\": \"当前 PE 处于历史 75 分位\"},\n    {\"name\": \"外资流出\", \"level\": \"low\",    \"description\": \"近 5 日北向资金小幅净流出\"}\n  ],\n  \"key_metrics\": [\n    {\"name\": \"PE\",   \"value\": \"32.5x\",  \"status\": \"neutral\"},\n    {\"name\": \"ROE\",  \"value\": \"31.2%\",  \"status\": \"good\"},\n    {\"name\": \"毛利率\", \"value\": \"91.5%\", \"status\": \"good\"}\n  ],\n  \"final_trade_decision\": \"综合技术面突破与基本面支撑，建议逢低分批建仓...\"\n}\n```\n\n## 🔄 任务执行流程\n\n深度分析通常耗时 **1 至 5 分钟**：\n\n1. **识别标的**：从对话中**仅**提取股票名称或代码（及可选日期/视角），不发送对话原文\n2. **告知用户**：反馈任务即将提交，预计耗时 1-5 分钟\n3. **执行脚本**：使用 Bash 工具运行 `bash scripts/analyze.sh <symbol> [date] [horizons]`（设置 `run_in_background: true`），脚本自动完成提交、轮询和结果获取\n4. **汇总结论**：脚本输出完成后，解析 JSON 结果，向用户展示决策、方向、目标价、风险点\n\n> **重要**：不要手动编写 curl 轮询循环，直接使用 `scripts/analyze.sh` 脚本。\n\n## 📌 支持标的范围\n\n- **沪深 A 股**：中文名称（如 \"比亚迪\"、\"宁德时代\"）或代码（`002594.SZ`、`601012.SH`）\n\n## 💡 注意事项\n\n- **轮询频率**：每次轮询间隔不低于 15 秒\n- **数据健壮性**：若部分数据源缺失，系统将基于宏观与行业逻辑进行外溢分析\n- **短线模式**：输入\"分析 XX 短线\"时，系统自动切换为 14 天技术面分析，跳过财报数据，速度更快\n\nFile v0.6.1:_meta.json\n\n{\n  \"ownerId\": \"kn7fp71x5ttbnyv3dk5w2dvnen82vkvn\",\n  \"slug\": \"tradingagents-analysis\",\n  \"version\": \"0.6.1\",\n  \"publishedAt\": 1774748480075\n}\n\nArchive v0.6.0: 3 files, 8014 bytes\n\nFiles: scripts/analyze.sh (6421b), SKILL.md (10070b), _meta.json (141b)\n\nFile v0.6.0:SKILL.md\n\n---\nname: tradingagents-analysis\nversion: 0.6.0\ndescription: >-\n  A股多智能体 AI 投研分析工具 — 15 名 AI 分析师协作完成技术分析、基本面分析、\n  市场情绪研判、资金流向追踪（北向资金/主力资金）、宏观经济分析及博弈论推演，\n  输出结构化买卖建议与风险评估。支持沪深 A 股股票代码和中文名称。\n  Multi-agent AI stock analysis for China A-shares.\n  15 specialized analysts collaborate across technical analysis, fundamental analysis,\n  sentiment analysis, smart money flow tracking, macro economics, and game theory\n  to deliver structured buy/sell/hold recommendations with risk assessment.\nhomepage: https://app.510168.xyz\nrepository: https://github.com/KylinMountain/TradingAgents-AShare\ntags:\n  - stock-analysis\n  - A-share\n  - A股\n  - 股票分析\n  - 股票\n  - 炒股\n  - 选股\n  - 荐股\n  - trading\n  - investment\n  - 投资\n  - 投研\n  - 量化投研\n  - 研报\n  - 盘后分析\n  - 复盘\n  - multi-agent\n  - 多智能体\n  - AI分析\n  - AI炒股\n  - technical-analysis\n  - 技术分析\n  - K线\n  - fundamental-analysis\n  - 基本面分析\n  - sentiment-analysis\n  - 市场情绪\n  - smart-money\n  - 资金流向\n  - 北向资金\n  - 主力资金\n  - 龙虎榜\n  - finance\n  - 金融\n  - China\n  - 中国股市\n  - 沪深\n  - 上证\n  - 深证\n  - quant\n  - risk-assessment\n  - 风险评估\n  - 买卖建议\n  - claude-code\n  - openclaw\nenv:\n  TRADINGAGENTS_TOKEN:\n    description: \"API 访问令牌，以 ta-sk- 开头 (Bearer token starts with ta-sk-)\"\n    required: true\n    primary_credential: true\n  TRADINGAGENTS_API_URL:\n    description: \"后端 API 地址 (TradingAgents API base URL)\"\n    default: \"https://api.510168.xyz\"\nmetadata: {\"clawdbot\":{\"emoji\":\"📈\"}}\n---\n\n# TradingAgents 多智能体 A 股投研分析\n\n使用 TradingAgents API，让 **15 名专业 AI 分析师**对 A 股进行五阶段深度协作研判，输出结构化投资建议。\n\n## 🎯 快速上手\n\n**直接对我说：**\n- \"帮我分析一下贵州茅台\"\n- \"宁德时代值得买入吗\"\n- \"分析一下 600519 的技术面\"\n- \"比亚迪最近资金流向怎么样\"\n\n**我会调用 15 个 AI 分析师，从市场、技术、基本面、情绪、资金五个维度深度分析，给你专业的投资建议。**\n\n---\n\n## 🤖 系统架构：五阶段 15 智能体\n\n| 阶段 | 智能体 | 职责 |\n|------|--------|------|\n| 1. 分析团队 | 市场/新闻/情绪/基本面/宏观/聪明钱 | 多维度原始数据解读 |\n| 2. 博弈裁判 | 博弈论管理者 | 主力与散户预期差分析 |\n| 3. 多空辩论 | 多头/空头研究员 + 裁判 | 对立观点激烈博弈 |\n| 4. 执行决策 | 交易员 | 综合研判生成操作建议 |\n| 5. 风险管控 | 激进/中性/保守分析师 + 组合经理 | 多维度风控审核 |\n\n---\n\n# TradingAgents Multi-Agent Investment Research\n\nUse the TradingAgents API to let **15 specialized AI analysts** conduct deep, five-stage collaborative research on A-Share stocks, delivering structured trading recommendations.\n\n## 🤖 System Architecture: 5 Stages · 15 Agents\n\n| Stage | Agents | Role |\n|-------|--------|------|\n| 1. Analyst Team | Market / News / Sentiment / Fundamentals / Macro / Smart Money | Multi-dimensional raw data analysis |\n| 2. Game Theory | Game Theory Manager | Main-force vs. retail expectation gap |\n| 3. Bull/Bear Debate | Bull & Bear Researchers + Judge | Adversarial viewpoint debate |\n| 4. Trade Execution | Trader | Synthesize research into actionable decision |\n| 5. Risk Control | Aggressive / Neutral / Conservative + Portfolio Manager | Multi-layer risk review |\n\n## 📋 适用场景\n\n✅ **适合使用：**\n- 个股深度分析（技术面 + 基本面）\n- 投资决策参考\n- 盘后复盘分析\n- 持仓标的风险评估\n- 资金流向与市场情绪研判\n\n❌ **不适合：**\n- 盘中实时盯盘（分析需要 1-5 分钟）\n- 超短线交易（分钟级决策）\n- 加密货币、美股等非 A 股市场\n\n## 🔒 隐私与安全\n\n- **发送范围**：本技能**仅**从对话中提取股票名称/代码、分析日期、分析视角等参数，将其作为 `symbol`/`trade_date`/`horizons` 字段发送至后端 API。**不发送对话原文、不读取本地文件、不上传任何其他隐私数据。**\n- **令牌安全**：`TRADINGAGENTS_TOKEN`（格式 `ta-sk-*`）是访问后端的唯一凭证，请使用最小权限令牌，如怀疑泄露请立即在 [app.510168.xyz](https://app.510168.xyz) 吊销并重新生成。\n- **敏感内容提示**：请勿在分析请求中粘贴个人账户信息、真实持仓或其他敏感内容，本技能无法阻止用户主动提交这些内容。\n- **自托管**：如需完全掌控数据流向，可参考 [GitHub 文档](https://github.com/KylinMountain/TradingAgents-AShare) 自行部署后端，并将 `TRADINGAGENTS_API_URL` 指向自建服务器。\n\n> **关于凭证元数据**：本技能的 frontmatter 已声明 `TRADINGAGENTS_TOKEN` 为 `required: true` 及 `primary_credential`。\n\n## 🔒 Privacy & Data Transmission\n\n- **What is sent**: Only the extracted stock symbol, trade date, and analysis parameters (`symbol`, `trade_date`, `horizons`) are transmitted to the backend. The raw conversation text is **never** forwarded.\n- **Token**: `TRADINGAGENTS_TOKEN` (pattern `ta-sk-*`) is the sole credential. Use a minimal-privilege token and rotate it immediately if compromised.\n- **Sensitive content**: Do not paste personal account data, real positions, or other sensitive information into analysis requests.\n- **Self-hosting**: For full data sovereignty, deploy the backend yourself and set `TRADINGAGENTS_API_URL` to your server. See the [GitHub repo](https://github.com/KylinMountain/TradingAgents-AShare).\n\n> **Credential metadata**: This skill's frontmatter declares `TRADINGAGENTS_TOKEN` as `required: true` and `primary_credential`.\n\n## ⚙️ 快速配置\n\n**方式一：使用官方托管服务（零部署，开箱即用）**\n\n1. 登录 [https://app.510168.xyz](https://app.510168.xyz)\n2. 进入 **Settings → API Tokens** 创建令牌\n3. 配置环境变量：\n```bash\nexport TRADINGAGENTS_TOKEN=\"ta-sk-your_key_here\"\n```\n\n**方式二：私有化部署（数据完全自主可控）**\n\n如对数据隐私有要求，可自行部署后端，所有分析数据仅在你自己的服务器上处理：\n\n```bash\n# 1. 部署后端，参考 https://github.com/KylinMountain/TradingAgents-AShare\n# 2. 将 API 地址指向自建服务\nexport TRADINGAGENTS_API_URL=\"http://your-server:8000\"\nexport TRADINGAGENTS_TOKEN=\"ta-sk-your_key_here\"\n```\n\n## 🚀 常用操作\n\n**推荐方式：使用一体化脚本**（自动提交 → 轮询 → 获取结果）\n\n```bash\n# 脚本路径（相对于技能目录）\nbash scripts/analyze.sh <symbol[,symbol2,...]> [trade_date] [horizons]\n\n# 单个分析\nbash scripts/analyze.sh 贵州茅台\nbash scripts/analyze.sh 600519.SH 2026-03-22\nbash scripts/analyze.sh 600519.SH 2026-03-22 medium\n\n# 批量分析（逗号分隔，并行提交，统一等待）\nbash scripts/analyze.sh 贵州茅台,比亚迪,宁德时代\nbash scripts/analyze.sh 600519.SH,002594.SZ,300750.SZ 2026-03-22\n```\n\n脚本会自动完成：提交任务 → 每 15 秒轮询状态 → 完成后输出 JSON 结果。\n批量模式下所有任务并行提交，统一轮询，最后汇总输出。超时默认 600 秒。\n\n可通过环境变量调整行为：\n- `POLL_INTERVAL` — 轮询间隔秒数（默认 15）\n- `POLL_TIMEOUT` — 最大等待秒数（默认 600）\n\n**手动分步操作**（如需单独调用某一步）\n\n所有请求使用 `$TRADINGAGENTS_TOKEN` 作为 Bearer 令牌。\n\n1. 提交分析任务\n```bash\ncurl -X POST \"${TRADINGAGENTS_API_URL:-https://api.510168.xyz}/v1/analyze\" \\\n  -H \"Authorization: Bearer $TRADINGAGENTS_TOKEN\" \\\n  -H \"Content-Type: application/json\" \\\n  -d '{\"symbol\": \"贵州茅台\"}'\n```\n\n2. 查询任务状态\n```bash\ncurl \"${TRADINGAGENTS_API_URL:-https://api.510168.xyz}/v1/jobs/{job_id}\" \\\n  -H \"Authorization: Bearer $TRADINGAGENTS_TOKEN\"\n```\n\n3. 获取完整分析结果（任务完成后）\n```bash\ncurl \"${TRADINGAGENTS_API_URL:-https://api.510168.xyz}/v1/jobs/{job_id}/result\" \\\n  -H \"Authorization: Bearer $TRADINGAGENTS_TOKEN\"\n```\n\n## 📊 示例输出\n\n```json\n{\n  \"decision\": \"BUY\",\n  \"direction\": \"看多\",\n  \"confidence\": 78,\n  \"target_price\": 1850.0,\n  \"stop_loss_price\": 1680.0,\n  \"risk_items\": [\n    {\"name\": \"估值偏高\", \"level\": \"medium\", \"description\": \"当前 PE 处于历史 75 分位\"},\n    {\"name\": \"外资流出\", \"level\": \"low\",    \"description\": \"近 5 日北向资金小幅净流出\"}\n  ],\n  \"key_metrics\": [\n    {\"name\": \"PE\",   \"value\": \"32.5x\",  \"status\": \"neutral\"},\n    {\"name\": \"ROE\",  \"value\": \"31.2%\",  \"status\": \"good\"},\n    {\"name\": \"毛利率\", \"value\": \"91.5%\", \"status\": \"good\"}\n  ],\n  \"final_trade_decision\": \"综合技术面突破与基本面支撑，建议逢低分批建仓...\"\n}\n```\n\n## 🔄 任务执行流程\n\n深度分析通常耗时 **1 至 5 分钟**：\n\n1. **识别标的**：从对话中**仅**提取股票名称或代码（及可选日期/视角），不发送对话原文\n2. **告知用户**：反馈任务即将提交，预计耗时 1-5 分钟\n3. **执行脚本**：使用 Bash 工具运行 `bash scripts/analyze.sh <symbol> [date] [horizons]`（设置 `run_in_background: true`），脚本自动完成提交、轮询和结果获取\n4. **汇总结论**：脚本输出完成后，解析 JSON 结果，向用户展示决策、方向、目标价、风险点\n\n> **重要**：不要手动编写 curl 轮询循环，直接使用 `scripts/analyze.sh` 脚本。\n\n## 📌 支持标的范围\n\n- **沪深 A 股**：中文名称（如 \"比亚迪\"、\"宁德时代\"）或代码（`002594.SZ`、`601012.SH`）\n\n## 💡 注意事项\n\n- **轮询频率**：每次轮询间隔不低于 15 秒\n- **数据健壮性**：若部分数据源缺失，系统将基于宏观与行业逻辑进行外溢分析\n- **短线模式**：输入\"分析 XX 短线\"时，系统自动切换为 14 天技术面分析，跳过财报数据，速度更快\n\nFile v0.6.0:_meta.json\n\n{\n  \"ownerId\": \"kn7fp71x5ttbnyv3dk5w2dvnen82vkvn\",\n  \"slug\": \"tradingagents-analysis\",\n  \"version\": \"0.6.0\",\n  \"publishedAt\": 1774748079146\n}\n\nArchive v0.5.0: 3 files, 7679 bytes\n\nFiles: scripts/analyze.sh (6311b), SKILL.md (9156b), _meta.json (141b)\n\nFile v0.5.0:SKILL.md\n\n---\nname: tradingagents-analysis\ndescription: 专业 A 股多智能体投研工具。15 名 AI 分析师五阶段协作，深度分析技术面、基本面、市场情绪与资金流向，提供结构化交易建议。Professional multi-agent investment research for A-Share & US stocks — market, fundamentals, sentiment, smart money.\nhomepage: https://app.510168.xyz\nrepository: https://github.com/KylinMountain/TradingAgents-AShare\ntags:\n  - A股\n  - 股票分析\n  - 量化投研\n  - 多智能体\n  - TradingAgent\n  - A-share\n  - stock-analysis\n  - China\n  - Multi-Agent\n  - 研报\n  - 资金流向\n  - 技术分析\n  - 基本面分析\nenv:\n  TRADINGAGENTS_API_URL:\n    description: \"后端 API 地址 (TradingAgents API base URL)\"\n    default: \"https://api.510168.xyz\"\n  TRADINGAGENTS_TOKEN:\n    description: \"API 访问令牌，以 ta-sk- 开头 (Bearer token starts with ta-sk-)\"\n    required: true\nprimary_credential: TRADINGAGENTS_TOKEN\nmetadata: {\"clawdbot\":{\"emoji\":\"📈\"}}\n---\n\n# TradingAgents 多智能体 A 股投研分析\n\n使用 TradingAgents API，让 **15 名专业 AI 分析师**对 A 股进行五阶段深度协作研判，输出结构化投资建议。\n\n## 🎯 快速上手\n\n**直接对我说：**\n- \"帮我分析一下贵州茅台\"\n- \"宁德时代值得买入吗\"\n- \"分析一下 600519 的技术面\"\n- \"比亚迪最近资金流向怎么样\"\n\n**我会调用 15 个 AI 分析师，从市场、技术、基本面、情绪、资金五个维度深度分析，给你专业的投资建议。**\n\n---\n\n## 🤖 系统架构：五阶段 15 智能体\n\n| 阶段 | 智能体 | 职责 |\n|------|--------|------|\n| 1. 分析团队 | 市场/新闻/情绪/基本面/宏观/聪明钱 | 多维度原始数据解读 |\n| 2. 博弈裁判 | 博弈论管理者 | 主力与散户预期差分析 |\n| 3. 多空辩论 | 多头/空头研究员 + 裁判 | 对立观点激烈博弈 |\n| 4. 执行决策 | 交易员 | 综合研判生成操作建议 |\n| 5. 风险管控 | 激进/中性/保守分析师 + 组合经理 | 多维度风控审核 |\n\n---\n\n# TradingAgents Multi-Agent Investment Research\n\nUse the TradingAgents API to let **15 specialized AI analysts** conduct deep, five-stage collaborative research on A-Share and US stocks, delivering structured trading recommendations.\n\n## 🤖 System Architecture: 5 Stages · 15 Agents\n\n| Stage | Agents | Role |\n|-------|--------|------|\n| 1. Analyst Team | Market / News / Sentiment / Fundamentals / Macro / Smart Money | Multi-dimensional raw data analysis |\n| 2. Game Theory | Game Theory Manager | Main-force vs. retail expectation gap |\n| 3. Bull/Bear Debate | Bull & Bear Researchers + Judge | Adversarial viewpoint debate |\n| 4. Trade Execution | Trader | Synthesize research into actionable decision |\n| 5. Risk Control | Aggressive / Neutral / Conservative + Portfolio Manager | Multi-layer risk review |\n\n## 📋 适用场景\n\n✅ **适合使用：**\n- 个股深度分析（技术面 + 基本面）\n- 投资决策参考\n- 盘后复盘分析\n- 持仓标的风险评估\n- 资金流向与市场情绪研判\n\n❌ **不适合：**\n- 盘中实时盯盘（分析需要 1-5 分钟）\n- 超短线交易（分钟级决策）\n- 加密货币分析（仅支持 A 股/美股）\n\n## 🔒 隐私与安全\n\n- **发送范围**：本技能**仅**从对话中提取股票名称/代码、分析日期、分析视角等参数，将其作为 `symbol`/`trade_date`/`horizons` 字段发送至后端 API。**不发送对话原文、不读取本地文件、不上传任何其他隐私数据。**\n- **令牌安全**：`TRADINGAGENTS_TOKEN`（格式 `ta-sk-*`）是访问后端的唯一凭证，请使用最小权限令牌，如怀疑泄露请立即在 [app.510168.xyz](https://app.510168.xyz) 吊销并重新生成。\n- **敏感内容提示**：请勿在分析请求中粘贴个人账户信息、真实持仓或其他敏感内容，本技能无法阻止用户主动提交这些内容。\n- **自托管**：如需完全掌控数据流向，可参考 [GitHub 文档](https://github.com/KylinMountain/TradingAgents-AShare) 自行部署后端，并将 `TRADINGAGENTS_API_URL` 指向自建服务器。\n\n> **关于凭证元数据**：本技能的授权 frontmatter 已声明 `TRADINGAGENTS_TOKEN` 为 `required: true` 及 `primary_credential`，此为权威配置。若任何注册表缓存显示无必填环境变量，请以本 SKILL.md 为准。\n\n## 🔒 Privacy & Data Transmission\n\n- **What is sent**: Only the extracted stock symbol, trade date, and analysis parameters (`symbol`, `trade_date`, `horizons`) are transmitted to the backend. The raw conversation text is **never** forwarded.\n- **Token**: `TRADINGAGENTS_TOKEN` (pattern `ta-sk-*`) is the sole credential. Use a minimal-privilege token and rotate it immediately if compromised.\n- **Sensitive content**: Do not paste personal account data, real positions, or other sensitive information into analysis requests.\n- **Self-hosting**: For full data sovereignty, deploy the backend yourself and set `TRADINGAGENTS_API_URL` to your server. See the [GitHub repo](https://github.com/KylinMountain/TradingAgents-AShare).\n\n> **Credential metadata**: This skill's frontmatter declares `TRADINGAGENTS_TOKEN` as `required: true` and `primary_credential`. This SKILL.md is authoritative — disregard any registry cache that omits the required env var.\n\n## ⚙️ 快速配置\n\n1. 登录 [https://app.510168.xyz](https://app.510168.xyz)\n2. 进入 **Settings → API Tokens** 创建令牌\n3. 配置环境变量：\n```bash\nexport TRADINGAGENTS_TOKEN=\"ta-sk-your_key_here\"\n# 可选，自托管时使用：\n# export TRADINGAGENTS_API_URL=\"http://your-server:8000\"\n```\n\n## 🚀 常用操作\n\n**推荐方式：使用一体化脚本**（自动提交 → 轮询 → 获取结果）\n\n```bash\n# 脚本路径（相对于技能目录）\nbash scripts/analyze.sh <symbol[,symbol2,...]> [trade_date] [horizons]\n\n# 单个分析\nbash scripts/analyze.sh 贵州茅台\nbash scripts/analyze.sh 600519.SH 2026-03-22\nbash scripts/analyze.sh AAPL 2026-03-22 short,medium\n\n# 批量分析（逗号分隔，并行提交，统一等待）\nbash scripts/analyze.sh 贵州茅台,比亚迪,宁德时代\nbash scripts/analyze.sh 600519.SH,002594.SZ,300750.SZ 2026-03-22\n```\n\n脚本会自动完成：提交任务 → 每 15 秒轮询状态 → 完成后输出 JSON 结果。\n批量模式下所有任务并行提交，统一轮询，最后汇总输出。超时默认 600 秒。\n\n可通过环境变量调整行为：\n- `POLL_INTERVAL` — 轮询间隔秒数（默认 15）\n- `POLL_TIMEOUT` — 最大等待秒数（默认 600）\n\n**手动分步操作**（如需单独调用某一步）\n\n所有请求使用 `$TRADINGAGENTS_TOKEN` 作为 Bearer 令牌。\n\n1. 提交分析任务\n```bash\ncurl -X POST \"${TRADINGAGENTS_API_URL:-https://api.510168.xyz}/v1/analyze\" \\\n  -H \"Authorization: Bearer $TRADINGAGENTS_TOKEN\" \\\n  -H \"Content-Type: application/json\" \\\n  -d '{\"symbol\": \"贵州茅台\"}'\n```\n\n2. 查询任务状态\n```bash\ncurl \"${TRADINGAGENTS_API_URL:-https://api.510168.xyz}/v1/jobs/{job_id}\" \\\n  -H \"Authorization: Bearer $TRADINGAGENTS_TOKEN\"\n```\n\n3. 获取完整分析结果（任务完成后）\n```bash\ncurl \"${TRADINGAGENTS_API_URL:-https://api.510168.xyz}/v1/jobs/{job_id}/result\" \\\n  -H \"Authorization: Bearer $TRADINGAGENTS_TOKEN\"\n```\n\n## 📊 示例输出\n\n```json\n{\n  \"decision\": \"BUY\",\n  \"direction\": \"看多\",\n  \"confidence\": 78,\n  \"target_price\": 1850.0,\n  \"stop_loss_price\": 1680.0,\n  \"risk_items\": [\n    {\"name\": \"估值偏高\", \"level\": \"medium\", \"description\": \"当前 PE 处于历史 75 分位\"},\n    {\"name\": \"外资流出\", \"level\": \"low\",    \"description\": \"近 5 日北向资金小幅净流出\"}\n  ],\n  \"key_metrics\": [\n    {\"name\": \"PE\",   \"value\": \"32.5x\",  \"status\": \"neutral\"},\n    {\"name\": \"ROE\",  \"value\": \"31.2%\",  \"status\": \"good\"},\n    {\"name\": \"毛利率\", \"value\": \"91.5%\", \"status\": \"good\"}\n  ],\n  \"final_trade_decision\": \"综合技术面突破与基本面支撑，建议逢低分批建仓...\"\n}\n```\n\n## 🔄 任务执行流程\n\n深度分析通常耗时 **1 至 5 分钟**：\n\n1. **识别标的**：从对话中**仅**提取股票名称或代码（及可选日期/视角），不发送对话原文\n2. **告知用户**：反馈任务即将提交，预计耗时 1-5 分钟\n3. **执行脚本**：使用 Bash 工具运行 `bash scripts/analyze.sh <symbol> [date] [horizons]`（设置 `run_in_background: true`），脚本自动完成提交、轮询和结果获取\n4. **汇总结论**：脚本输出完成后，解析 JSON 结果，向用户展示决策、方向、目标价、风险点\n\n> **重要**：不要手动编写 curl 轮询循环，直接使用 `scripts/analyze.sh` 脚本。\n\n## 📌 支持标的范围\n\n- **A 股**：中文名称（如 \"比亚迪\"、\"宁德时代\"）或代码（`002594.SZ`、`601012.SH`）\n- **美股**：`AAPL`、`TSLA`、`NVDA` 等标准 Ticker\n\n## 💡 注意事项\n\n- **轮询频率**：每次轮询间隔不低于 15 秒\n- **数据健壮性**：若部分数据源缺失，系统将基于宏观与行业逻辑进行外溢分析\n- **短线模式**：输入\"分析 XX 短线\"时，系统自动切换为 14 天技术面分析，跳过财报数据，速度更快\n\nFile v0.5.0:_meta.json\n\n{\n  \"ownerId\": \"kn7fp71x5ttbnyv3dk5w2dvnen82vkvn\",\n  \"slug\": \"tradingagents-analysis\",\n  \"version\": \"0.5.0\",\n  \"publishedAt\": 1774232218197\n}\n\nArchive v0.4.4: 2 files, 4673 bytes\n\nFiles: SKILL.md (8324b), _meta.json (141b)\n\nFile v0.4.4:SKILL.md\n\n---\nname: tradingagents-analysis\ndescription: 专业 A 股多智能体投研工具。15 名 AI 分析师五阶段协作，深度分析技术面、基本面、市场情绪与资金流向，提供结构化交易建议。Professional multi-agent investment research for A-Share & US stocks — market, fundamentals, sentiment, smart money.\nhomepage: https://app.510168.xyz\nrepository: https://github.com/KylinMountain/TradingAgents-AShare\ntags:\n  - A股\n  - 股票分析\n  - 量化投研\n  - 多智能体\n  - TradingAgent\n  - A-share\n  - stock-analysis\n  - China\n  - Multi-Agent\n  - 研报\n  - 资金流向\n  - 技术分析\n  - 基本面分析\nenv:\n  TRADINGAGENTS_API_URL:\n    description: \"后端 API 地址 (TradingAgents API base URL)\"\n    default: \"https://api.510168.xyz\"\n  TRADINGAGENTS_TOKEN:\n    description: \"API 访问令牌，以 ta-sk- 开头 (Bearer token starts with ta-sk-)\"\n    required: true\nprimary_credential: TRADINGAGENTS_TOKEN\nmetadata: {\"clawdbot\":{\"emoji\":\"📈\"}}\n---\n\n# TradingAgents 多智能体 A 股投研分析\n\n使用 TradingAgents API，让 **15 名专业 AI 分析师**对 A 股进行五阶段深度协作研判，输出结构化投资建议。\n\n## 🎯 快速上手\n\n**直接对我说：**\n- \"帮我分析一下贵州茅台\"\n- \"宁德时代值得买入吗\"\n- \"分析一下 600519 的技术面\"\n- \"比亚迪最近资金流向怎么样\"\n\n**我会调用 15 个 AI 分析师，从市场、技术、基本面、情绪、资金五个维度深度分析，给你专业的投资建议。**\n\n---\n\n## 🤖 系统架构：五阶段 15 智能体\n\n| 阶段 | 智能体 | 职责 |\n|------|--------|------|\n| 1. 分析团队 | 市场/新闻/情绪/基本面/宏观/聪明钱 | 多维度原始数据解读 |\n| 2. 博弈裁判 | 博弈论管理者 | 主力与散户预期差分析 |\n| 3. 多空辩论 | 多头/空头研究员 + 裁判 | 对立观点激烈博弈 |\n| 4. 执行决策 | 交易员 | 综合研判生成操作建议 |\n| 5. 风险管控 | 激进/中性/保守分析师 + 组合经理 | 多维度风控审核 |\n\n---\n\n# TradingAgents Multi-Agent Investment Research\n\nUse the TradingAgents API to let **15 specialized AI analysts** conduct deep, five-stage collaborative research on A-Share and US stocks, delivering structured trading recommendations.\n\n## 🤖 System Architecture: 5 Stages · 15 Agents\n\n| Stage | Agents | Role |\n|-------|--------|------|\n| 1. Analyst Team | Market / News / Sentiment / Fundamentals / Macro / Smart Money | Multi-dimensional raw data analysis |\n| 2. Game Theory | Game Theory Manager | Main-force vs. retail expectation gap |\n| 3. Bull/Bear Debate | Bull & Bear Researchers + Judge | Adversarial viewpoint debate |\n| 4. Trade Execution | Trader | Synthesize research into actionable decision |\n| 5. Risk Control | Aggressive / Neutral / Conservative + Portfolio Manager | Multi-layer risk review |\n\n## 📋 适用场景\n\n✅ **适合使用：**\n- 个股深度分析（技术面 + 基本面）\n- 投资决策参考\n- 盘后复盘分析\n- 持仓标的风险评估\n- 资金流向与市场情绪研判\n\n❌ **不适合：**\n- 盘中实时盯盘（分析需要 1-5 分钟）\n- 超短线交易（分钟级决策）\n- 加密货币分析（仅支持 A 股/美股）\n\n## 🔒 隐私与安全\n\n- **发送范围**：本技能**仅**从对话中提取股票名称/代码、分析日期、分析视角等参数，将其作为 `symbol`/`trade_date`/`horizons` 字段发送至后端 API。**不发送对话原文、不读取本地文件、不上传任何其他隐私数据。**\n- **令牌安全**：`TRADINGAGENTS_TOKEN`（格式 `ta-sk-*`）是访问后端的唯一凭证，请使用最小权限令牌，如怀疑泄露请立即在 [app.510168.xyz](https://app.510168.xyz) 吊销并重新生成。\n- **敏感内容提示**：请勿在分析请求中粘贴个人账户信息、真实持仓或其他敏感内容，本技能无法阻止用户主动提交这些内容。\n- **自托管**：如需完全掌控数据流向，可参考 [GitHub 文档](https://github.com/KylinMountain/TradingAgents-AShare) 自行部署后端，并将 `TRADINGAGENTS_API_URL` 指向自建服务器。\n\n> **关于凭证元数据**：本技能的授权 frontmatter 已声明 `TRADINGAGENTS_TOKEN` 为 `required: true` 及 `primary_credential`，此为权威配置。若任何注册表缓存显示无必填环境变量，请以本 SKILL.md 为准。\n\n## 🔒 Privacy & Data Transmission\n\n- **What is sent**: Only the extracted stock symbol, trade date, and analysis parameters (`symbol`, `trade_date`, `horizons`) are transmitted to the backend. The raw conversation text is **never** forwarded.\n- **Token**: `TRADINGAGENTS_TOKEN` (pattern `ta-sk-*`) is the sole credential. Use a minimal-privilege token and rotate it immediately if compromised.\n- **Sensitive content**: Do not paste personal account data, real positions, or other sensitive information into analysis requests.\n- **Self-hosting**: For full data sovereignty, deploy the backend yourself and set `TRADINGAGENTS_API_URL` to your server. See the [GitHub repo](https://github.com/KylinMountain/TradingAgents-AShare).\n\n> **Credential metadata**: This skill's frontmatter declares `TRADINGAGENTS_TOKEN` as `required: true` and `primary_credential`. This SKILL.md is authoritative — disregard any registry cache that omits the required env var.\n\n## ⚙️ 快速配置\n\n1. 登录 [https://app.510168.xyz](https://app.510168.xyz)\n2. 进入 **Settings → API Tokens** 创建令牌\n3. 配置环境变量：\n```bash\nexport TRADINGAGENTS_TOKEN=\"ta-sk-your_key_here\"\n# 可选，自托管时使用：\n# export TRADINGAGENTS_API_URL=\"http://your-server:8000\"\n```\n\n## 🚀 常用操作\n\n所有请求使用 `$TRADINGAGENTS_TOKEN` 作为 Bearer 令牌。\n\n**1. 提交分析任务**（支持中文名称、6 位代码或标准代码）\n```bash\n# 中文名称\ncurl -X POST \"${TRADINGAGENTS_API_URL:-https://api.510168.xyz}/v1/analyze\" \\\n  -H \"Authorization: Bearer $TRADINGAGENTS_TOKEN\" \\\n  -H \"Content-Type: application/json\" \\\n  -d '{\"symbol\": \"贵州茅台\"}'\n\n# 标准代码\ncurl -X POST \"${TRADINGAGENTS_API_URL:-https://api.510168.xyz}/v1/analyze\" \\\n  -H \"Authorization: Bearer $TRADINGAGENTS_TOKEN\" \\\n  -H \"Content-Type: application/json\" \\\n  -d '{\"symbol\": \"600519.SH\"}'\n```\n\n**2. 查询任务状态**\n```bash\ncurl \"${TRADINGAGENTS_API_URL:-https://api.510168.xyz}/v1/jobs/{job_id}\" \\\n  -H \"Authorization: Bearer $TRADINGAGENTS_TOKEN\"\n```\n\n**3. 获取完整分析结果**（任务完成后）\n```bash\ncurl \"${TRADINGAGENTS_API_URL:-https://api.510168.xyz}/v1/jobs/{job_id}/result\" \\\n  -H \"Authorization: Bearer $TRADINGAGENTS_TOKEN\"\n```\n\n## 📊 示例输出\n\n```json\n{\n  \"decision\": \"BUY\",\n  \"direction\": \"看多\",\n  \"confidence\": 78,\n  \"target_price\": 1850.0,\n  \"stop_loss_price\": 1680.0,\n  \"risk_items\": [\n    {\"name\": \"估值偏高\", \"level\": \"medium\", \"description\": \"当前 PE 处于历史 75 分位\"},\n    {\"name\": \"外资流出\", \"level\": \"low\",    \"description\": \"近 5 日北向资金小幅净流出\"}\n  ],\n  \"key_metrics\": [\n    {\"name\": \"PE\",   \"value\": \"32.5x\",  \"status\": \"neutral\"},\n    {\"name\": \"ROE\",  \"value\": \"31.2%\",  \"status\": \"good\"},\n    {\"name\": \"毛利率\", \"value\": \"91.5%\", \"status\": \"good\"}\n  ],\n  \"final_trade_decision\": \"综合技术面突破与基本面支撑，建议逢低分批建仓...\"\n}\n```\n\n## 🔄 任务执行流程\n\n深度分析通常耗时 **1 至 5 分钟**：\n\n1. **识别标的**：从对话中**仅**提取股票名称或代码（及可选日期/视角），不发送对话原文\n2. **提交任务**：调用 `POST /v1/analyze`，仅传递 `symbol`、`trade_date`、`horizons` 等结构化参数\n3. **告知用户**：反馈任务已受理，预计耗时\n4. **轮询进度**：每 30 秒查询一次状态\n5. **汇总结论**：任务完成后提取并展示决策、方向、目标价、风险点\n\n## 📌 支持标的范围\n\n- **A 股**：中文名称（如 \"比亚迪\"、\"宁德时代\"）或代码（`002594.SZ`、`601012.SH`）\n- **美股**：`AAPL`、`TSLA`、`NVDA` 等标准 Ticker\n\n## 💡 注意事项\n\n- **轮询频率**：每次轮询间隔不低于 15 秒\n- **数据健壮性**：若部分数据源缺失，系统将基于宏观与行业逻辑进行外溢分析\n- **短线模式**：输入\"分析 XX 短线\"时，系统自动切换为 14 天技术面分析，跳过财报数据，速度更快\n\nFile v0.4.4:_meta.json\n\n{\n  \"ownerId\": \"kn7fp71x5ttbnyv3dk5w2dvnen82vkvn\",\n  \"slug\": \"tradingagents-analysis\",\n  \"version\": \"0.4.4\",\n  \"publishedAt\": 1773584475344\n}\n\nArchive v0.4.3: 2 files, 4673 bytes\n\nFiles: SKILL.md (8324b), _meta.json (141b)\n\nFile v0.4.3:SKILL.md\n\n---\nname: tradingagents-analysis\ndescription: 专业 A 股多智能体投研工具。15 名 AI 分析师五阶段协作，深度分析技术面、基本面、市场情绪与资金流向，提供结构化交易建议。Professional multi-agent investment research for A-Share & US stocks — market, fundamentals, sentiment, smart money.\nhomepage: https://app.510168.xyz\nrepository: https://github.com/KylinMountain/TradingAgents-AShare\ntags:\n  - A股\n  - 股票分析\n  - 量化投研\n  - 多智能体\n  - TradingAgent\n  - A-share\n  - stock-analysis\n  - China\n  - Multi-Agent\n  - 研报\n  - 资金流向\n  - 技术分析\n  - 基本面分析\nenv:\n  TRADINGAGENTS_API_URL:\n    description: \"后端 API 地址 (TradingAgents API base URL)\"\n    default: \"https://api.510168.xyz\"\n  TRADINGAGENTS_TOKEN:\n    description: \"API 访问令牌，以 ta-sk- 开头 (Bearer token starts with ta-sk-)\"\n    required: true\nprimary_credential: TRADINGAGENTS_TOKEN\nmetadata: {\"clawdbot\":{\"emoji\":\"📈\"}}\n---\n\n# TradingAgents 多智能体 A 股投研分析\n\n使用 TradingAgents API，让 **15 名专业 AI 分析师**对 A 股进行五阶段深度协作研判，输出结构化投资建议。\n\n## 🎯 快速上手\n\n**直接对我说：**\n- \"帮我分析一下贵州茅台\"\n- \"宁德时代值得买入吗\"\n- \"分析一下 600519 的技术面\"\n- \"比亚迪最近资金流向怎么样\"\n\n**我会调用 15 个 AI 分析师，从市场、技术、基本面、情绪、资金五个维度深度分析，给你专业的投资建议。**\n\n---\n\n## 🤖 系统架构：五阶段 15 智能体\n\n| 阶段 | 智能体 | 职责 |\n|------|--------|------|\n| 1. 分析团队 | 市场/新闻/情绪/基本面/宏观/聪明钱 | 多维度原始数据解读 |\n| 2. 博弈裁判 | 博弈论管理者 | 主力与散户预期差分析 |\n| 3. 多空辩论 | 多头/空头研究员 + 裁判 | 对立观点激烈博弈 |\n| 4. 执行决策 | 交易员 | 综合研判生成操作建议 |\n| 5. 风险管控 | 激进/中性/保守分析师 + 组合经理 | 多维度风控审核 |\n\n---\n\n# TradingAgents Multi-Agent Investment Research\n\nUse the TradingAgents API to let **15 specialized AI analysts** conduct deep, five-stage collaborative research on A-Share and US stocks, delivering structured trading recommendations.\n\n## 🤖 System Architecture: 5 Stages · 15 Agents\n\n| Stage | Agents | Role |\n|-------|--------|------|\n| 1. Analyst Team | Market / News / Sentiment / Fundamentals / Macro / Smart Money | Multi-dimensional raw data analysis |\n| 2. Game Theory | Game Theory Manager | Main-force vs. retail expectation gap |\n| 3. Bull/Bear Debate | Bull & Bear Researchers + Judge | Adversarial viewpoint debate |\n| 4. Trade Execution | Trader | Synthesize research into actionable decision |\n| 5. Risk Control | Aggressive / Neutral / Conservative + Portfolio Manager | Multi-layer risk review |\n\n## 📋 适用场景\n\n✅ **适合使用：**\n- 个股深度分析（技术面 + 基本面）\n- 投资决策参考\n- 盘后复盘分析\n- 持仓标的风险评估\n- 资金流向与市场情绪研判\n\n❌ **不适合：**\n- 盘中实时盯盘（分析需要 1-5 分钟）\n- 超短线交易（分钟级决策）\n- 加密货币分析（仅支持 A 股/美股）\n\n## 🔒 隐私与安全\n\n- **发送范围**：本技能**仅**从对话中提取股票名称/代码、分析日期、分析视角等参数，将其作为 `symbol`/`trade_date`/`horizons` 字段发送至后端 API。**不发送对话原文、不读取本地文件、不上传任何其他隐私数据。**\n- **令牌安全**：`TRADINGAGENTS_TOKEN`（格式 `ta-sk-*`）是访问后端的唯一凭证，请使用最小权限令牌，如怀疑泄露请立即在 [app.510168.xyz](https://app.510168.xyz) 吊销并重新生成。\n- **敏感内容提示**：请勿在分析请求中粘贴个人账户信息、真实持仓或其他敏感内容，本技能无法阻止用户主动提交这些内容。\n- **自托管**：如需完全掌控数据流向，可参考 [GitHub 文档](https://github.com/KylinMountain/TradingAgents-AShare) 自行部署后端，并将 `TRADINGAGENTS_API_URL` 指向自建服务器。\n\n> **关于凭证元数据**：本技能的授权 frontmatter 已声明 `TRADINGAGENTS_TOKEN` 为 `required: true` 及 `primary_credential`，此为权威配置。若任何注册表缓存显示无必填环境变量，请以本 SKILL.md 为准。\n\n## 🔒 Privacy & Data Transmission\n\n- **What is sent**: Only the extracted stock symbol, trade date, and analysis parameters (`symbol`, `trade_date`, `horizons`) are transmitted to the backend. The raw conversation text is **never** forwarded.\n- **Token**: `TRADINGAGENTS_TOKEN` (pattern `ta-sk-*`) is the sole credential. Use a minimal-privilege token and rotate it immediately if compromised.\n- **Sensitive content**: Do not paste personal account data, real positions, or other sensitive information into analysis requests.\n- **Self-hosting**: For full data sovereignty, deploy the backend yourself and set `TRADINGAGENTS_API_URL` to your server. See the [GitHub repo](https://github.com/KylinMountain/TradingAgents-AShare).\n\n> **Credential metadata**: This skill's frontmatter declares `TRADINGAGENTS_TOKEN` as `required: true` and `primary_credential`. This SKILL.md is authoritative — disregard any registry cache that omits the required env var.\n\n## ⚙️ 快速配置\n\n1. 登录 [https://app.510168.xyz](https://app.510168.xyz)\n2. 进入 **Settings → API Tokens** 创建令牌\n3. 配置环境变量：\n```bash\nexport TRADINGAGENTS_TOKEN=\"ta-sk-your_key_here\"\n# 可选，自托管时使用：\n# export TRADINGAGENTS_API_URL=\"http://your-server:8000\"\n```\n\n## 🚀 常用操作\n\n所有请求使用 `$TRADINGAGENTS_TOKEN` 作为 Bearer 令牌。\n\n**1. 提交分析任务**（支持中文名称、6 位代码或标准代码）\n```bash\n# 中文名称\ncurl -X POST \"${TRADINGAGENTS_API_URL:-https://api.510168.xyz}/v1/analyze\" \\\n  -H \"Authorization: Bearer $TRADINGAGENTS_TOKEN\" \\\n  -H \"Content-Type: application/json\" \\\n  -d '{\"symbol\": \"贵州茅台\"}'\n\n# 标准代码\ncurl -X POST \"${TRADINGAGENTS_API_URL:-https://api.510168.xyz}/v1/analyze\" \\\n  -H \"Authorization: Bearer $TRADINGAGENTS_TOKEN\" \\\n  -H \"Content-Type: application/json\" \\\n  -d '{\"symbol\": \"600519.SH\"}'\n```\n\n**2. 查询任务状态**\n```bash\ncurl \"${TRADINGAGENTS_API_URL:-https://api.510168.xyz}/v1/jobs/{job_id}\" \\\n  -H \"Authorization: Bearer $TRADINGAGENTS_TOKEN\"\n```\n\n**3. 获取完整分析结果**（任务完成后）\n```bash\ncurl \"${TRADINGAGENTS_API_URL:-https://api.510168.xyz}/v1/jobs/{job_id}/result\" \\\n  -H \"Authorization: Bearer $TRADINGAGENTS_TOKEN\"\n```\n\n## 📊 示例输出\n\n```json\n{\n  \"decision\": \"BUY\",\n  \"direction\": \"看多\",\n  \"confidence\": 78,\n  \"target_price\": 1850.0,\n  \"stop_loss_price\": 1680.0,\n  \"risk_items\": [\n    {\"name\": \"估值偏高\", \"level\": \"medium\", \"description\": \"当前 PE 处于历史 75 分位\"},\n    {\"name\": \"外资流出\", \"level\": \"low\",    \"description\": \"近 5 日北向资金小幅净流出\"}\n  ],\n  \"key_metrics\": [\n    {\"name\": \"PE\",   \"value\": \"32.5x\",  \"status\": \"neutral\"},\n    {\"name\": \"ROE\",  \"value\": \"31.2%\",  \"status\": \"good\"},\n    {\"name\": \"毛利率\", \"value\": \"91.5%\", \"status\": \"good\"}\n  ],\n  \"final_trade_decision\": \"综合技术面突破与基本面支撑，建议逢低分批建仓...\"\n}\n```\n\n## 🔄 任务执行流程\n\n深度分析通常耗时 **1 至 5 分钟**：\n\n1. **识别标的**：从对话中**仅**提取股票名称或代码（及可选日期/视角），不发送对话原文\n2. **提交任务**：调用 `POST /v1/analyze`，仅传递 `symbol`、`trade_date`、`horizons` 等结构化参数\n3. **告知用户**：反馈任务已受理，预计耗时\n4. **轮询进度**：每 30 秒查询一次状态\n5. **汇总结论**：任务完成后提取并展示决策、方向、目标价、风险点\n\n## 📌 支持标的范围\n\n- **A 股**：中文名称（如 \"比亚迪\"、\"宁德时代\"）或代码（`002594.SZ`、`601012.SH`）\n- **美股**：`AAPL`、`TSLA`、`NVDA` 等标准 Ticker\n\n## 💡 注意事项\n\n- **轮询频率**：每次轮询间隔不低于 15 秒\n- **数据健壮性**：若部分数据源缺失，系统将基于宏观与行业逻辑进行外溢分析\n- **短线模式**：输入\"分析 XX 短线\"时，系统自动切换为 14 天技术面分析，跳过财报数据，速度更快\n\nFile v0.4.3:_meta.json\n\n{\n  \"ownerId\": \"kn7fp71x5ttbnyv3dk5w2dvnen82vkvn\",\n  \"slug\": \"tradingagents-analysis\",\n  \"version\": \"0.4.3\",\n  \"publishedAt\": 1773548224706\n}\n\nArchive v0.4.2: 2 files, 3375 bytes\n\nFiles: SKILL.md (5615b), _meta.json (141b)\n\nFile v0.4.2:SKILL.md\n\n---\nname: tradingagents-analysis\ndescription: 专业 A 股多智能体投研工具。15 名 AI 分析师五阶段协作，深度分析技术面、基本面、市场情绪与资金流向，提供结构化交易建议。Professional multi-agent investment research for A-Share & US stocks — market, fundamentals, sentiment, smart money.\nhomepage: https://app.510168.xyz\nrepository: https://github.com/KylinMountain/TradingAgents-AShare\ntags:\n  - A股\n  - 股票分析\n  - 量化投研\n  - 多智能体\n  - TradingAgent\n  - A-share\n  - stock-analysis\n  - China\n  - Multi-Agent\nenv:\n  TRADINGAGENTS_API_URL:\n    description: \"后端 API 地址 (TradingAgents API base URL)\"\n    default: \"https://api.510168.xyz\"\n  TRADINGAGENTS_TOKEN:\n    description: \"API 访问令牌，以 ta-sk- 开头 (Bearer token starts with ta-sk-)\"\n    required: true\nprimary_credential: TRADINGAGENTS_TOKEN\nmetadata: {\"clawdbot\":{\"emoji\":\"📈\"}}\n---\n\n# TradingAgents 多智能体 A 股投研分析\n\n使用 TradingAgents API，让 **15 名专业 AI 分析师**对 A 股进行五阶段深度协作研判，输出结构化投资建议。\n\n## 🤖 系统架构：五阶段 15 智能体\n\n| 阶段 | 智能体 | 职责 |\n|------|--------|------|\n| 1. 分析团队 | 市场/新闻/情绪/基本面/宏观/聪明钱 | 多维度原始数据解读 |\n| 2. 博弈裁判 | 博弈论管理者 | 主力与散户预期差分析 |\n| 3. 多空辩论 | 多头/空头研究员 + 裁判 | 对立观点激烈博弈 |\n| 4. 执行决策 | 交易员 | 综合研判生成操作建议 |\n| 5. 风险管控 | 激进/中性/保守分析师 + 组合经理 | 多维度风控审核 |\n\n---\n\n# TradingAgents Multi-Agent Investment Research\n\nUse the TradingAgents API to let **15 specialized AI analysts** conduct deep, five-stage collaborative research on A-Share and US stocks, delivering structured trading recommendations.\n\n## 🤖 System Architecture: 5 Stages · 15 Agents\n\n| Stage | Agents | Role |\n|-------|--------|------|\n| 1. Analyst Team | Market / News / Sentiment / Fundamentals / Macro / Smart Money | Multi-dimensional raw data analysis |\n| 2. Game Theory | Game Theory Manager | Main-force vs. retail expectation gap |\n| 3. Bull/Bear Debate | Bull & Bear Researchers + Judge | Adversarial viewpoint debate |\n| 4. Trade Execution | Trader | Synthesize research into actionable decision |\n| 5. Risk Control | Aggressive / Neutral / Conservative + Portfolio Manager | Multi-layer risk review |\n\n## 🔒 隐私与安全\n\n- **数据传输**：本技能仅向后端发送股票代码和分析参数，不读取本地文件或隐私数据。\n- **自托管**：如需最大隐私保障，可参考 [GitHub 文档](https://github.com/KylinMountain/TradingAgents-AShare) 自行部署后端。\n\n## ⚙️ 快速配置\n\n1. 登录 [https://app.510168.xyz](https://app.510168.xyz)\n2. 进入 **Settings → API Tokens** 创建令牌\n3. 配置环境变量：\n```bash\nexport TRADINGAGENTS_TOKEN=\"ta-sk-your_key_here\"\n# 可选，自托管时使用：\n# export TRADINGAGENTS_API_URL=\"http://your-server:8000\"\n```\n\n## 🚀 常用操作\n\n所有请求使用 `$TRADINGAGENTS_TOKEN` 作为 Bearer 令牌。\n\n**1. 提交分析任务**（支持中文名称、6 位代码或标准代码）\n```bash\n# 中文名称\ncurl -X POST \"${TRADINGAGENTS_API_URL:-https://api.510168.xyz}/v1/analyze\" \\\n  -H \"Authorization: Bearer $TRADINGAGENTS_TOKEN\" \\\n  -H \"Content-Type: application/json\" \\\n  -d '{\"symbol\": \"贵州茅台\"}'\n\n# 标准代码\ncurl -X POST \"${TRADINGAGENTS_API_URL:-https://api.510168.xyz}/v1/analyze\" \\\n  -H \"Authorization: Bearer $TRADINGAGENTS_TOKEN\" \\\n  -H \"Content-Type: application/json\" \\\n  -d '{\"symbol\": \"600519.SH\"}'\n```\n\n**2. 查询任务状态**\n```bash\ncurl \"${TRADINGAGENTS_API_URL:-https://api.510168.xyz}/v1/jobs/{job_id}\" \\\n  -H \"Authorization: Bearer $TRADINGAGENTS_TOKEN\"\n```\n\n**3. 获取完整分析结果**（任务完成后）\n```bash\ncurl \"${TRADINGAGENTS_API_URL:-https://api.510168.xyz}/v1/jobs/{job_id}/result\" \\\n  -H \"Authorization: Bearer $TRADINGAGENTS_TOKEN\"\n```\n\n## 📊 示例输出\n\n```json\n{\n  \"decision\": \"BUY\",\n  \"direction\": \"看多\",\n  \"confidence\": 78,\n  \"target_price\": 1850.0,\n  \"stop_loss_price\": 1680.0,\n  \"risk_items\": [\n    {\"name\": \"估值偏高\", \"level\": \"medium\", \"description\": \"当前 PE 处于历史 75 分位\"},\n    {\"name\": \"外资流出\", \"level\": \"low\",    \"description\": \"近 5 日北向资金小幅净流出\"}\n  ],\n  \"key_metrics\": [\n    {\"name\": \"PE\",   \"value\": \"32.5x\",  \"status\": \"neutral\"},\n    {\"name\": \"ROE\",  \"value\": \"31.2%\",  \"status\": \"good\"},\n    {\"name\": \"毛利率\", \"value\": \"91.5%\", \"status\": \"good\"}\n  ],\n  \"final_trade_decision\": \"综合技术面突破与基本面支撑，建议逢低分批建仓...\"\n}\n```\n\n## 🔄 任务执行流程\n\n深度分析通常耗时 **1 至 5 分钟**：\n\n1. **识别标的**：从对话中提取股票名称或代码\n2. **提交任务**：调用 `POST /v1/analyze`\n3. **告知用户**：反馈任务已受理，预计耗时\n4. **轮询进度**：每 30 秒查询一次状态\n5. **汇总结论**：任务完成后提取并展示决策、方向、目标价、风险点\n\n## 📌 支持标的范围\n\n- **A 股**：中文名称（如 \"比亚迪\"、\"宁德时代\"）或代码（`002594.SZ`、`601012.SH`）\n- **美股**：`AAPL`、`TSLA`、`NVDA` 等标准 Ticker\n\n## 💡 注意事项\n\n- **轮询频率**：每次轮询间隔不低于 15 秒\n- **数据健壮性**：若部分数据源缺失，系统将基于宏观与行业逻辑进行外溢分析\n- **短线模式**：输入\"分析 XX 短线\"时，系统自动切换为 14 天技术面分析，跳过财报数据，速度更快\n\nFile v0.4.2:_meta.json\n\n{\n  \"ownerId\": \"kn7fp71x5ttbnyv3dk5w2dvnen82vkvn\",\n  \"slug\": \"tradingagents-analysis\",\n  \"version\": \"0.4.2\",\n  \"publishedAt\": 1773547410309\n}\n\nArchive v0.4.1: 2 files, 2124 bytes\n\nFiles: SKILL.md (3352b), _meta.json (141b)\n\nFile v0.4.1:SKILL.md\n\n---\nname: tradingagents-analysis\ndescription: Professional multi-agent investment research tool for A-Share. Analyzes market, technicals, fundamentals, sentiment, and smart money using a 12-agent debate system.\nhomepage: https://app.510168.xyz\nrepository: https://github.com/KylinMountain/TradingAgents-AShare\nenv:\n  TRADINGAGENTS_API_URL:\n    description: \"TradingAgents API base URL\"\n    default: \"https://api.510168.xyz\"\n  TRADINGAGENTS_TOKEN:\n    description: \"Bearer token — generate at Settings → API Tokens\"\n    required: true\nprimary_credential: TRADINGAGENTS_TOKEN\nmetadata: {\"clawdbot\":{\"emoji\":\"📈\"}}\n---\n\n# tradingagents-analysis\n\nUse the TradingAgents API to perform deep multi-agent stock analysis and get structured trading recommendations for A-Share stocks.\n\n## 🔒 Privacy & Security\n\n- **Data Transmission**: This skill sends the **target symbol** (or name) to the configured backend. It does NOT access your local files or sensitive personal data.\n- **Backend Ownership**: The default API (`https://api.510168.xyz`) is the official project endpoint. \n- **Self-Hosting**: You can fully control your data by hosting the backend yourself. See our [Docker Deployment Guide](https://github.com/KylinMountain/TradingAgents-AShare#4-docker-一键部署-推荐) for more info.\n\n## Setup\n\n1. Login at https://app.510168.xyz\n2. Go to **Settings** → **API Tokens**\n3. Configure your environment:\n```bash\nexport TRADINGAGENTS_TOKEN=\"ta-sk-your_key_here\"\n```\n\n## API Basics\n\nThe primary endpoint is `POST /v1/analyze`. It automatically resolves stock names to codes using natural language processing.\n\n## Common Operations\n\n**Submit Analysis Job:**\nSubmit a stock by its **Natural Language Name** or **Standard Code**.\n```bash\n# Example 1: Using name (e.g. \"帮我分析一下贵州茅台\")\ncurl -X POST \"${TRADINGAGENTS_API_URL:-https://api.510168.xyz}/v1/analyze\" \\\n  -H \"Authorization: Bearer $TRADINGAGENTS_TOKEN\" \\\n  -H \"Content-Type: application/json\" \\\n  -d '{\"symbol\": \"帮我分析一下贵州茅台\"}'\n\n# Example 2: Using code (e.g. \"Analyze 300274.SZ\")\ncurl -X POST \"${TRADINGAGENTS_API_URL:-https://api.510168.xyz}/v1/analyze\" \\\n  -H \"Authorization: Bearer $TRADINGAGENTS_TOKEN\" \\\n  -H \"Content-Type: application/json\" \\\n  -d '{\"symbol\": \"Please analyze 300274.SZ\"}'\n```\n\n**Check Job Status / Retrieve Result:**\n- Status: `GET /v1/jobs/{job_id}`\n- Result: `GET /v1/jobs/{job_id}/result`\n\n## Job Workflow\n\nAnalysis is a compute-heavy process involving a 12-agent debate and takes **1 to 5 minutes**. \n\n1. **Extract**: Identify the stock from user query (e.g. \"帮我看看宁德时代\" -> \"宁德时代\").\n2. **Submit**: Call `POST /v1/analyze` with the target name/code.\n3. **Wait**: Inform the user: \"Starting multi-agent research. This typically takes 2-3 minutes. I'll monitor the agents for you.\"\n4. **Poll**: Check `/v1/jobs/{job_id}` every 30s until status is `completed`.\n5. **Summary**: Retrieve results and present the **Decision** (BUY/SELL/HOLD), **Market Direction**, and **Target Price**.\n\n## Supported Inputs\n\n- **Chinese Stock Names**: \"阳光电源\", \"比亚迪\", \"中际旭创\".\n- **Standard Codes**: `002594.SZ`, `601012.SH`.\n\n## Notes\n- **Polling Rate**: Do not poll faster than every 15 seconds.\n- **Robustness**: If certain data is missing, agents will provide logical inferences based on macro trends.\n\nFile v0.4.1:_meta.json\n\n{\n  \"ownerId\": \"kn7fp71x5ttbnyv3dk5w2dvnen82vkvn\",\n  \"slug\": \"tradingagents-analysis\",\n  \"version\": \"0.4.1\",\n  \"publishedAt\": 1773453324303\n}\n\nArchive v0.4.0: 2 files, 1611 bytes\n\nFiles: SKILL.md (2050b), _meta.json (141b)\n\nFile v0.4.0:SKILL.md\n\n---\nname: tradingagents-analysis\ndescription: Use when the user asks to analyze a stock, research market trends, or has any investment-related questions for TradingAgents. Supports natural language queries.\nenv:\n  TRADINGAGENTS_API_URL: \"TradingAgents API base URL (default: https://api.510168.xyz)\"\n  TRADINGAGENTS_TOKEN: \"Bearer token — login at https://app.510168.xyz → Settings → create an API Token\"\n---\n\n# TradingAgents Analysis Skill (Natural Language)\n\nAsk questions like \"How is CATL doing?\", \"Analyze 600519.SH\", or \"Is it a good time to buy semiconductors?\".\n\n## ⚠️ Performance Expectation\n- **Duration**: Deep analysis takes **1 to 5 minutes**.\n- **User Feedback**: Always inform the user that a multi-agent investigation has started.\n\n## API Reference\n\n### 1. Intent Detection & Quick Chat (POST /v1/chat/completions)\nSend the user's message directly to the TradingAgents backend. The backend will automatically detect the symbol and start an analysis job if needed.\n\n**Request:**\n```json\n{\n  \"messages\": [\n    {\"role\": \"user\", \"content\": \"帮我看看阳光电源目前的表现，适合买入吗？\"}\n  ],\n  \"stream\": false\n}\n```\n\n**Response (Intent Detected):**\nIf the backend detects an analysis intent, it returns a message like `[Analysis Started: 300274.SZ @ 2026-03-13] job_id: <id>`.\n\n### 2. Job Lifecycle (for Analysis Jobs)\n- **Status**: `GET /v1/jobs/{job_id}`\n- **Result**: `GET /v1/jobs/{job_id}/result`\n\n## AI Implementation Strategy\n1. **Chat First**: Instead of trying to extract the symbol yourself, send the user's full query to `/v1/chat/completions`.\n2. **Handle Job ID**: Look for a `job_id` in the chat response. If found, start the polling loop.\n3. **Wait & Poll**: Use a 30s interval to poll `/v1/jobs/{id}` until status is `completed`.\n4. **Final Summary**: Retrieve the full report from `/v1/jobs/{id}/result` and provide a high-level expert summary.\n\n## Common Symbols\n- Supports Chinese names (e.g., 贵州茅台)\n- Supports 6-digit codes (e.g., 000001)\n- Prefers suffixes for accuracy (.SH / .SZ)\n\nFile v0.4.0:_meta.json\n\n{\n  \"ownerId\": \"kn7fp71x5ttbnyv3dk5w2dvnen82vkvn\",\n  \"slug\": \"tradingagents-analysis\",\n  \"version\": \"0.4.0\",\n  \"publishedAt\": 1773407097501\n}","readmeExcerpt":"Skill: A股多智能体投研-15 AI 分析师 Owner: kylinmountain Summary: A股多智能体 AI 投研分析工具 — 15 名 AI 分析师协作完成技术分析、基本面分析、 市场情绪研判、资金流向追踪（北向资金/主力资金）、宏观经济分析及博弈论推演， 输出结构化买卖建议与风险评估。支持沪深 A 股股票代码和中文名称。 Multi-agent AI stock analysis for Chin... Tags: A-Share:0.5.0, Agent:0.5.0, a-share:0.4.0, finance:0.5.0, investment:0.4.0, latest:0.6.2, multi-agent:0.4.0, stock:0.5.0, stocks:0.4.0 Version history: v0.6.2 | 2026-03-29T01:48:41.096Z | user Vers","codeSnippets":[],"executableExamples":[{"language":"bash","snippet":"export TRADINGAGENTS_TOKEN=\"ta-sk-your_key_here\""},{"language":"bash","snippet":"# 1. 部署后端，参考 https://github.com/KylinMountain/TradingAgents-AShare\n# 2. 将 API 地址指向自建服务\nexport TRADINGAGENTS_API_URL=\"http://your-server:8000\"\nexport TRADINGAGENTS_TOKEN=\"ta-sk-your_key_here\""},{"language":"bash","snippet":"# 脚本路径（相对于技能目录）\nbash scripts/analyze.sh <symbol[,symbol2,...]> [trade_date] [horizons]\n\n# 单个分析\nbash scripts/analyze.sh 贵州茅台\nbash scripts/analyze.sh 600519.SH 2026-03-22\nbash scripts/analyze.sh 600519.SH 2026-03-22 medium\n\n# 批量分析（逗号分隔，并行提交，统一等待）\nbash scripts/analyze.sh 贵州茅台,比亚迪,宁德时代\nbash scripts/analyze.sh 600519.SH,002594.SZ,300750.SZ 2026-03-22"},{"language":"bash","snippet":"curl -X POST \"${TRADINGAGENTS_API_URL:-https://api.510168.xyz}/v1/analyze\" \\\n  -H \"Authorization: Bearer $TRADINGAGENTS_TOKEN\" \\\n  -H \"Content-Type: application/json\" \\\n  -d '{\"symbol\": \"贵州茅台\"}'"},{"language":"bash","snippet":"curl -X POST \"${TRADINGAGENTS_API_URL:-https://api.510168.xyz}/v1/analyze\" \\\n  -H \"Authorization: Bearer $TRADINGAGENTS_TOKEN\" \\\n  -H \"Content-Type: application/json\" \\\n  -d '{\"symbol\": \"贵州茅台\"}'"},{"language":"bash","snippet":"curl \"${TRADINGAGENTS_API_URL:-https://api.510168.xyz}/v1/jobs/{job_id}\" \\\n  -H \"Authorization: Bearer $TRADINGAGENTS_TOKEN\""}],"parameters":null,"dependencies":[],"permissions":[],"extractedFiles":[{"path":"SKILL.md","content":"---\nname: tradingagents-analysis\nversion: 0.6.1\ndescription: >-\n  A股多智能体 AI 投研分析工具 — 15 名 AI 分析师协作完成技术分析、基本面分析、\n  市场情绪研判、资金流向追踪（北向资金/主力资金）、宏观经济分析及博弈论推演，\n  输出结构化买卖建议与风险评估。支持沪深 A 股股票代码和中文名称。\n  Multi-agent AI stock analysis for China A-shares.\n  15 specialized analysts collaborate across technical analysis, fundamental analysis,\n  sentiment analysis, smart money flow tracking, macro economics, and game theory\n  to deliver structured buy/sell/hold recommendations with risk assessment.\nhomepage: https://app.510168.xyz\nrepository: https://github.com/KylinMountain/TradingAgents-AShare\ntags:\n  - stock-analysis\n  - A-share\n  - A股\n  - 股票分析\n  - 股票\n  - 炒股\n  - 选股\n  - 荐股\n  - trading\n  - investment\n  - 投资\n  - 投研\n  - 量化投研\n  - 研报\n  - 盘后分析\n  - 复盘\n  - multi-agent\n  - 多智能体\n  - AI分析\n  - AI炒股\n  - technical-analysis\n  - 技术分析\n  - K线\n  - fundamental-analysis\n  - 基本面分析\n  - sentiment-analysis\n  - 市场情绪\n  - smart-money\n  - 资金流向\n  - 北向资金\n  - 主力资金\n  - 龙虎榜\n  - finance\n  - 金融\n  - China\n  - 中国股市\n  - 沪深\n  - 上证\n  - 深证\n  - quant\n  - risk-assessment\n  - 风险评估\n  - 买卖建议\n  - claude-code\n  - openclaw\nmetadata:\n  openclaw:\n    requires:\n      env:\n        - TRADINGAGENTS_TOKEN\n        - TRADINGAGENTS_API_URL\n      bins:\n        - curl\n        - python3\n        - bash\n    primaryEnv: TRADINGAGENTS_TOKEN\n    emoji: \"📈\"\n    homepage: https://app.510168.xyz\n---\n\n# TradingAgents 多智能体 A 股投研分析\n\n使用 TradingAgents API，让 **15 名专业 AI 分析师**对 A 股进行五阶段深度协作研判，输出结构化投资建议。\n\n## 🎯 快速上手\n\n**直接对我说：**\n- \"帮我分析一下贵州茅台\"\n- \"宁德时代值得买入吗\"\n- \"分析一下 600519 的技术面\"\n- \"比亚迪最近资金流向怎么样\"\n\n**我会调用 15 个 AI 分析师，从市场、技术、基本面、情绪、资金五个维度深度分析，给你专业的投资建议。**\n\n---\n\n## 🤖 系统架构：五阶段 15 智能体\n\n| 阶段 | 智能体 | 职责 |\n|------|--------|------|\n| 1. 分析团队 | 市场/新闻/情绪/基本面/宏观/聪明钱 | 多维度原始数据解读 |\n| 2. 博弈裁判 | 博弈论管理者 | 主力与散户预期差分析 |\n| 3. 多空辩论 | 多头/空头研究员 + 裁判 | 对立观点激烈博弈 |\n| 4. 执行决策 | 交易员 | 综合研判生成操作建议 |\n| 5. 风险管控 | 激进/中性/保守分析师 + 组合经理 | 多维度风控审核 |\n\n---\n\n# TradingAgents Multi-Agent Investment Research\n\nUse the TradingAgents API to let **15 specialized AI analysts** conduct deep, five-stage collaborative research on A-Share stocks, delivering structured trading recommendations.\n\n## 🤖 System Architecture: 5 Stages · 15 Agents\n\n| Stage | Agents | Role |\n|-------|--------|------|\n| 1. Analyst Team | Market / News / Sentiment / Fundamentals / Macro / Smart Money | Multi-dimensional raw data analysis |\n| 2. Game Theory | Game Theory Manager | Main-force vs. retail expectation gap |\n| 3. Bull/Bear Debate | Bull & Bear Researchers + Judge | Adversarial viewpoint debate |\n| 4. Trade Execution | Trader | Synthesize research into actionable decision |\n| 5. Risk Control | Aggressive / Neutral / Conservative + Portfolio Manager | Multi-layer risk review |\n\n## 📋 适用场景\n\n✅ **适合使用：**\n- 个股深度分析（技术面 + 基本面）\n- 投资决策参考\n- 盘后复盘分析\n- 持仓标的风险评估\n- 资金流向与市场情绪研判\n\n❌ **不适合：**\n- 盘中实时盯盘（分析需要 1-5 分钟）\n- 超短线交易（分钟级决策）\n- 加密货币、美股等非 A 股市场\n\n## 🔒 隐私与安全\n\n- **发送范围**：本技能**仅**从对话中提取股票名称/代码、分析日期、分析视角等参数，将其作为 `symbol`/`trade_date`/`horizons` 字段发送至后端 API。**不发送对话原文、不读取本地文件、不上传任何其他隐私数据。**\n- **令牌安全**：`TRADINGAGENTS_TOKEN`（格式 `ta-s"},{"path":"_meta.json","content":"{\n  \"ownerId\": \"kn7fp71x5ttbnyv3dk5w2dvnen82vkvn\",\n  \"slug\": \"tradingagents-analysis\",\n  \"version\": \"0.6.2\",\n  \"publishedAt\": 1774748921096\n}"},{"path":"skill-card.md","content":"## Description:\n\nA股多智能体 AI 投研分析工具 uses 15 AI analysts to analyze China A-share stocks across technical, fundamental, sentiment, smart-money, macroeconomic, and game-theory perspectives, producing structured buy, sell, or hold recommendations with risk assessment.\n\nThis skill is ready for commercial/non-commercial use.\n\n## Publisher:\n\n[kylinmountain](https://clawhub.ai/user/kylinmountain)\n\n### License/Terms of Use:\n\nMIT-0\n\n## Use Case:\n\nExternal users and investment researchers use this skill to request deep analysis of Shanghai and Shenzhen A-share stocks by symbol or Chinese company name. The skill submits stock-analysis jobs to the TradingAgents API and returns structured decisions, confidence, target and stop-loss prices, key metrics, and risk items.\n\n### Deployment Geography for Use:\n\nGlobal\n\n## Known Risks and Mitigations:\n\nRisk: The skill can send stock-analysis requests and a bearer token to a configurable backend API endpoint.\n\nMitigation: Use the default HTTPS endpoint or an HTTPS self-hosted endpoint, avoid plain HTTP except loopback-only local testing with disposable credentials, and rotate the TradingAgents token if exposed.\n\nRisk: The skill produces investment-analysis recommendations that may be incorrect, stale, or unsuitable for a user's financial situation.\n\nMitigation: Treat outputs as decision support, require user confirmation before submitting jobs, and review recommendations with independent financial judgment before acting.\n\nRisk: Users may include personal account details, actual positions, or other sensitive financial information in prompts even though the skill only needs stock-analysis parameters.\n\nMitigation: Ask users to provide only stock symbols, trade dates, and analysis horizons; do not include account data, holdings, or other sensitive personal information.\n\n## Reference(s):\n\n- [ClawHub skill listing](https://clawhub.ai/kylinmountain/skills/tradingagents-analysis)\n- [TradingAgents application homepage](https://app.510168.xyz)\n- [TradingAgents-AShare self-hosting documentation](https://github.com/KylinMountain/TradingAgents-AShare)\n\n## Skill Output:\n\n**Output Type(s):** [text, markdown, shell commands, configuration, guidance]\n\n**Output Format:** [Markdown guidance with shell commands and JSON analysis results]\n\n**Output Parameters:** [1D]\n\n**Other Properties Related to Output:** [Analysis jobs usually take 1 to 5 minutes; batch mode submits multiple symbols and returns a JSON result summary for completed jobs.]\n\n## Skill Version(s):\n\n0.6.2 (source: server release evidence)\n\n## Ethical Considerations:\n\nUsers should evaluate whether this skill is appropriate for their environment, review any generated or modified files before relying on them, and apply their organization's safety, security, and compliance requirements before deployment."}],"languages":[],"docsSourceLabel":"CLAWHUB","editorialOverview":"A股多智能体 AI 投研分析工具 — 15 名 AI 分析师协作完成技术分析、基本面分析、 市场情绪研判、资金流向追踪（北向资金/主力资金）、宏观经济分析及博弈论推演， 输出结构化买卖建议与风险评估。支持沪深 A 股股票代码和中文名称。 Multi-agent AI stock analysis for Chin... Skill: A股多智能体投研-15 AI 分析师 Owner: kylinmountain Summary: A股多智能体 AI 投研分析工具 — 15 名 AI 分析师协作完成技术分析、基本面分析、 市场情绪研判、资金流向追踪（北向资金/主力资金）、宏观经济分析及博弈论推演， 输出结构化买卖建议与风险评估。支持沪深 A 股股票代码和中文名称。 Multi-agent AI stock analysis for Chin... Tags: A-Share:0.5.0, Agent:0.5.0, a-share:0.4.0, finance:0.5.0, investment:0.4.0, latest:0.6.2, multi-agent:0.4.0, stock:0.5.0, stocks:0.4.0 Version history: v0.6.2 | 2026-03-29T01:48:41.096Z | user Vers","editorialQuality":{"score":100,"threshold":65,"status":"ready","wordCount":1370,"uniquenessScore":52,"reasons":[]}},"media":{"evidence":{"source":"no-media","verified":false,"confidence":"low","updatedAt":"2026-10-09T05:21:20.882Z","emptyReason":"No screenshots, media assets, or demo links are available."},"primaryImageUrl":null,"mediaAssetCount":0,"assets":[],"demoUrl":null},"ownerResources":{"evidence":{"source":"unclaimed","verified":false,"confidence":"low","updatedAt":"2026-10-09T05:21:20.882Z","emptyReason":"This page has not been claimed by the agent owner."},"hasCustomPage":false,"customPageUpdatedAt":null,"customLinks":[],"structuredLinks":{"docsUrl":null,"demoUrl":null,"supportUrl":null,"pricingUrl":null,"statusUrl":null},"customPage":null},"relatedAgents":{"evidence":{"source":"protocol-neighbors","verified":false,"confidence":"medium","updatedAt":"2026-10-09T12:24:33.971Z","emptyReason":null},"items":[{"id":"b917f68a-ebff-438e-84f8-3f4b2494c0bc","entityType":"agent","canonicalPath":"/agent/activepieces-activepieces","slug":"activepieces-activepieces","name":"activepieces","description":"AI Agents & MCPs & AI Workflow Automation • (~400 MCP servers for AI agents) • AI Automation / AI Agent with MCPs • AI Workflows & AI Agents • MCPs for AI Agents","url":"https://github.com/activepieces/activepieces","homepage":"https://www.activepieces.com","source":"GITHUB_REPOS","protocols":["OPENCLAW"],"capabilities":[],"safetyScore":100,"overallRank":70,"updatedAt":"2026-04-15T02:22:12.426Z","createdAt":"2026-02-25T03:38:12.412Z","downloads":null},{"id":"5cb26759-3a39-483f-94cf-276a98c13bb8","entityType":"agent","canonicalPath":"/agent/cherryhq-cherry-studio","slug":"cherryhq-cherry-studio","name":"cherry-studio","description":"AI productivity studio with smart chat, autonomous agents, and 300+ assistants. Unified access to frontier LLMs","url":"https://github.com/CherryHQ/cherry-studio","homepage":"https://cherry-ai.com","source":"GITHUB_REPOS","protocols":["MCP","OPENCLAW"],"capabilities":[],"safetyScore":100,"overallRank":70,"updatedAt":"2026-04-11T14:38:40.986Z","createdAt":"2026-02-25T03:38:19.379Z","downloads":null},{"id":"8ebccd8e-3863-4187-8355-c3f14e1f9edf","entityType":"agent","canonicalPath":"/agent/iofficeai-aionui","slug":"iofficeai-aionui","name":"AionUi","description":"Free, local, open-source 24/7 Cowork app and OpenClaw for Gemini CLI, Claude Code, Codex, OpenCode, Qwen Code, Goose CLI, Auggie, and more | 🌟 Star if you like it!","url":"https://github.com/iOfficeAI/AionUi","homepage":"https://www.aionui.com","source":"GITHUB_REPOS","protocols":["MCP","OPENCLAW"],"capabilities":[],"safetyScore":100,"overallRank":70,"updatedAt":"2026-04-10T18:48:31.762Z","createdAt":"2026-02-25T03:38:16.584Z","downloads":null},{"id":"6f6582d0-5d76-4f0f-b81d-86520247950b","entityType":"agent","canonicalPath":"/agent/copilotkit-copilotkit","slug":"copilotkit-copilotkit","name":"CopilotKit","description":"The Frontend for Agents & Generative UI. React + Angular","url":"https://github.com/CopilotKit/CopilotKit","homepage":"https://docs.copilotkit.ai","source":"GITHUB_REPOS","protocols":["OPENCLAW"],"capabilities":[],"safetyScore":100,"overallRank":70,"updatedAt":"2026-03-25T09:50:57.846Z","createdAt":"2026-02-25T03:39:14.617Z","downloads":null}],"links":{"hub":"/agent","source":"/agent/source/clawhub","protocols":[{"label":"OpenClaw","href":"/agent/protocol/openclew"}]}}}