{"id":"43a6f384-1f10-4bf5-a024-a021beba592e","entityType":"agent","slug":"clawhub-kkkkhazix-aihot","name":"Aihot Skill Lite","canonicalUrl":"https://www.xpersona.co/agent/clawhub-kkkkhazix-aihot","canonicalPath":"/agent/clawhub-kkkkhazix-aihot","generatedAt":"2026-10-10T00:20:05.860Z","source":"CLAWHUB","claimStatus":"UNCLAIMED","verificationTier":"NONE","summary":{"evidence":{"source":"editorial-content","verified":true,"confidence":"high","updatedAt":"2026-10-09T15:42:24.725Z","emptyReason":null},"description":"AI HOT (aihot.virxact.com) 中文 AI 资讯查询 Skill。当用户想知道\"今天 AI 圈有什么\"、\"AI 日报\"、\"AI HOT\"、\"AI 资讯\"、\"AI 热点\"、\"最近 AI\"、\"OpenAI/Anthropic/Google 最近发布了什么\"、\"AI hot today\"、\"AI... Skill: Aihot Skill Lite Owner: kkkkhazix Summary: AI HOT (aihot.virxact.com) 中文 AI 资讯查询 Skill。当用户想知道\"今天 AI 圈有什么\"、\"AI 日报\"、\"AI HOT\"、\"AI 资讯\"、\"AI 热点\"、\"最近 AI\"、\"OpenAI/Anthropic/Google 最近发布了什么\"、\"AI hot today\"、\"AI... Tags: latest:0.1.1 Version history: v0.1.1 | 2026-05-07T23:49:37.450Z | auto aihot 0.1.1 - SKILL.md 文档重写，进一步精简内容，使其适配 ClawHub 8192 token 限制。 - 路由优先级说明更直接，默认走精选条目（mode=selected），日报（daily）和全量（mode=all）需明确触发。 - 大幅","descriptionLabel":"Technical summary","evidenceSummary":"Capability contract not published. No trust telemetry is available yet. 2.4K downloads reported by the source. Last updated 10/9/2026.","installCommand":"clawhub skill install s17d1k4dvwcb90jz5r5xvvpjtx83j0ds:aihot","sourceUrl":"https://clawhub.ai/kkkkhazix/aihot","homepage":"https://clawhub.ai/kkkkhazix/skills/aihot","primaryLinks":[{"label":"View on ClawHub","url":"https://clawhub.ai/kkkkhazix/aihot","kind":"source"},{"label":"Homepage","url":"https://clawhub.ai/kkkkhazix/skills/aihot","kind":"homepage"}],"safetyScore":84,"overallRank":62,"popularityScore":68,"trustScore":null,"claimedByName":null,"isOwner":false,"seoDescription":"AI HOT (aihot.virxact.com) 中文 AI 资讯查询 Skill。当用户想知道\"今天 AI 圈有什么\"、\"AI 日报\"、\"AI HOT\"、\"AI 资讯\"、\"AI 热点\"、\"最近 AI\"、\"OpenAI/Anthropic/Google 最近发布了什么\"、\"AI hot today\"、\"AI... "},"coverage":{"evidence":{"source":"public-profile","verified":false,"confidence":"medium","updatedAt":"2026-10-09T15:42:24.725Z","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":"2026-10-09T15:42:24.725Z","emptyReason":null},"stars":null,"forks":null,"downloads":2373,"packageName":null,"latestVersion":"0.1.1","tractionLabel":"2.4K downloads"},"release":{"evidence":{"source":"CLAWHUB","verified":false,"confidence":"medium","updatedAt":"2026-10-09T15:42:24.725Z","emptyReason":null},"lastUpdatedAt":"2026-10-09T15:42:24.725Z","lastCrawledAt":"2026-10-09T15:42:24.725Z","lastIndexedAt":null,"nextCrawlAt":"2026-10-10T15:42:24.725Z","lastVerifiedAt":null,"highlights":[{"version":"0.1.1","createdAt":"2026-05-07T23:49:37.450Z","changelog":"aihot 0.1.1 - SKILL.md 文档重写，进一步精简内容，使其适配 ClawHub 8192 token 限制。 - 路由优先级说明更直接，默认走精选条目（mode=selected），日报（daily）和全量（mode=all）需明确触发。 - 大幅收紧开发者与用户交互边界，强调用户输出不暴露任何端点/raw参数/限流等后台细节。 - 补充工作流 curl 示例、完整约束、典型错误用法，以及输出人话/时间格式要求。 - 全面标注完整版/详细文档的线上入口（GitHub）。","fileCount":3,"zipByteSize":5139},{"version":"0.1.0","createdAt":"2026-05-07T22:29:57.411Z","changelog":"aihot 0.1.0 (Initial Release) - 新增面向中文用户的 AI 行业资讯查询能力，聚合每日 AI HOT 日报及最新 AI 动态。 - 通过公开 REST API 自动获取今日/指定日期 AI 日报、精选条目、模型/产品/行业热点、最新论文等信息。 - 所有调用均无需 API Key，完全匿名免费，适配主流中文查询表达。 - 强调准确性，仅以 API 返回为准，不使用训练数据补全近期动态。 - 输出优化为中文 Markdown 简报，方便用户直接获取最新 AI 新闻与热点。","fileCount":2,"zipByteSize":3310}]},"execution":{"evidence":{"source":"CLAWHUB","verified":false,"confidence":"low","updatedAt":null,"emptyReason":"No published capability contract is available yet."},"installCommand":"clawhub skill install s17d1k4dvwcb90jz5r5xvvpjtx83j0ds:aihot","setupComplexity":"low","setupSteps":["Setup complexity is LOW. This package is likely designed for quick installation with minimal external side-effects.","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-kkkkhazix-aihot/snapshot","contractUrl":"https://www.xpersona.co/api/v1/agents/clawhub-kkkkhazix-aihot/contract","trustUrl":"https://www.xpersona.co/api/v1/agents/clawhub-kkkkhazix-aihot/trust"},"curlExamples":["curl -s \"https://www.xpersona.co/api/v1/agents/clawhub-kkkkhazix-aihot/snapshot\"","curl -s \"https://www.xpersona.co/api/v1/agents/clawhub-kkkkhazix-aihot/contract\"","curl -s \"https://www.xpersona.co/api/v1/agents/clawhub-kkkkhazix-aihot/trust\""],"jsonRequestTemplate":{"query":"summarize this repo","constraints":{"maxLatencyMs":2000,"protocolPreference":["OPENCLEW"]}},"jsonResponseTemplate":{"ok":true,"result":{"summary":"...","confidence":0.9},"meta":{"source":"CLAWHUB","generatedAt":"2026-10-10T00:20:05.860Z"}},"retryPolicy":{"maxAttempts":3,"backoffMs":[500,1500,3500],"retryableConditions":["HTTP_429","HTTP_503","NETWORK_TIMEOUT"]}},"endpoints":{"dossierUrl":"https://www.xpersona.co/api/v1/agents/clawhub-kkkkhazix-aihot/dossier","snapshotUrl":"https://www.xpersona.co/api/v1/agents/clawhub-kkkkhazix-aihot/snapshot","contractUrl":"https://www.xpersona.co/api/v1/agents/clawhub-kkkkhazix-aihot/contract","trustUrl":"https://www.xpersona.co/api/v1/agents/clawhub-kkkkhazix-aihot/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":"2026-10-09T15:42:24.725Z","emptyReason":null},"readme":"Skill: Aihot Skill Lite\n\nOwner: kkkkhazix\n\nSummary: AI HOT (aihot.virxact.com) 中文 AI 资讯查询 Skill。当用户想知道\"今天 AI 圈有什么\"、\"AI 日报\"、\"AI HOT\"、\"AI 资讯\"、\"AI 热点\"、\"最近 AI\"、\"OpenAI/Anthropic/Google 最近发布了什么\"、\"AI hot today\"、\"AI...\n\nTags: latest:0.1.1\n\nVersion history:\n\nv0.1.1 | 2026-05-07T23:49:37.450Z | auto\n\naihot 0.1.1\n\n- SKILL.md 文档重写，进一步精简内容，使其适配 ClawHub 8192 token 限制。\n- 路由优先级说明更直接，默认走精选条目（mode=selected），日报（daily）和全量（mode=all）需明确触发。\n- 大幅收紧开发者与用户交互边界，强调用户输出不暴露任何端点/raw参数/限流等后台细节。\n- 补充工作流 curl 示例、完整约束、典型错误用法，以及输出人话/时间格式要求。\n- 全面标注完整版/详细文档的线上入口（GitHub）。\n\nv0.1.0 | 2026-05-07T22:29:57.411Z | auto\n\naihot 0.1.0 (Initial Release)\n\n- 新增面向中文用户的 AI 行业资讯查询能力，聚合每日 AI HOT 日报及最新 AI 动态。\n- 通过公开 REST API 自动获取今日/指定日期 AI 日报、精选条目、模型/产品/行业热点、最新论文等信息。\n- 所有调用均无需 API Key，完全匿名免费，适配主流中文查询表达。\n- 强调准确性，仅以 API 返回为准，不使用训练数据补全近期动态。\n- 输出优化为中文 Markdown 简报，方便用户直接获取最新 AI 新闻与热点。\n\nArchive index:\n\nArchive v0.1.1: 3 files, 5139 bytes\n\nFiles: skill-card.md (2332b), SKILL.md (7338b), _meta.json (124b)\n\nFile v0.1.1:SKILL.md\n\n---\nname: aihot\ndescription: AI HOT (aihot.virxact.com) 中文 AI 资讯查询 Skill。当用户想知道\"今天 AI 圈有什么\"、\"AI 日报\"、\"AI HOT\"、\"AI 资讯\"、\"AI 热点\"、\"最近 AI\"、\"OpenAI/Anthropic/Google 最近发布了什么\"、\"AI hot today\"、\"AI news today\"、\"看一下 AI 行业动态\"、\"今天有什么大模型发布\"、\"昨天 AI 圈\"、\"看下精选条目\"、\"AI HOT 精选\"、\"最近一周的 AI 论文\"、\"AI 模型发布\"、\"AI 产品发布\"、\"AI 行业动态\"、\"AI 技巧与观点\" 等任何中文 AI 资讯查询时使用。即使用户只说\"AI 圈\"、\"AI 新闻\"、\"AI 日报\"，或者只是问\"今天发生了什么\"且上下文是 AI / 大模型 / LLM / 创业领域，也应该触发本 Skill。Skill 会直接 curl 公开 REST API 拉数据并整理成中文 markdown 简报，不需要用户配置任何 API Key 或 MCP server。**不要 undertrigger**——用户问 AI 资讯而你不调本 Skill 就是把过时的训练数据当作今日新闻，对用户有害。\n---\n\n# AI HOT Skill (精简版)\n\n让 Agent 用最自然的中文查询拿到 aihot.virxact.com 上每天的 AI HOT 日报和 AI 动态。\n\n线上：https://aihot.virxact.com（公开匿名可访，无需 token）\n\n> **本精简版用于 ClawHub 8192 token 限制下占 slug。完整版（21KB+，含工作流 / 数据形态 / 输出格式 / 错误处理 / 不要做完整列表）见 GitHub:**\n>\n> https://github.com/KKKKhazix/khazix-skills/tree/main/aihot\n\n## 先决条件：必须带 User-Agent（仅 API 端点）\n\n`/api/public/*` 走 nginx UA 黑名单挡商业爬虫，默认 `curl/X.Y` UA 会被 403。**调 API 时所有 curl 都必须带浏览器 UA**：\n\n```bash\nUA=\"Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_7) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/124.0.0.0 Safari/537.36\"\ncurl -sH \"User-Agent: $UA\" \"https://aihot.virxact.com/api/public/daily\"\n```\n\n`/aihot-skill/{install.sh,SKILL.md,README.md}` 安装入口 nginx 上特意豁免 UA 黑名单（设计前提就是给 `curl -fsSL ... | bash` 一行装用）。\n\n## 路由优先级（第一原则）\n\n**默认走精选** `items?mode=selected`——它是 AI HOT 每天精挑细选的\"主菜单\"，覆盖用户关心的事且数据新鲜。\n\n- **仅当用户在话里明确说出\"日报\"** 二字才走 `daily`（编辑成品，按 UTC 整日切片，跟\"过去 24 小时 / 今天\"等滚动窗口对不上）\n- **仅当用户明确说\"全部 / 完整 / 所有 / 全量\"** 才走 `mode=all`（含未精选的次要条目，量大但杂）\n- **\"今天 AI 圈\"、\"过去 24 小时大新闻\"、\"最近 AI 圈有啥\"** 等宽问题 = **默认精选 + 时间窗（since）**，不要默认走日报或全部\n\n## 什么时候用\n\n| 用户在说 | 应该走的接口 |\n|---|---|\n| **默认（宽问题）**：\"今天 AI 圈有什么\"、\"过去 24 小时大新闻\"、\"最近 AI 圈\" | `GET /api/public/items?mode=selected&since=<语义时间窗>` |\n| **明确说\"日报\"**：\"AI 日报\"、\"今天的日报\"、\"看下日报\" | `GET /api/public/daily` 或 `daily/{YYYY-MM-DD}` |\n| **明确说\"全部 / 完整 / 所有 / 全量\"** | `GET /api/public/items?mode=all` |\n| \"最近的模型发布\"、\"AI 论文\"、\"AI 行业动态\" | `GET /api/public/items?mode=selected&category=...&since=<7d 前>` |\n| \"OpenAI/Anthropic 最近发的\"、\"Sora 相关\"、\"RAG 论文\" | `GET /api/public/items?q=<关键词>`（server-side 关键词搜索） |\n| \"看下精选 50 条\"、\"AI HOT 精选\" | `GET /api/public/items?mode=selected&take=50` |\n| \"列一下日报有哪些\"、\"日报存档\" | `GET /api/public/dailies?take=N` |\n\n通用启发：**用户问的是\"现在的 AI 行业事实\"，不要凭训练数据脑补，永远走 API**。\n\n## 5 个 category（items 用英文 slug，daily 看到的中文 label）\n\n| `items?category=` | `daily.sections[].label` |\n|---|---|\n| `ai-models` | 模型发布/更新 |\n| `ai-products` | 产品发布/更新 |\n| `industry` | 行业动态 |\n| `paper` | 论文研究 |\n| `tip` | 技巧与观点 |\n\n## 核心约束\n\n- **`since` 限最近 7 天**：不传等同 `since=now-7d`（服务端兜底硬上限）；早于 7 天前自动截到 7 天前；未来时间 → 400。需要更深历史走日报存档 `/api/public/daily/{date}`\n- **`take` ≤ 100**，更多走 cursor 翻页\n- **`cursor` 是 opaque token**，原样回传给下一次请求；不要尝试解析、递增、跨端点复用\n- **`q` 至少 2 字符**，最长 200 字（超出截断），跟其它参数正交叠加\n- **限流 600 req/min/IP**，串行调用不要并发猛拉\n- 完整 OpenAPI 3.1 规范：`https://aihot.virxact.com/openapi.yaml`\n\n## 工作流示例\n\n```bash\nUA=\"Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_7) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/124.0.0.0 Safari/537.36\"\n\n# 默认：拉过去 24 小时精选（用户问\"过去 24 小时大新闻\"）\nsince=$(date -u -v-24H +%Y-%m-%dT%H:%M:%SZ 2>/dev/null || date -u -d '24 hours ago' +%Y-%m-%dT%H:%M:%SZ)\ncurl -sH \"User-Agent: $UA\" \"https://aihot.virxact.com/api/public/items?mode=selected&since=$since&take=50\"\n\n# 明确日报\ncurl -sH \"User-Agent: $UA\" \"https://aihot.virxact.com/api/public/daily\"\n\n# 明确全部（用户说\"全部 / 所有\"）\ncurl -sH \"User-Agent: $UA\" \"https://aihot.virxact.com/api/public/items?mode=all&since=$since&take=100\"\n\n# 关键词（OpenAI 最近发的，server-side 全池搜索）\ncurl -sH \"User-Agent: $UA\" \"https://aihot.virxact.com/api/public/items?q=OpenAI&take=30\"\n```\n\n## 给用户的输出格式\n\n> **核心原则**：直接展示给用户的最终内容必须 **markdown + 排版好 + 普通人能看懂的人话**。**所有\"端点路径 / `mode=selected` 这种 raw 参数 / 限流 / nginx 缓存 / cursor / hasNext\"等基础设施细节都不能出现**在用户输出里。\n\n### 列表式输出（items 端点时）\n\n按 category 分组 + 全局编号；每条带 title / source / 时间转人话 / summary / url：\n\n```markdown\n**AI HOT — 过去 24 小时精选**（共 N 条）\n\n## 模型发布/更新\n1. **<title>** — <source>\n   2 小时前 / 今天上午 09:48\n   <summary>\n   <url>\n\n## 产品发布/更新\n2. ...\n```\n\n### 日报式输出（daily 端点时）\n\n按 5 版块顺序展开（模型发布/更新 → 产品发布/更新 → 行业动态 → 论文研究 → 技巧与观点）。\n\n时间转人话：`2026-05-08T01:48:00.000Z` → \"今天上午 09:48\" / \"2 小时前\"，不要直接展示 ISO 字符串。\n\n## 不要做（核心几条）\n\n- **不要把\"今天 AI 圈\"、\"过去 24 小时大新闻\"等宽问题路由到 daily** — 滚动时间窗 vs UTC 整日切片对不上。默认 `mode=selected + since=<语义窗>`\n- **不要在用户没说\"全部 / 完整 / 所有 / 全量\"时默认走 `mode=all`** — 默认 `mode=selected`\n- **不要客户端 grep 公司维度** — 用 server-side `?q=<词>`，覆盖全池\n- **不要在用户输出暴露端点路径 / raw 参数 / 限流 / cursor** — 这些是开发者细节，用户看不懂\n- **不要丢每条的 sourceUrl** — 跨日 / 跨版块压缩输出也必须保留 url（标题后或单独一行），否则信息不可信\n- **不要凭训练数据脑补** — AI HOT 比训练截止日新得多，永远走 API\n\n---\n\n完整文档（工作流 / 数据形态 / 错误处理 / 完整 do/don't）见：\n**https://github.com/KKKKhazix/khazix-skills/tree/main/aihot**\n\nFile v0.1.1:_meta.json\n\n{\n  \"ownerId\": \"kn747k2gzavewdpzfb0tm6xq0d82td3f\",\n  \"slug\": \"aihot\",\n  \"version\": \"0.1.1\",\n  \"publishedAt\": 1778197777450\n}\n\nFile v0.1.1:skill-card.md\n\n## Description:\n\nAihot Skill Lite lets an agent fetch current AI HOT news from aihot.virxact.com and produce concise Chinese Markdown briefings.\n\nThis skill is ready for commercial/non-commercial use.\n\n## Publisher:\n\n[kkkkhazix](https://clawhub.ai/user/kkkkhazix)\n\n### License/Terms of Use:\n\nMIT-0\n\n## Use Case:\n\nExternal users and developers use this skill to retrieve recent AI industry news, AI HOT daily reports, category updates, and keyword-specific AI news, then present the results as readable Chinese Markdown briefings.\n\n### Deployment Geography for Use:\n\nGlobal\n\n## Known Risks and Mitigations:\n\nRisk: AI-news search terms and timing parameters may be sent to aihot.virxact.com.\n\nMitigation: Avoid using confidential or sensitive search terms, and deploy only where sending those queries to the disclosed public service is acceptable.\n\nRisk: The skill relies on live public AI news data, which may be incomplete, unavailable, or changed after retrieval.\n\nMitigation: Keep source URLs in the briefing and review important claims before using them in business-critical decisions.\n\nRisk: The skill instructs curl to use a browser-like User-Agent for public API calls.\n\nMitigation: Limit calls to the disclosed AI HOT service and ensure usage follows the service's access expectations.\n\n## Reference(s):\n\n- [ClawHub skill page](https://clawhub.ai/kkkkhazix/skills/aihot)\n- [Publisher profile](https://clawhub.ai/user/kkkkhazix)\n- [AI HOT public site](https://aihot.virxact.com)\n- [AI HOT OpenAPI specification](https://aihot.virxact.com/openapi.yaml)\n- [Full AI HOT skill documentation](https://github.com/KKKKhazix/khazix-skills/tree/main/aihot)\n\n## Skill Output:\n\n**Output Type(s):** [Text, Markdown, Shell commands, Guidance]\n\n**Output Format:** [Chinese Markdown briefing with source links and optional inline shell command examples]\n\n**Output Parameters:** [1D]\n\n**Other Properties Related to Output:** [Outputs should summarize current AI news in plain language and preserve source URLs.]\n\n## Skill Version(s):\n\n0.1.1 (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 v0.1.0: 2 files, 3310 bytes\n\nFiles: SKILL.md (5371b), _meta.json (124b)\n\nFile v0.1.0:SKILL.md\n\n---\nname: aihot\ndescription: AI HOT (aihot.virxact.com) 中文 AI 资讯查询 Skill。当用户想知道\"今天 AI 圈有什么\"、\"AI 日报\"、\"AI HOT\"、\"AI 资讯\"、\"AI 热点\"、\"最近 AI\"、\"OpenAI/Anthropic/Google 最近发布了什么\"、\"AI hot today\"、\"AI news today\"、\"看一下 AI 行业动态\"、\"今天有什么大模型发布\"、\"昨天 AI 圈\"、\"看下精选条目\"、\"AI HOT 精选\"、\"最近一周的 AI 论文\"、\"AI 模型发布\"、\"AI 产品发布\"、\"AI 行业动态\"、\"AI 技巧与观点\" 等任何中文 AI 资讯查询时使用。即使用户只说\"AI 圈\"、\"AI 新闻\"、\"AI 日报\"，或者只是问\"今天发生了什么\"且上下文是 AI / 大模型 / LLM / 创业领域，也应该触发本 Skill。Skill 会直接 curl 公开 REST API 拉数据并整理成中文 markdown 简报，不需要用户配置任何 API Key 或 MCP server。**不要 undertrigger**——用户问 AI 资讯而你不调本 Skill 就是把过时的训练数据当作今日新闻，对用户有害。\n---\n\n# AI HOT Skill (精简版)\n\n> 本版本是 ClawHub embedding 限制下的占位精简版。完整文档(详细工作流 / 输出模板 / 错误处理 / 17 条不要做)见 GitHub:\n> **https://github.com/KKKKhazix/khazix-skills/tree/main/aihot**\n\n让 Agent 用最自然的中文查询拿到 [aihot.virxact.com](https://aihot.virxact.com) 上每天的 AI HOT 日报和全部 AI 动态。匿名免费,无需 API Key。\n\n## 先决条件:必须带 User-Agent\n\n公开 API 走 nginx UA 黑名单,默认 `curl/X.Y` 会 403。所有 curl 必须带浏览器 UA:\n\n```bash\nUA=\"Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_7) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/124.0.0.0 Safari/537.36\"\ncurl -sH \"User-Agent: $UA\" \"https://aihot.virxact.com/api/public/daily\"\n```\n\n## 什么时候用\n\n| 用户在说 | 调用 |\n|---|---|\n| \"今天 AI 圈有什么\"、\"AI 日报\" | `GET /api/public/daily` (今日精编) |\n| \"5 月 6 号的 AI HOT\" | `GET /api/public/daily/2026-05-06` |\n| \"看下精选条目\" | `GET /api/public/items?mode=selected` |\n| \"最近的模型发布 / 产品 / 行业 / 论文\" | `GET /api/public/items?mode=all&category=ai-models\\|ai-products\\|industry\\|paper\\|tip` |\n| \"OpenAI 最近发的\" / \"Sora 相关\" / \"RAG 论文\" | `GET /api/public/items?q=<关键词>` (server-side 搜索) |\n| \"最近 N 天的 AI 动态\" | 加 `since=<ISO 8601 日期>`, 例如 `since=2026-05-01T00:00:00Z` |\n\n**通用启发**: 用户问\"现在的 AI 行业事实\"时永远走 API,不要凭训练数据脑补。AI HOT 比训练截止日新得多。\n\n## 端点速览\n\n| 端点 | 用途 | 主要参数 |\n|---|---|---|\n| `/api/public/daily` | 最新日报 | 无 |\n| `/api/public/daily/{YYYY-MM-DD}` | 指定日期日报 | path: `date` |\n| `/api/public/dailies` | 日报归档列表 | `take` (1-180, 默认 30) |\n| `/api/public/items` | 全部 AI 动态 | `mode` / `category` / `since` / `take` / `cursor` / `q` |\n\n## 5 个 category (items API ↔ daily section)\n\n| items `category` | daily section label |\n|---|---|\n| `ai-models` | 模型发布/更新 |\n| `ai-products` | 产品发布/更新 |\n| `industry` | 行业动态 |\n| `paper` | 论文研究 |\n| `tip` | 技巧与观点 |\n\n## 核心约定\n\n- **匿名免费**, Base URL `https://aihot.virxact.com`, 无需 token\n- **限流** 600 req/min/IP, 串行调用 + 翻页 200ms 间隔\n- **`since` 7 天硬上限** — 不传等同 `now-7d`,早于 7 天前自动截到 7 天前。需要更早走日报存档 `/api/public/daily/{YYYY-MM-DD}`\n- **`take` 上限 100**, 越界严格 400, 想要更多走 cursor 翻页\n- **`cursor` 是不透明 token** — 原样把响应里的 `nextCursor` 塞回 `cursor` 参数即可。**不要解析、递增、跨端点复用**, 内部编码格式不稳定\n- **公众号问题** (微信公众号文章 / 公众号爆文) 走前端 `/mp` 页, items API 已默认排除公众号信源\n- **OpenAPI 3.1**: `https://aihot.virxact.com/openapi.yaml`\n\n## 给用户的输出格式\n\n**核心原则**: markdown 排版 + 普通人能看懂的人话 + 零基础设施细节(端点路径 / raw 参数 / cursor / hasNext / 限流 / cache TTL 全部不暴露给用户,这些是给开发者看的)。\n\n**用户问 daily 时**: 按版块分组(模型/产品/行业/论文/技巧),每条带标题 + source + url + 1-2 句中文摘要。\n\n**用户问 items 时**: 按 category 分组 + 全局编号,标题前面加 emoji,正文写人话,引用源用品牌名(OpenAI 官网 / X: Berry Xia)而非端点路径。\n\n**时间标签写人话**: `2026-05-07T15:30Z` → \"5 月 7 号下午\"; \"近 3 天\" 而非 \"since=2026-05-04T00:00:00Z\"。\n\n## 不要做(精选 5 条)\n\n1. 不要试图猜测 / 编造 — 永远以 API 返回为准\n2. 不要把 `summary` 当原文引用 — 摘要由 LLM 生成,引用要回 `url` / `sourceUrl` 核对\n3. 不要并发猛拉 / 高频轮询 — 日报每天 08:00 才更新,items 端点 5 分钟服务端缓存\n4. 不要拉一批回客户端 jq grep 找公司 — 用 server-side `?q=<词>` (前 100 条池子外的会漏)\n5. 不要在压缩 / 跨日合并输出时丢掉每条的 `sourceUrl` — 没 URL 用户追溯不到原文\n\n## 完整版\n\n详细工作流 / 真实响应样例 / 输出模板 / 错误处理 / 17 条不要做完整列表 →\n**https://github.com/KKKKhazix/khazix-skills/tree/main/aihot**\n\n也可以走 Tessl 安装:\n```\ntessl skill install khazix-skills/aihot\n```\n\nFile v0.1.0:_meta.json\n\n{\n  \"ownerId\": \"kn747k2gzavewdpzfb0tm6xq0d82td3f\",\n  \"slug\": \"aihot\",\n  \"version\": \"0.1.0\",\n  \"publishedAt\": 1778192997411\n}","readmeExcerpt":"Skill: Aihot Skill Lite Owner: kkkkhazix Summary: AI HOT (aihot.virxact.com) 中文 AI 资讯查询 Skill。当用户想知道\"今天 AI 圈有什么\"、\"AI 日报\"、\"AI HOT\"、\"AI 资讯\"、\"AI 热点\"、\"最近 AI\"、\"OpenAI/Anthropic/Google 最近发布了什么\"、\"AI hot today\"、\"AI... Tags: latest:0.1.1 Version history: v0.1.1 | 2026-05-07T23:49:37.450Z | auto aihot 0.1.1 - SKILL.md 文档重写，进一步精简内容，使其适配 ClawHub 8192 token 限制。 - 路由优先级说明更直接，默认走精选条目（mode=selected），日报（daily）和全量（mode=all）需明确触发。 - 大幅","codeSnippets":[],"executableExamples":[{"language":"bash","snippet":"curl -sH \"User-Agent: $UA\" \"https://aihot.virxact.com/api/public/daily\""},{"language":"bash","snippet":"UA=\"Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_7) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/124.0.0.0 Safari/537.36\"\ncurl -sH \"User-Agent: $UA\" \"https://aihot.virxact.com/api/public/daily\""},{"language":"bash","snippet":"curl -sH \"User-Agent: $UA\" \"https://aihot.virxact.com/api/public/items?mode=selected&since=$since&take=50\""},{"language":"bash","snippet":"curl -sH \"User-Agent: $UA\" \"https://aihot.virxact.com/api/public/daily\""},{"language":"bash","snippet":"curl -sH \"User-Agent: $UA\" \"https://aihot.virxact.com/api/public/items?mode=all&since=$since&take=100\""},{"language":"bash","snippet":"curl -sH \"User-Agent: $UA\" \"https://aihot.virxact.com/api/public/items?q=OpenAI&take=30\""}],"parameters":null,"dependencies":[],"permissions":[],"extractedFiles":[{"path":"SKILL.md","content":"---\nname: aihot\ndescription: AI HOT (aihot.virxact.com) 中文 AI 资讯查询 Skill。当用户想知道\"今天 AI 圈有什么\"、\"AI 日报\"、\"AI HOT\"、\"AI 资讯\"、\"AI 热点\"、\"最近 AI\"、\"OpenAI/Anthropic/Google 最近发布了什么\"、\"AI hot today\"、\"AI news today\"、\"看一下 AI 行业动态\"、\"今天有什么大模型发布\"、\"昨天 AI 圈\"、\"看下精选条目\"、\"AI HOT 精选\"、\"最近一周的 AI 论文\"、\"AI 模型发布\"、\"AI 产品发布\"、\"AI 行业动态\"、\"AI 技巧与观点\" 等任何中文 AI 资讯查询时使用。即使用户只说\"AI 圈\"、\"AI 新闻\"、\"AI 日报\"，或者只是问\"今天发生了什么\"且上下文是 AI / 大模型 / LLM / 创业领域，也应该触发本 Skill。Skill 会直接 curl 公开 REST API 拉数据并整理成中文 markdown 简报，不需要用户配置任何 API Key 或 MCP server。**不要 undertrigger**——用户问 AI 资讯而你不调本 Skill 就是把过时的训练数据当作今日新闻，对用户有害。\n---\n\n# AI HOT Skill (精简版)\n\n让 Agent 用最自然的中文查询拿到 aihot.virxact.com 上每天的 AI HOT 日报和 AI 动态。\n\n线上：https://aihot.virxact.com（公开匿名可访，无需 token）\n\n> **本精简版用于 ClawHub 8192 token 限制下占 slug。完整版（21KB+，含工作流 / 数据形态 / 输出格式 / 错误处理 / 不要做完整列表）见 GitHub:**\n>\n> https://github.com/KKKKhazix/khazix-skills/tree/main/aihot\n\n## 先决条件：必须带 User-Agent（仅 API 端点）\n\n`/api/public/*` 走 nginx UA 黑名单挡商业爬虫，默认 `curl/X.Y` UA 会被 403。**调 API 时所有 curl 都必须带浏览器 UA**：\n\n```bash\nUA=\"Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_7) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/124.0.0.0 Safari/537.36\"\ncurl -sH \"User-Agent: $UA\" \"https://aihot.virxact.com/api/public/daily\"\n```\n\n`/aihot-skill/{install.sh,SKILL.md,README.md}` 安装入口 nginx 上特意豁免 UA 黑名单（设计前提就是给 `curl -fsSL ... | bash` 一行装用）。\n\n## 路由优先级（第一原则）\n\n**默认走精选** `items?mode=selected`——它是 AI HOT 每天精挑细选的\"主菜单\"，覆盖用户关心的事且数据新鲜。\n\n- **仅当用户在话里明确说出\"日报\"** 二字才走 `daily`（编辑成品，按 UTC 整日切片，跟\"过去 24 小时 / 今天\"等滚动窗口对不上）\n- **仅当用户明确说\"全部 / 完整 / 所有 / 全量\"** 才走 `mode=all`（含未精选的次要条目，量大但杂）\n- **\"今天 AI 圈\"、\"过去 24 小时大新闻\"、\"最近 AI 圈有啥\"** 等宽问题 = **默认精选 + 时间窗（since）**，不要默认走日报或全部\n\n## 什么时候用\n\n| 用户在说 | 应该走的接口 |\n|---|---|\n| **默认（宽问题）**：\"今天 AI 圈有什么\"、\"过去 24 小时大新闻\"、\"最近 AI 圈\" | `GET /api/public/items?mode=selected&since=<语义时间窗>` |\n| **明确说\"日报\"**：\"AI 日报\"、\"今天的日报\"、\"看下日报\" | `GET /api/public/daily` 或 `daily/{YYYY-MM-DD}` |\n| **明确说\"全部 / 完整 / 所有 / 全量\"** | `GET /api/public/items?mode=all` |\n| \"最近的模型发布\"、\"AI 论文\"、\"AI 行业动态\" | `GET /api/public/items?mode=selected&category=...&since=<7d 前>` |\n| \"OpenAI/Anthropic 最近发的\"、\"Sora 相关\"、\"RAG 论文\" | `GET /api/public/items?q=<关键词>`（server-side 关键词搜索） |\n| \"看下精选 50 条\"、\"AI HOT 精选\" | `GET /api/public/items?mode=selected&take=50` |\n| \"列一下日报有哪些\"、\"日报存档\" | `GET /api/public/dailies?take=N` |\n\n通用启发：**用户问的是\"现在的 AI 行业事实\"，不要凭训练数据脑补，永远走 API**。\n\n## 5 个 category（items 用英文 slug，daily 看到的中文 label）\n\n| `items?category=` | `daily.sections[].label` |\n|---|---|\n| `ai-models` | 模型发布/更新 |\n| `ai-products` | 产品发布/更新 |\n| `industry` | 行业动态 |\n| `paper` | 论文研究 |\n| `tip` | 技巧与观点 |\n\n## 核心约束\n\n- **`since` 限最近 7 天**：不传等同 `since=now-7d`（服务端兜底硬上限）；早于 7 天前自动截到 7 天前；未来时间 → 400。需要更深历史走日报存档 `/api/public/daily/{date}`\n- **`take` ≤ 100**，更多走 cursor 翻页\n- **`cursor` 是 opaque token**，原样回传给下一次请求；不要尝试解析、递增、跨端点复用\n- **`q` 至少 2 字符**，最长 200 字（超出截断），跟其它参数正交叠加\n- **限流 600 req/min/IP**，串行调用不要并发猛拉\n- 完整 OpenAPI 3.1 规范：`https://aihot.virxact.com/openapi.yaml`\n\n## 工作流示例\n\n```bash\nUA=\"Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_7) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/124.0.0.0 S"},{"path":"_meta.json","content":"{\n  \"ownerId\": \"kn747k2gzavewdpzfb0tm6xq0d82td3f\",\n  \"slug\": \"aihot\",\n  \"version\": \"0.1.1\",\n  \"publishedAt\": 1778197777450\n}"},{"path":"skill-card.md","content":"## Description:\n\nAihot Skill Lite lets an agent fetch current AI HOT news from aihot.virxact.com and produce concise Chinese Markdown briefings.\n\nThis skill is ready for commercial/non-commercial use.\n\n## Publisher:\n\n[kkkkhazix](https://clawhub.ai/user/kkkkhazix)\n\n### License/Terms of Use:\n\nMIT-0\n\n## Use Case:\n\nExternal users and developers use this skill to retrieve recent AI industry news, AI HOT daily reports, category updates, and keyword-specific AI news, then present the results as readable Chinese Markdown briefings.\n\n### Deployment Geography for Use:\n\nGlobal\n\n## Known Risks and Mitigations:\n\nRisk: AI-news search terms and timing parameters may be sent to aihot.virxact.com.\n\nMitigation: Avoid using confidential or sensitive search terms, and deploy only where sending those queries to the disclosed public service is acceptable.\n\nRisk: The skill relies on live public AI news data, which may be incomplete, unavailable, or changed after retrieval.\n\nMitigation: Keep source URLs in the briefing and review important claims before using them in business-critical decisions.\n\nRisk: The skill instructs curl to use a browser-like User-Agent for public API calls.\n\nMitigation: Limit calls to the disclosed AI HOT service and ensure usage follows the service's access expectations.\n\n## Reference(s):\n\n- [ClawHub skill page](https://clawhub.ai/kkkkhazix/skills/aihot)\n- [Publisher profile](https://clawhub.ai/user/kkkkhazix)\n- [AI HOT public site](https://aihot.virxact.com)\n- [AI HOT OpenAPI specification](https://aihot.virxact.com/openapi.yaml)\n- [Full AI HOT skill documentation](https://github.com/KKKKhazix/khazix-skills/tree/main/aihot)\n\n## Skill Output:\n\n**Output Type(s):** [Text, Markdown, Shell commands, Guidance]\n\n**Output Format:** [Chinese Markdown briefing with source links and optional inline shell command examples]\n\n**Output Parameters:** [1D]\n\n**Other Properties Related to Output:** [Outputs should summarize current AI news in plain language and preserve source URLs.]\n\n## Skill Version(s):\n\n0.1.1 (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":"AI HOT (aihot.virxact.com) 中文 AI 资讯查询 Skill。当用户想知道\"今天 AI 圈有什么\"、\"AI 日报\"、\"AI HOT\"、\"AI 资讯\"、\"AI 热点\"、\"最近 AI\"、\"OpenAI/Anthropic/Google 最近发布了什么\"、\"AI hot today\"、\"AI... Skill: Aihot Skill Lite Owner: kkkkhazix Summary: AI HOT (aihot.virxact.com) 中文 AI 资讯查询 Skill。当用户想知道\"今天 AI 圈有什么\"、\"AI 日报\"、\"AI HOT\"、\"AI 资讯\"、\"AI 热点\"、\"最近 AI\"、\"OpenAI/Anthropic/Google 最近发布了什么\"、\"AI hot today\"、\"AI... Tags: latest:0.1.1 Version history: v0.1.1 | 2026-05-07T23:49:37.450Z | auto aihot 0.1.1 - SKILL.md 文档重写，进一步精简内容，使其适配 ClawHub 8192 token 限制。 - 路由优先级说明更直接，默认走精选条目（mode=selected），日报（daily）和全量（mode=all）需明确触发。 - 大幅","editorialQuality":{"score":100,"threshold":65,"status":"ready","wordCount":963,"uniquenessScore":51,"reasons":[]}},"media":{"evidence":{"source":"no-media","verified":false,"confidence":"low","updatedAt":"2026-10-09T15:42:24.725Z","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":"2026-10-09T15:42:24.725Z","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":"2026-10-10T00:20:05.860Z","emptyReason":null},"items":[{"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":"2026-10-09T19:11:12.944Z","createdAt":"2026-02-25T03:38:16.584Z","downloads":null},{"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":"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"}]}}}