{"id":"d777b649-19cd-42d4-ac7f-027c234b95b3","entityType":"agent","slug":"clawhub-sgtbaixiao-meme-digger","name":"meme-digger","canonicalUrl":"https://www.xpersona.co/agent/clawhub-sgtbaixiao-meme-digger","canonicalPath":"/agent/clawhub-sgtbaixiao-meme-digger","generatedAt":"2026-10-09T22:50:32.563Z","source":"CLAWHUB","claimStatus":"UNCLAIMED","verificationTier":"NONE","summary":{"evidence":{"source":"editorial-content","verified":true,"confidence":"high","updatedAt":"2026-10-09T17:55:02.702Z","emptyReason":null},"description":"网络梗考古与科普（刨根问底式）。连接贴吧（Tieba）与 B 站（Bilibili），针对用户问到的网络梗/抽象话/热梗，读取 B 站搜索、视频详情与评论区（含评论里的梗图），从评论中提取线索做发散式搜索，把 B 站、贴吧、评论、梗图、来源考证分文件收集，最后整合成一份带文字说明、梗图、来源介绍的综合科普报告。当用户问\"这是什么梗 / 这个梗什么来历 / 这个说法哪来的\"时使用。 Skill: meme-digger Owner: sgtbaixiao Summary: 网络梗考古与科普（刨根问底式）。连接贴吧（Tieba）与 B 站（Bilibili），针对用户问到的网络梗/抽象话/热梗，读取 B 站搜索、视频详情与评论区（含评论里的梗图），从评论中提取线索做发散式搜索，把 B 站、贴吧、评论、梗图、来源考证分文件收集，最后整合成一份带文字说明、梗图、来源介绍的综合科普报告。当用户问\"这是什么梗 / 这个梗什么来历 / 这个说法哪来的\"时使用。 Tags: latest:0.1.0 Version history: v0.1.0 | 2026-08-09T13:38:40.547Z | auto Initial release of \"meme-digger\". - Provides an in-depth workflow for internet meme investigation and doc","descriptionLabel":"Technical summary","evidenceSummary":"Capability contract not published. No trust telemetry is available yet. 2.2K downloads reported by the source. Last updated 10/9/2026.","installCommand":"clawhub skill install s172yq424m3anmm92ags91c9xx8c5ac5:meme-digger","sourceUrl":"https://clawhub.ai/sgtbaixiao/meme-digger","homepage":"https://clawhub.ai/sgtbaixiao/skills/meme-digger","primaryLinks":[{"label":"View on ClawHub","url":"https://clawhub.ai/sgtbaixiao/meme-digger","kind":"source"},{"label":"Homepage","url":"https://clawhub.ai/sgtbaixiao/skills/meme-digger","kind":"homepage"}],"safetyScore":84,"overallRank":62,"popularityScore":67,"trustScore":null,"claimedByName":null,"isOwner":false,"seoDescription":"网络梗考古与科普（刨根问底式）。连接贴吧（Tieba）与 B 站（Bilibili），针对用户问到的网络梗/抽象话/热梗，读取 B 站搜索、视频详情与评论区（含评论里的梗图），从评论中提取线索做发散式搜索，把 B 站、贴吧、评论、梗图、来源考证分文件收集，最后整合成一份带文字说明、梗图、来源介绍的综合科普报告。当用户问"},"coverage":{"evidence":{"source":"public-profile","verified":false,"confidence":"medium","updatedAt":"2026-10-09T17:55:02.702Z","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":"2026-10-09T17:55:02.702Z","emptyReason":null},"stars":null,"forks":null,"downloads":2171,"packageName":null,"latestVersion":"0.1.0","tractionLabel":"2.2K downloads"},"release":{"evidence":{"source":"CLAWHUB","verified":false,"confidence":"medium","updatedAt":"2026-10-09T17:55:02.666Z","emptyReason":null},"lastUpdatedAt":"2026-10-09T17:55:02.702Z","lastCrawledAt":"2026-10-09T17:55:02.666Z","lastIndexedAt":null,"nextCrawlAt":"2026-10-10T17:55:02.666Z","lastVerifiedAt":null,"highlights":[{"version":"0.1.0","createdAt":"2026-08-09T13:38:40.547Z","changelog":"Initial release of \"meme-digger\". - Provides an in-depth workflow for internet meme investigation and documentation, focusing on origins, spread, and context. - Integrates Bilibili and Tieba search, video/comment analysis, and meme image collection, organizing findings in a structured multi-file workspace. - Automated tools to search, analyze, and cross-reference comments, images, and posts; supports batch meme gallery collection with de-duplication. - Offers a step-by-step process from initial hypothesis, source gathering, to final report and self-contained HTML encyclopedia generation. - Includes scripts for cookie management, platform integration, and customizable reporting templates. - Emphasizes evidence-based reporting, source reliability ratings, and clear separation of fact, rumor, and open questions.","fileCount":21,"zipByteSize":41532}]},"execution":{"evidence":{"source":"CLAWHUB","verified":false,"confidence":"low","updatedAt":null,"emptyReason":"No published capability contract is available yet."},"installCommand":"clawhub skill install s172yq424m3anmm92ags91c9xx8c5ac5:meme-digger","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-sgtbaixiao-meme-digger/snapshot","contractUrl":"https://www.xpersona.co/api/v1/agents/clawhub-sgtbaixiao-meme-digger/contract","trustUrl":"https://www.xpersona.co/api/v1/agents/clawhub-sgtbaixiao-meme-digger/trust"},"curlExamples":["curl -s \"https://www.xpersona.co/api/v1/agents/clawhub-sgtbaixiao-meme-digger/snapshot\"","curl -s \"https://www.xpersona.co/api/v1/agents/clawhub-sgtbaixiao-meme-digger/contract\"","curl -s \"https://www.xpersona.co/api/v1/agents/clawhub-sgtbaixiao-meme-digger/trust\""],"jsonRequestTemplate":{"query":"summarize this repo","constraints":{"maxLatencyMs":2000,"protocolPreference":["OPENCLEW"]}},"jsonResponseTemplate":{"ok":true,"result":{"summary":"...","confidence":0.9},"meta":{"source":"CLAWHUB","generatedAt":"2026-10-09T22:50:32.563Z"}},"retryPolicy":{"maxAttempts":3,"backoffMs":[500,1500,3500],"retryableConditions":["HTTP_429","HTTP_503","NETWORK_TIMEOUT"]}},"endpoints":{"dossierUrl":"https://www.xpersona.co/api/v1/agents/clawhub-sgtbaixiao-meme-digger/dossier","snapshotUrl":"https://www.xpersona.co/api/v1/agents/clawhub-sgtbaixiao-meme-digger/snapshot","contractUrl":"https://www.xpersona.co/api/v1/agents/clawhub-sgtbaixiao-meme-digger/contract","trustUrl":"https://www.xpersona.co/api/v1/agents/clawhub-sgtbaixiao-meme-digger/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":"2026-10-09T17:55:02.702Z","emptyReason":null},"readme":"Skill: meme-digger\n\nOwner: sgtbaixiao\n\nSummary: 网络梗考古与科普（刨根问底式）。连接贴吧（Tieba）与 B 站（Bilibili），针对用户问到的网络梗/抽象话/热梗，读取 B 站搜索、视频详情与评论区（含评论里的梗图），从评论中提取线索做发散式搜索，把 B 站、贴吧、评论、梗图、来源考证分文件收集，最后整合成一份带文字说明、梗图、来源介绍的综合科普报告。当用户问\"这是什么梗 / 这个梗什么来历 / 这个说法哪来的\"时使用。\n\nTags: latest:0.1.0\n\nVersion history:\n\nv0.1.0 | 2026-08-09T13:38:40.547Z | auto\n\nInitial release of \"meme-digger\".\n\n- Provides an in-depth workflow for internet meme investigation and documentation, focusing on origins, spread, and context.\n- Integrates Bilibili and Tieba search, video/comment analysis, and meme image collection, organizing findings in a structured multi-file workspace.\n- Automated tools to search, analyze, and cross-reference comments, images, and posts; supports batch meme gallery collection with de-duplication.\n- Offers a step-by-step process from initial hypothesis, source gathering, to final report and self-contained HTML encyclopedia generation.\n- Includes scripts for cookie management, platform integration, and customizable reporting templates.\n- Emphasizes evidence-based reporting, source reliability ratings, and clear separation of fact, rumor, and open questions.\n\nArchive index:\n\nArchive v0.1.0: 21 files, 41532 bytes\n\nFiles: .gitignore (183b), config (0b), config/cookies.json.example (563b), LICENSE (1068b), README.md (2811b), scripts (0b), scripts/bili_comments.py (5411b), scripts/bili_dl.py (2614b), scripts/bili_memes.py (6360b), scripts/bili_search.py (3195b), scripts/bili_video.py (2258b), scripts/collect_gallery.py (17005b), scripts/common.py (3016b), scripts/config_cookies.py (5568b), scripts/make_report.py (12346b), scripts/tieba_search.py (3687b), skill-card.md (2480b), SKILL.md (13496b), templates (0b), templates/encyclopedia.css (5793b), _meta.json (130b)\n\nFile v0.1.0:SKILL.md\n\n---\nname: meme-digger\ndescription: 网络梗考古与科普（刨根问底式）。连接贴吧（Tieba）与 B 站（Bilibili），针对用户问到的网络梗/抽象话/热梗，读取 B 站搜索、视频详情与评论区（含评论里的梗图），从评论中提取线索做发散式搜索，把 B 站、贴吧、评论、梗图、来源考证分文件收集，最后整合成一份带文字说明、梗图、来源介绍的综合科普报告。当用户问\"这是什么梗 / 这个梗什么来历 / 这个说法哪来的\"时使用。\nlicense: MIT\ncompatibility: pi, Claude Code, Codex, OpenCode（Agent Skills 标准）\nmetadata:\n  author: Sgt_BaiXiao\n  version: \"1.0.0\"\n  homepage: https://github.com/SgtBaixiao/meme-digger\n---\n\n# Meme Digger — 网络梗考古与科普（刨根问底版）\n\n梗的答案不在任何单一平台：起源往往在贴吧/论坛，走红靠 B 站/微博，二次创作散落各平台，**真正的线索常常藏在评论区里**（高赞评论是用户集体认知，评论里的名字/作品/梗图是发散搜索的起点）。本 skill 采用\"**分文件收集 → 发散深挖 → 最终整合**\"的刨根问底工作法，绝不编造出处，区分事实与网络传闻。\n\n**脚本位置**：所有 `scripts/...` 路径相对本 skill 目录（即 SKILL.md 所在目录）。调用前先解析 skill 目录（Claude Code 可用 `${CLAUDE_SKILL_DIR}`；pi 等其它 agent 定位到 SKILL.md 所在目录即可），再以 `python <skill_dir>/scripts/xxx.py` 执行，不要在其它工作目录直接写相对路径。\n\n## 工作区结构（每个梗一个目录）\n\n在**当前工作目录**下创建 `meme-research/<梗名-slug>/`，所有调查产物分文件存放：\n\n```\nmeme-research/<梗名>/\n├── 00-计划.md               # 立项：关键词变体、假设、待查问题清单\n├── 01-b站搜索.md             # B站搜索结果 + 候选视频详情\n├── 02-b站评论区.md           # 评论区挖掘（高赞评论/线索/评论图片URL）\n├── 03-贴吧.md                # 贴吧帖子与吧内讨论\n├── 04-发散线索.md            # 从评论/视频中提取的线索 → 发散搜索的记录\n├── 05-梗图.md                # 梗图图鉴：本地图/出处/含义/使用场景\n├── images/                   # 下载到本地的梗图文件 + manifest.txt\n├── 06-来源考证.md            # 每条关键论断的证据链与可信度评级\n├── 报告-<梗名>.md            # 最终整合：文字说明 + 梗图 + 来源介绍\n└── <梗名>-百科.html          # 第9步生成的单文件 Meme 百科页（最终交付物）\n```\n\n## 工作流程\n\n### 第 1 步：立项（先想清楚再动手）\n\n创建 `00-计划.md`，写清：\n- **关键词变体**：原名 / 拼音缩写 / 英文名 / 表情包关键词 / 话题标签 / 近义梗（例：\"典\" → `典`、`典中典`、`太典了`）。\n- **待查问题清单**：它是什么？什么时候出现的？谁发明的？怎么火的？现在怎么用？衍生了什么？\n- **假设**：先写下自己的初判（多义词时列多个义项），之后逐条验证或推翻。\n\n### 第 2 步：B 站搜索（主通道）\n\n```bash\npython \"scripts/bili_search.py\" \"<关键词>\" --limit 10\n```\n\n- 对候选视频逐一取详情（发布时间 = 时间线证据）：\n\n```bash\npython \"scripts/bili_video.py\" \"<bvid>\"\n```\n\n- 把结果整理进 `01-b站搜索.md`。标记出\"考古/科普/盘点\"向视频（标题含科普/考古/溯源/梗百科/盘点）。\n\n### 第 3 步：评论区深挖（本版核心，免登录）\n\n对 **2-5 个关键视频** 挖掘评论区：\n\n```bash\npython \"scripts/bili_comments.py\" \"<bvid>\" --pages 3 --top 50 --min-like 20 --out \"meme-research/<梗名>/02-b站评论区.md\"\n```\n\n- 同时生成 `02-b站评论区.images.txt`（评论里的梗图 URL 清单）。\n- **读评论看什么**：\n  1. 高赞评论 = 大众对该梗的集体认知/用法示例。\n  2. 评论里出现的**专有名词** = 发散线索（人名、up主、作品名、平台、事件、其他梗名）。\n  3. 评论区吵什么 = 该梗的争议点。\n- 把线索（含来源评论）登记到 `04-发散线索.md`。\n\n### 第 4 步：贴吧采集（需 cookie，见下）\n\n```bash\npython \"scripts/tieba_search.py\" \"<关键词>\"\n```\n\n- **cookie 配置（B站 + 贴吧统一管理）**：复制 `config/cookies.json.example` 为 `config/cookies.json` 并填写，**推荐用配置向导**（自动验证 cookie 是否有效）：\n\n```bash\npython \"scripts/config_cookies.py\"                    # 交互式：粘贴 B站/贴吧 Cookie，自动验证后写入\npython \"scripts/config_cookies.py\" --status           # 查看当前配置与有效性\npython \"scripts/config_cookies.py\" --bili-cookie \"...\" --tieba-cookie \"...\"   # 命令行方式\n```\n\n- 获取方式：登录对应站点 → F12 → Network → 刷新 → 复制请求头的 Cookie 整段。\n- B站 cookie 用于提升稳定性（评论/搜索默认免登录即可，有 cookie 更稳）；贴吧 cookie **必需**（否则 403 安全验证）。\n- 贴吧价值：**起源考据**（最早帖子）、讨论语境、吧内黑话。\n- 无 cookie 时降级：web_search `site:tieba.baidu.com <关键词>`（工具可用时）→ web_fetch 吧页 → 或明确告知用户\"贴吧侧缺失\"。\n\n### 第 5 步：发散式搜索（刨根问底的引擎）\n\n把 `04-发散线索.md` 里登记的**每一条线索**作为新关键词，回到第 2-4 步循环搜索（通常 2-3 轮）：\n\n- 人名/up主 → 搜其代表作、最早作品\n- 作品名 → 搜其起源、主创\n- 平台/事件 → 搜时间节点\n- 其他梗名 → 搜其与主梗的关系\n\n每轮把新发现追加进 `04-发散线索.md`（标注：线索 → 搜了什么 → 找到了什么 → 新线索）。**收敛条件**：连续一轮没有产生新线索，或待查问题清单全部有答案。\n\n### 第 6 步：梗图收集（一次性完整图鉴，v1.1）\n\n**一次运行收集所有图源**，自动完成相关性分档、去重、生成候选清单：\n\n```bash\npython \"scripts/collect_gallery.py\" \"<梗名>\" \\\n  --variants \"<变体1,变体2,...>\" \\\n  --out \"meme-research/<梗名>\" --limit 60\n```\n\n- **图源与分档**（T1 直接联系最强 → T6 尽力而为）：\n\n| 级 | 源 | 直接联系保证 |\n|---|---|---|\n| T1 | B站代表视频封面 | 视频标题含梗 |\n| T2 | B站高赞评论配图 | 评论含梗词/反应词 |\n| T3 | B站二创/表情包/合集/整活视频封面 | 查询=梗名+二创词（**二创检索通道**） |\n| T4 | 百度图片（表情包/梗图/二创 查询） | 查询词相关，内容需人工复核 |\n| T5 | 贴吧帖子首楼图（需 cookie） | 帖子标题含梗；风控验证页自动降级 |\n| T6 | 斗图啦 | 尽力而为，失败静默 |\n\n- **二创梗图**：T3/T4 显式按 \"二创/整活/表情包/梗图/合集/抽象\" 检索，覆盖二创梗图通道。\n- **自动去重**：URL 归一化 + 下载后 sha256 内容去重。\n- **产出**：`images/`（编号图片 + manifest.json）+ `05-梗图.md` 候选清单（出处/评分/上下文），人工复核后定稿。\n- **预览**：先 `--no-download` 看候选，再正式下载；单源不可用时自动降级不中断。\n- 旧版定向挖掘（bili_memes）仍可单独使用：`python \"scripts/bili_memes.py\" \"<bvid>\" --pages 2 --min-like 20 --download N --out ...`\n\n**人工复核（强制，不变）**：每张梗图定稿前确认：① 图片内容与梗主题相关（看上下文/原图佐证）；② 记录出处；③ 标注含义与使用场景。**拿不准的图一律不收**，宁可少收。\n\n### 第 7 步：来源考证\n\n在 `06-来源考证.md` 里为**每条关键论断**建立证据链：\n\n| 论断 | 证据(链接/引用) | 可信度 |\n|---|---|---|\n| 起源 | ... | 确凿/网友考证/待考证 |\n\n- 至少 **2 个独立信源**一致才写\"确认\"。\n- 严格区分：确凿证据（原始链接/时间戳）vs 网友考证 vs 流传说法。\n- 找不到出处 → 明确写\"待考证\"，不编造。\n\n### 第 8 步：最终整合\n\n读取所有分文件，整合成 `报告-<梗名>.md`（模板见下）。要点：\n- **先给结论**：一句话概括放最前。\n- **证据链**：每条论断后标注来源（BV 链接/帖子链接/平台）。\n- **时间线精确到月**，给时间点不给\"大概\"。\n- **梗图入报告**：正文相关处引用本地梗图（`![图](images/xxx.jpg)`），并标注含义。\n- **来源介绍**：除链接外，一句话说明每个来源是什么（哪个 up 主、什么立场、辟谣还是玩梗）。\n- 末尾附\"仍不确定\"清单。\n\n### 第 9 步：生成 Meme 百科 HTML（最终交付）\n\n```bash\npython \"scripts/make_report.py\" \"meme-research/<梗名>\" --out \"meme-research/<梗名>/<梗名>-百科.html\" [--title 自定义标题]\n```\n\n- **单文件自包含**：内联 CSS + 图片 base64 内嵌，字体走 CDN（Poppins/Inter）+ 系统回退，可离线阅读核心内容。\n- **百科页固定模板**（`templates/encyclopedia.css` 控制样式，遵循用户级 `house-style` 技能：极简纸质·米白+橙·章节红分割线·低多边形/粒子 hero·reduced-motion）→ 各章节（起源/时间线/含义/例句/梗图图鉴/衍生/数据/信源/注意事项）→ 页脚。\n- 梗图图鉴自动渲染为网格画廊，时间线自动渲染为列表，信源渲染为可点击链接。\n- 每次调查只生成 **一个 HTML 文件**，即最终交付物。\n\n## 输出模板（报告-<梗名>.md）\n\n```markdown\n# 「<梗名>」是什么梗？\n\n## 一句话概括\n<谁、什么时候、因为什么、怎么火的，30 字内>\n\n## 起源与出处\n- <最早的出处/原型，标注信源>\n- <多条说法并存时：说法A（来源1）、说法B（来源2），注明主流观点>\n\n## 走红时间线\n- YYYY-MM：<事件>（信源）\n\n## 含义与用法\n- 原义 / 引申义 / 当下主流用法；使用场景与语气\n\n## 经典例句 / 句式\n> \"例句\"\n\n## 梗图图鉴\n![梗图1](images/xxx.jpg)\n<这张图是什么、梗在哪、常用场景>\n![梗图2](images/yyy.jpg)\n...\n\n## 衍生与相关梗\n- <衍生梗>：<一句话>（信源）\n\n## 数据佐证\n- B站代表视频：<标题>（<bvid>）播放<X>，发布于<日期>\n- 贴吧/评论热度：<若有>\n\n## 信源列表（含来源介绍）\n1. <平台> <作者>：<标题>（<一句话说明该来源的性质>）<链接>\n\n## 注意事项\n- 争议/敏感：<若有>\n- 待考证：<明确列出未能证实的内容>\n```\n\n## 质量标准（写完自查）\n\n- [ ] 每个关键论断带信源，链接可点开\n- [ ] 事实与传闻分开标注\n- [ ] 有时间线（尽量精确到月）\n- [ ] 有例句，读者能立刻学会用\n- [ ] 梗图有出处与含义说明\n- [ ] 信源列表包含\"来源介绍\"（作者/立场）\n- [ ] \"待考证\"项明确列出，没有编造\n\n## 边界与安全\n\n- 不传播谣言与恶意抹黑；涉及争议内容只陈述\"网络说法\"并标注风险。\n- 涉及低俗/违规梗：正常科普可以，不教唆、不美化、不过度展开。\n- 引用遵守\"简短引用 + 链接\"，不整段复制他人文案。\n- **梗图版权**：只下载保存用于分析，报告中保留原图 URL 与出处；不声称拥有版权。\n- 用户问的梗若带明显攻击/引战意图，先温和澄清意图再科普。\n\n## 故障排查\n\n| 现象 | 处理 |\n|---|---|\n| bili_search 解析 0 条 | 风控/改版 → web_fetch 打开搜索页；加 --page 2；稍后重试 |\n| bili_comments code≠0 或无评论 | 视频被删/限流 → 换 bvid；评论关闭 → 跳过该视频 |\n| 贴吧 403 安全验证 | 配置 config/cookies.json（第 4 步）或走降级路径 |\n| web_search/web_fetch 不可用 | 提示 Ollama web search 未启动；B站三件套脚本不依赖它 |\n| 梗太新搜不到 | 告知\"尚未形成稳定记录\"，给已确认部分 + 观察建议 |\n| 下载的图打不开 | 部分图片 URL 需 Referer（脚本已带）；重试或换源 |\n\n## 脚本与配置\n\n- `scripts/bili_search.py <关键词> [--page N] [--limit N]` — B站搜索（免登录）\n- `scripts/bili_video.py <bvid> [--cover]` — 视频详情（免登录；--cover 输出封面 URL）\n- `scripts/bili_comments.py <bvid> [--pages N] [--top N] [--min-like N] [--out 文件] [--root <rpid>]` — 评论区深挖（免登录，附带图片URL清单）\n- `scripts/collect_gallery.py <梗名> [--variants a,b,c] [--out 目录] [--limit N] [--no-download]` — **一次性完整图鉴收集**（T1-T6 多源 + 二创检索 + 去重 + 自动 05-梗图.md）\n- `scripts/bili_memes.py <bvid...> [--pages N] [--min-like N] [--download N] [--out 目录]` — 单视频定向梗图挖掘（旧版）\n- `scripts/bili_dl.py <url...>|--from <清单文件> --out <目录>` — 图片下载（去重）\n- `scripts/tieba_search.py <关键词>` — 贴吧搜索（需 cookie）\n- `scripts/config_cookies.py` — **B站+贴吧 cookie 配置向导**（验证后写入 config/cookies.json）\n- `scripts/make_report.py <工作目录> --out <输出.html> [--title 自定义标题]` — 生成单文件 Meme 百科 HTML\n- `scripts/common.py` — 共享模块（UA / cookie 加载 / 重试抓取），所有脚本依赖\n- `config/cookies.json` — 统一 cookie 配置（bilibili + tieba 两个条目），由 config_cookies.py 写入\n- `templates/encyclopedia.css` — 百科页固定模板样式（make_report.py 自动引用）\n- 全部仅用 Python 标准库，无需安装依赖。\n\nFile v0.1.0:README.md\n\n# meme-digger — 网络梗考古与科普（Agent Skill）\n\n刨根问底式网络梗调查：连接贴吧与 B 站，从评论区挖线索做发散搜索，产出带证据链、时间线、梗图、来源介绍的单文件 Meme 百科 HTML。\n\n遵循 [Agent Skills](https://agentskills.io) 开放标准，兼容 pi / Claude Code / Codex / OpenCode。\n\n## 安装（各平台）\n\n| 平台 | 方式 | 状态 |\n|---|---|---|\n| **pi** | 复制整个目录到 `~/.pi/agent/skills/meme-digger/` | ✅ 已安装 |\n| **Claude Code** | `git clone https://github.com/SgtBaixiao/meme-digger ~/.claude/skills/meme-digger` | ✅ 可克隆 |\n| **Codex / OpenCode** | 复制到 `~/.codex/skills/` / `~/.opencode/skills/` | ✅ 可克隆 |\n| **Hugging Face CLI** | `hf skills add https://github.com/SgtBaixiao/meme-digger` | ⏳ 上架后 |\n| **Agent Skill Hub** | `skhub add SgtBaixiao/meme-digger` | ⏳ 待导入（需账号） |\n| **Skillstore** | `skillstore install meme-digger` | ⏳ 待提交（需账号） |\n\n## 依赖\n\n- Python ≥ 3.10，**仅标准库**，零第三方依赖\n- B 站：免登录（搜索/详情/评论/图片全通）\n- 贴吧：需 cookie（`python scripts/config_cookies.py` 配置向导，见 SKILL.md 第 4 步）\n\n## 使用\n\n直接问 agent\"这是什么梗 / 这个梗什么来历\"，或在支持 `/` 命令的客户端输入 `/meme-digger <梗名>`。\n\n完整工作流（9 步：立项 → B站搜索 → 评论区深挖 → 贴吧采集 → 发散搜索 → 梗图收集 → 来源考证 → 整合报告 → Meme 百科 HTML）见 [SKILL.md](SKILL.md)。\n\n## 结构\n\n```\nmeme-digger/\n├── SKILL.md                    # 方法论 + 9 步工作流 + 质量标准（入口）\n├── scripts/                    # Python 标准库脚本套件\n│   ├── bili_search.py          # B站搜索（免登录）\n│   ├── bili_video.py           # 视频详情\n│   ├── bili_comments.py        # 评论区深挖 + 梗图 URL 清单\n│   ├── bili_memes.py           # 定向梗图挖掘（T1封面/T2高赞评分）\n│   ├── bili_dl.py              # 图片下载（去重）\n│   ├── tieba_search.py         # 贴吧搜索（需 cookie）\n│   ├── config_cookies.py       # cookie 配置向导\n│   ├── make_report.py          # 生成单文件 Meme 百科 HTML\n│   └── common.py               # 共享模块\n├── templates/encyclopedia.css  # 百科页样式模板\n└── config/cookies.json.example # cookie 配置样例（真实 cookie 不入库）\n```\n\n## 安全与边界\n\n- 不传播谣言、不教唆、不美化低俗内容；事实与网络传闻严格分标注\n- 梗图仅下载用于分析，报告保留原图 URL 与出处，不声称版权\n- 引用遵守\"简短引用 + 链接\"\n\n## License\n\nMIT © Sgt_BaiXiao\n\nFile v0.1.0:_meta.json\n\n{\n  \"ownerId\": \"kn70zc8xyczzxmfzbjft9gveks8c4j27\",\n  \"slug\": \"meme-digger\",\n  \"version\": \"0.1.0\",\n  \"publishedAt\": 1786282720547\n}\n\nFile v0.1.0:skill-card.md\n\n## Description:\n\nMeme Digger helps agents research internet memes by collecting evidence from Bilibili, Tieba, comments, images, and source trails, then producing an evidence-based explainer report.\n\nThis skill is ready for commercial/non-commercial use.\n\n## Publisher:\n\n[sgtbaixiao](https://clawhub.ai/user/sgtbaixiao)\n\n### License/Terms of Use:\n\nMIT\n\n## Use Case:\n\nExternal users and developers use this skill when they ask what an internet meme means, where it came from, how it spread, and which evidence supports the explanation. The skill guides an agent through search, comment review, image collection, source checking, and final report generation.\n\n### Deployment Geography for Use:\n\nGlobal\n\n## Known Risks and Mitigations:\n\nRisk: The skill may require Bilibili or Tieba session cookies, which are account credentials.\n\nMitigation: Prefer environment variables over repo-local cookie files, restrict cookie file permissions, avoid passing cookies on the command line, and delete or rotate cookies after use.\n\nRisk: Generated Markdown or HTML reports may embed local files or active content.\n\nMitigation: Review generated reports before sharing them and remove unexpected local-file references or active content.\n\nRisk: Downloaded images and meme evidence can include copyrighted, misleading, or sensitive material.\n\nMitigation: Use downloaded images for analysis, retain source attribution, separate fact from rumor, and manually review uncertain images before including them.\n\n## Reference(s):\n\n- [Server-resolved source repository](https://github.com/SgtBaixiao/meme-digger)\n- [ClawHub skill page](https://clawhub.ai/sgtbaixiao/skills/meme-digger)\n- [Agent Skills open standard](https://agentskills.io)\n\n## Skill Output:\n\n**Output Type(s):** [text, markdown, code, shell commands, configuration, guidance, HTML]\n\n**Output Format:** [Markdown reports, structured text files, shell commands, configuration guidance, image manifests, and self-contained HTML]\n\n**Output Parameters:** [1D]\n\n**Other Properties Related to Output:** [Outputs are organized into a per-meme research workspace and may include downloaded meme images for analysis.]\n\n## Skill Version(s):\n\n0.1.0 (source: ClawHub release metadata)\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\nFile v0.1.0:LICENSE\n\nMIT License\n\nCopyright (c) 2026 Sgt_BaiXiao\n\nPermission is hereby granted, free of charge, to any person obtaining a copy\nof this software and associated documentation files (the \"Software\"), to deal\nin the Software without restriction, including without limitation the rights\nto use, copy, modify, merge, publish, distribute, sublicense, and/or sell\ncopies of the Software, and to permit persons to whom the Software is\nfurnished to do so, subject to the following conditions:\n\nThe above copyright notice and this permission notice shall be included in all\ncopies or substantial portions of the Software.\n\nTHE SOFTWARE IS PROVIDED \"AS IS\", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR\nIMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,\nFITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE\nAUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER\nLIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,\nOUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE\nSOFTWARE.","readmeExcerpt":"Skill: meme-digger Owner: sgtbaixiao Summary: 网络梗考古与科普（刨根问底式）。连接贴吧（Tieba）与 B 站（Bilibili），针对用户问到的网络梗/抽象话/热梗，读取 B 站搜索、视频详情与评论区（含评论里的梗图），从评论中提取线索做发散式搜索，把 B 站、贴吧、评论、梗图、来源考证分文件收集，最后整合成一份带文字说明、梗图、来源介绍的综合科普报告。当用户问\"这是什么梗 / 这个梗什么来历 / 这个说法哪来的\"时使用。 Tags: latest:0.1.0 Version history: v0.1.0 | 2026-08-09T13:38:40.547Z | auto Initial release of \"meme-digger\". - Provides an in-depth workflow for internet meme investigation and doc","codeSnippets":[],"executableExamples":[{"language":"text","snippet":"meme-research/<梗名>/\n├── 00-计划.md               # 立项：关键词变体、假设、待查问题清单\n├── 01-b站搜索.md             # B站搜索结果 + 候选视频详情\n├── 02-b站评论区.md           # 评论区挖掘（高赞评论/线索/评论图片URL）\n├── 03-贴吧.md                # 贴吧帖子与吧内讨论\n├── 04-发散线索.md            # 从评论/视频中提取的线索 → 发散搜索的记录\n├── 05-梗图.md                # 梗图图鉴：本地图/出处/含义/使用场景\n├── images/                   # 下载到本地的梗图文件 + manifest.txt\n├── 06-来源考证.md            # 每条关键论断的证据链与可信度评级\n├── 报告-<梗名>.md            # 最终整合：文字说明 + 梗图 + 来源介绍\n└── <梗名>-百科.html          # 第9步生成的单文件 Meme 百科页（最终交付物）"},{"language":"bash","snippet":"python \"scripts/bili_search.py\" \"<关键词>\" --limit 10"},{"language":"bash","snippet":"python \"scripts/bili_video.py\" \"<bvid>\""},{"language":"bash","snippet":"python \"scripts/bili_comments.py\" \"<bvid>\" --pages 3 --top 50 --min-like 20 --out \"meme-research/<梗名>/02-b站评论区.md\""},{"language":"bash","snippet":"python \"scripts/tieba_search.py\" \"<关键词>\""},{"language":"bash","snippet":"python \"scripts/config_cookies.py\"                    # 交互式：粘贴 B站/贴吧 Cookie，自动验证后写入\npython \"scripts/config_cookies.py\" --status           # 查看当前配置与有效性\npython \"scripts/config_cookies.py\" --bili-cookie \"...\" --tieba-cookie \"...\"   # 命令行方式"}],"parameters":null,"dependencies":[],"permissions":[],"extractedFiles":[{"path":"SKILL.md","content":"---\nname: meme-digger\ndescription: 网络梗考古与科普（刨根问底式）。连接贴吧（Tieba）与 B 站（Bilibili），针对用户问到的网络梗/抽象话/热梗，读取 B 站搜索、视频详情与评论区（含评论里的梗图），从评论中提取线索做发散式搜索，把 B 站、贴吧、评论、梗图、来源考证分文件收集，最后整合成一份带文字说明、梗图、来源介绍的综合科普报告。当用户问\"这是什么梗 / 这个梗什么来历 / 这个说法哪来的\"时使用。\nlicense: MIT\ncompatibility: pi, Claude Code, Codex, OpenCode（Agent Skills 标准）\nmetadata:\n  author: Sgt_BaiXiao\n  version: \"1.0.0\"\n  homepage: https://github.com/SgtBaixiao/meme-digger\n---\n\n# Meme Digger — 网络梗考古与科普（刨根问底版）\n\n梗的答案不在任何单一平台：起源往往在贴吧/论坛，走红靠 B 站/微博，二次创作散落各平台，**真正的线索常常藏在评论区里**（高赞评论是用户集体认知，评论里的名字/作品/梗图是发散搜索的起点）。本 skill 采用\"**分文件收集 → 发散深挖 → 最终整合**\"的刨根问底工作法，绝不编造出处，区分事实与网络传闻。\n\n**脚本位置**：所有 `scripts/...` 路径相对本 skill 目录（即 SKILL.md 所在目录）。调用前先解析 skill 目录（Claude Code 可用 `${CLAUDE_SKILL_DIR}`；pi 等其它 agent 定位到 SKILL.md 所在目录即可），再以 `python <skill_dir>/scripts/xxx.py` 执行，不要在其它工作目录直接写相对路径。\n\n## 工作区结构（每个梗一个目录）\n\n在**当前工作目录**下创建 `meme-research/<梗名-slug>/`，所有调查产物分文件存放：\n\n```\nmeme-research/<梗名>/\n├── 00-计划.md               # 立项：关键词变体、假设、待查问题清单\n├── 01-b站搜索.md             # B站搜索结果 + 候选视频详情\n├── 02-b站评论区.md           # 评论区挖掘（高赞评论/线索/评论图片URL）\n├── 03-贴吧.md                # 贴吧帖子与吧内讨论\n├── 04-发散线索.md            # 从评论/视频中提取的线索 → 发散搜索的记录\n├── 05-梗图.md                # 梗图图鉴：本地图/出处/含义/使用场景\n├── images/                   # 下载到本地的梗图文件 + manifest.txt\n├── 06-来源考证.md            # 每条关键论断的证据链与可信度评级\n├── 报告-<梗名>.md            # 最终整合：文字说明 + 梗图 + 来源介绍\n└── <梗名>-百科.html          # 第9步生成的单文件 Meme 百科页（最终交付物）\n```\n\n## 工作流程\n\n### 第 1 步：立项（先想清楚再动手）\n\n创建 `00-计划.md`，写清：\n- **关键词变体**：原名 / 拼音缩写 / 英文名 / 表情包关键词 / 话题标签 / 近义梗（例：\"典\" → `典`、`典中典`、`太典了`）。\n- **待查问题清单**：它是什么？什么时候出现的？谁发明的？怎么火的？现在怎么用？衍生了什么？\n- **假设**：先写下自己的初判（多义词时列多个义项），之后逐条验证或推翻。\n\n### 第 2 步：B 站搜索（主通道）\n\n```bash\npython \"scripts/bili_search.py\" \"<关键词>\" --limit 10\n```\n\n- 对候选视频逐一取详情（发布时间 = 时间线证据）：\n\n```bash\npython \"scripts/bili_video.py\" \"<bvid>\"\n```\n\n- 把结果整理进 `01-b站搜索.md`。标记出\"考古/科普/盘点\"向视频（标题含科普/考古/溯源/梗百科/盘点）。\n\n### 第 3 步：评论区深挖（本版核心，免登录）\n\n对 **2-5 个关键视频** 挖掘评论区：\n\n```bash\npython \"scripts/bili_comments.py\" \"<bvid>\" --pages 3 --top 50 --min-like 20 --out \"meme-research/<梗名>/02-b站评论区.md\"\n```\n\n- 同时生成 `02-b站评论区.images.txt`（评论里的梗图 URL 清单）。\n- **读评论看什么**：\n  1. 高赞评论 = 大众对该梗的集体认知/用法示例。\n  2. 评论里出现的**专有名词** = 发散线索（人名、up主、作品名、平台、事件、其他梗名）。\n  3. 评论区吵什么 = 该梗的争议点。\n- 把线索（含来源评论）登记到 `04-发散线索.md`。\n\n### 第 4 步：贴吧采集（需 cookie，见下）\n\n```bash\npython \"scripts/tieba_search.py\" \"<关键词>\"\n```\n\n- **cookie 配置（B站 + 贴吧统一管理）**：复制 `config/cookies.json.example` 为 `config/cookies.json` 并填写，**推荐用配置向导**（自动验证 cookie 是否有效）：\n\n```bash\npython \"scripts/config_cookies.py\"                    # 交互式：粘贴 B站/贴吧 Cookie，自动验证后写入\npython \"scripts/config_cookies.py\" --status           # 查看当前配置与有效性\npython \"scripts/config_cookies.py\" --bili-cookie \"...\" --tieba-cookie \"...\"   # 命令行方式\n```\n\n- 获取方式：登录对应站点 → F12 → Network → 刷新 → 复制请求头的 Cookie 整段。\n- B站 cookie 用于提升稳定性（评论/搜索默认免登录即可，有 cookie 更稳）；贴吧 cookie **必需**（否则 403 安全验证）。\n- 贴吧价值：**起源考据**（最早帖子）、讨论语境、吧内黑话。\n- 无 cookie 时降级：web_search `site:tieba.baidu.com <关键词>`（工具可用时）→ web_fetch 吧页 → 或明确告知用户\"贴吧侧缺失\"。\n\n### 第 5 步：发散式搜索（刨根问底的引擎）\n\n把 `04-发散线索.md` 里登记的**每一条线索**作为新关键"},{"path":"README.md","content":"# meme-digger — 网络梗考古与科普（Agent Skill）\n\n刨根问底式网络梗调查：连接贴吧与 B 站，从评论区挖线索做发散搜索，产出带证据链、时间线、梗图、来源介绍的单文件 Meme 百科 HTML。\n\n遵循 [Agent Skills](https://agentskills.io) 开放标准，兼容 pi / Claude Code / Codex / OpenCode。\n\n## 安装（各平台）\n\n| 平台 | 方式 | 状态 |\n|---|---|---|\n| **pi** | 复制整个目录到 `~/.pi/agent/skills/meme-digger/` | ✅ 已安装 |\n| **Claude Code** | `git clone https://github.com/SgtBaixiao/meme-digger ~/.claude/skills/meme-digger` | ✅ 可克隆 |\n| **Codex / OpenCode** | 复制到 `~/.codex/skills/` / `~/.opencode/skills/` | ✅ 可克隆 |\n| **Hugging Face CLI** | `hf skills add https://github.com/SgtBaixiao/meme-digger` | ⏳ 上架后 |\n| **Agent Skill Hub** | `skhub add SgtBaixiao/meme-digger` | ⏳ 待导入（需账号） |\n| **Skillstore** | `skillstore install meme-digger` | ⏳ 待提交（需账号） |\n\n## 依赖\n\n- Python ≥ 3.10，**仅标准库**，零第三方依赖\n- B 站：免登录（搜索/详情/评论/图片全通）\n- 贴吧：需 cookie（`python scripts/config_cookies.py` 配置向导，见 SKILL.md 第 4 步）\n\n## 使用\n\n直接问 agent\"这是什么梗 / 这个梗什么来历\"，或在支持 `/` 命令的客户端输入 `/meme-digger <梗名>`。\n\n完整工作流（9 步：立项 → B站搜索 → 评论区深挖 → 贴吧采集 → 发散搜索 → 梗图收集 → 来源考证 → 整合报告 → Meme 百科 HTML）见 [SKILL.md](SKILL.md)。\n\n## 结构\n\n```\nmeme-digger/\n├── SKILL.md                    # 方法论 + 9 步工作流 + 质量标准（入口）\n├── scripts/                    # Python 标准库脚本套件\n│   ├── bili_search.py          # B站搜索（免登录）\n│   ├── bili_video.py           # 视频详情\n│   ├── bili_comments.py        # 评论区深挖 + 梗图 URL 清单\n│   ├── bili_memes.py           # 定向梗图挖掘（T1封面/T2高赞评分）\n│   ├── bili_dl.py              # 图片下载（去重）\n│   ├── tieba_search.py         # 贴吧搜索（需 cookie）\n│   ├── config_cookies.py       # cookie 配置向导\n│   ├── make_report.py          # 生成单文件 Meme 百科 HTML\n│   └── common.py               # 共享模块\n├── templates/encyclopedia.css  # 百科页样式模板\n└── config/cookies.json.example # cookie 配置样例（真实 cookie 不入库）\n```\n\n## 安全与边界\n\n- 不传播谣言、不教唆、不美化低俗内容；事实与网络传闻严格分标注\n- 梗图仅下载用于分析，报告保留原图 URL 与出处，不声称版权\n- 引用遵守\"简短引用 + 链接\"\n\n## License\n\nMIT © Sgt_BaiXiao"},{"path":"_meta.json","content":"{\n  \"ownerId\": \"kn70zc8xyczzxmfzbjft9gveks8c4j27\",\n  \"slug\": \"meme-digger\",\n  \"version\": \"0.1.0\",\n  \"publishedAt\": 1786282720547\n}"},{"path":"skill-card.md","content":"## Description:\n\nMeme Digger helps agents research internet memes by collecting evidence from Bilibili, Tieba, comments, images, and source trails, then producing an evidence-based explainer report.\n\nThis skill is ready for commercial/non-commercial use.\n\n## Publisher:\n\n[sgtbaixiao](https://clawhub.ai/user/sgtbaixiao)\n\n### License/Terms of Use:\n\nMIT\n\n## Use Case:\n\nExternal users and developers use this skill when they ask what an internet meme means, where it came from, how it spread, and which evidence supports the explanation. The skill guides an agent through search, comment review, image collection, source checking, and final report generation.\n\n### Deployment Geography for Use:\n\nGlobal\n\n## Known Risks and Mitigations:\n\nRisk: The skill may require Bilibili or Tieba session cookies, which are account credentials.\n\nMitigation: Prefer environment variables over repo-local cookie files, restrict cookie file permissions, avoid passing cookies on the command line, and delete or rotate cookies after use.\n\nRisk: Generated Markdown or HTML reports may embed local files or active content.\n\nMitigation: Review generated reports before sharing them and remove unexpected local-file references or active content.\n\nRisk: Downloaded images and meme evidence can include copyrighted, misleading, or sensitive material.\n\nMitigation: Use downloaded images for analysis, retain source attribution, separate fact from rumor, and manually review uncertain images before including them.\n\n## Reference(s):\n\n- [Server-resolved source repository](https://github.com/SgtBaixiao/meme-digger)\n- [ClawHub skill page](https://clawhub.ai/sgtbaixiao/skills/meme-digger)\n- [Agent Skills open standard](https://agentskills.io)\n\n## Skill Output:\n\n**Output Type(s):** [text, markdown, code, shell commands, configuration, guidance, HTML]\n\n**Output Format:** [Markdown reports, structured text files, shell commands, configuration guidance, image manifests, and self-contained HTML]\n\n**Output Parameters:** [1D]\n\n**Other Properties Related to Output:** [Outputs are organized into a per-meme research workspace and may include downloaded meme images for analysis.]\n\n## Skill Version(s):\n\n0.1.0 (source: ClawHub release metadata)\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."},{"path":"LICENSE","content":"MIT License\n\nCopyright (c) 2026 Sgt_BaiXiao\n\nPermission is hereby granted, free of charge, to any person obtaining a copy\nof this software and associated documentation files (the \"Software\"), to deal\nin the Software without restriction, including without limitation the rights\nto use, copy, modify, merge, publish, distribute, sublicense, and/or sell\ncopies of the Software, and to permit persons to whom the Software is\nfurnished to do so, subject to the following conditions:\n\nThe above copyright notice and this permission notice shall be included in all\ncopies or substantial portions of the Software.\n\nTHE SOFTWARE IS PROVIDED \"AS IS\", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR\nIMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,\nFITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE\nAUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER\nLIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,\nOUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE\nSOFTWARE."}],"languages":[],"docsSourceLabel":"CLAWHUB","editorialOverview":"网络梗考古与科普（刨根问底式）。连接贴吧（Tieba）与 B 站（Bilibili），针对用户问到的网络梗/抽象话/热梗，读取 B 站搜索、视频详情与评论区（含评论里的梗图），从评论中提取线索做发散式搜索，把 B 站、贴吧、评论、梗图、来源考证分文件收集，最后整合成一份带文字说明、梗图、来源介绍的综合科普报告。当用户问\"这是什么梗 / 这个梗什么来历 / 这个说法哪来的\"时使用。 Skill: meme-digger Owner: sgtbaixiao Summary: 网络梗考古与科普（刨根问底式）。连接贴吧（Tieba）与 B 站（Bilibili），针对用户问到的网络梗/抽象话/热梗，读取 B 站搜索、视频详情与评论区（含评论里的梗图），从评论中提取线索做发散式搜索，把 B 站、贴吧、评论、梗图、来源考证分文件收集，最后整合成一份带文字说明、梗图、来源介绍的综合科普报告。当用户问\"这是什么梗 / 这个梗什么来历 / 这个说法哪来的\"时使用。 Tags: latest:0.1.0 Version history: v0.1.0 | 2026-08-09T13:38:40.547Z | auto Initial release of \"meme-digger\". - Provides an in-depth workflow for internet meme investigation and doc","editorialQuality":{"score":100,"threshold":65,"status":"ready","wordCount":1110,"uniquenessScore":53,"reasons":[]}},"media":{"evidence":{"source":"no-media","verified":false,"confidence":"low","updatedAt":"2026-10-09T17:55:02.702Z","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":"2026-10-09T17:55:02.702Z","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":"2026-10-09T22:50:32.563Z","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"}]}}}