{ "schemaVersion": "1.0", "item": { "slug": "larksync-feishu-local-cache", "name": "LarkSync Feishu Local Cache", "source": "tencent", "type": "skill", "category": "效率提升", "sourceUrl": "https://clawhub.ai/gooderno1/larksync-feishu-local-cache", "canonicalUrl": "https://clawhub.ai/gooderno1/larksync-feishu-local-cache", "targetPlatform": "OpenClaw" }, "install": { "downloadMode": "redirect", "downloadUrl": "/downloads/larksync-feishu-local-cache", "sourceDownloadUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=larksync-feishu-local-cache", "sourcePlatform": "tencent", "targetPlatform": "OpenClaw", "installMethod": "Manual import", "extraction": "Extract archive", "prerequisites": [ "OpenClaw" ], "packageFormat": "ZIP package", "includedAssets": [ "OPENCLAW_AGENT_GUIDE.md", "README.md", "scripts/larksync_skill_helper.py", "scripts/larksync_wsl_helper.py", "SKILL.md" ], "primaryDoc": "SKILL.md", "quickSetup": [ "Download the package from Yavira.", "Extract the archive and review SKILL.md first.", "Import or place the package into your OpenClaw setup." ], "agentAssist": { "summary": "Hand the extracted package to your coding agent with a concrete install brief instead of figuring it out manually.", "steps": [ "Download the package from Yavira.", "Extract it into a folder your agent can access.", "Paste one of the prompts below and point your agent at the extracted folder." ], "prompts": [ { "label": "New install", "body": "I downloaded a skill package from Yavira. Read SKILL.md from the extracted folder and install it by following the included instructions. Then review README.md for any prerequisites, environment setup, or post-install checks. Tell me what you changed and call out any manual steps you could not complete." }, { "label": "Upgrade existing", "body": "I downloaded an updated skill package from Yavira. Read SKILL.md from the extracted folder, compare it with my current installation, and upgrade it while preserving any custom configuration unless the package docs explicitly say otherwise. Then review README.md for any prerequisites, environment setup, or post-install checks. Summarize what changed and any follow-up checks I should run." } ] }, "sourceHealth": { "source": "tencent", "status": "healthy", "reason": "direct_download_ok", "recommendedAction": "download", "checkedAt": "2026-04-23T16:43:11.935Z", "expiresAt": "2026-04-30T16:43:11.935Z", "httpStatus": 200, "finalUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=4claw-imageboard", "contentType": "application/zip", "probeMethod": "head", "details": { "probeUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=4claw-imageboard", "contentDisposition": "attachment; filename=\"4claw-imageboard-1.0.1.zip\"", "redirectLocation": null, "bodySnippet": null }, "scope": "source", "summary": "Source download looks usable.", "detail": "Yavira can redirect you to the upstream package for this source.", "primaryActionLabel": "Download for OpenClaw", "primaryActionHref": "/downloads/larksync-feishu-local-cache" }, "validation": { "installChecklist": [ "Use the Yavira download entry.", "Review SKILL.md after the package is downloaded.", "Confirm the extracted package contains the expected setup assets." ], "postInstallChecks": [ "Confirm the extracted package includes the expected docs or setup files.", "Validate the skill or prompts are available in your target agent workspace.", "Capture any manual follow-up steps the agent could not complete." ] }, "downloadPageUrl": "https://openagent3.xyz/downloads/larksync-feishu-local-cache", "agentPageUrl": "https://openagent3.xyz/skills/larksync-feishu-local-cache/agent", "manifestUrl": "https://openagent3.xyz/skills/larksync-feishu-local-cache/agent.json", "briefUrl": "https://openagent3.xyz/skills/larksync-feishu-local-cache/agent.md" }, "agentAssist": { "summary": "Hand the extracted package to your coding agent with a concrete install brief instead of figuring it out manually.", "steps": [ "Download the package from Yavira.", "Extract it into a folder your agent can access.", "Paste one of the prompts below and point your agent at the extracted folder." ], "prompts": [ { "label": "New install", "body": "I downloaded a skill package from Yavira. Read SKILL.md from the extracted folder and install it by following the included instructions. Then review README.md for any prerequisites, environment setup, or post-install checks. Tell me what you changed and call out any manual steps you could not complete." }, { "label": "Upgrade existing", "body": "I downloaded an updated skill package from Yavira. Read SKILL.md from the extracted folder, compare it with my current installation, and upgrade it while preserving any custom configuration unless the package docs explicitly say otherwise. Then review README.md for any prerequisites, environment setup, or post-install checks. Summarize what changed and any follow-up checks I should run." } ] }, "documentation": { "source": "clawhub", "primaryDoc": "SKILL.md", "sections": [ { "title": "LarkSync Feishu Local Cache Skill", "body": "参考：\n\nOPENCLAW_AGENT_GUIDE.md：面向 OpenClaw 代理的自动执行 runbook（首次授权分支、无人值守分支、失败分支）" }, { "title": "English Overview", "body": "Purpose: sync Feishu documents to local markdown/files and let OpenClaw read local cache first.\nValue: fewer Feishu API calls, lower token consumption, and more stable retrieval latency.\nDefault mode: download_only with low-frequency schedule (daily by default).\nAdvanced mode: bidirectional and upload_only are supported when explicitly requested." }, { "title": "Typical intents (EN)", "body": "\"Set up a daily 01:00 sync from this Feishu folder to local cache.\"\n\"Check my current LarkSync auth and task status first.\"\n\"Switch this task to bidirectional sync and explain the risk.\"" }, { "title": "价值主张", "body": "让 OpenClaw 的高频文档问答“走本地、不走云端接口”。\n把 API 调用从“每次问答触发”变成“低频定时同步触发”。\n在不改用户飞书使用习惯的前提下，直接获得更稳、更省的文档检索链路。" }, { "title": "适用目标", "body": "目标：减少 OpenClaw 直接调用飞书 API 的频率，优先读取本地 Markdown/附件。\n默认策略：download_only + 每日低频同步（可自定义时间与周期）。\n进阶策略：支持 bidirectional（双向）和 upload_only，但仅在用户明确要求时启用。\nWindows 侧建议直接使用 LarkSync 安装包版运行服务，不需要源码构建。" }, { "title": "触发意图（示例）", "body": "“把飞书生产测试文件夹每天 01:00 同步到本地，给我配置好。”\n“先检查 LarkSync 当前授权和同步任务状态。”\n“我想把这个目录切成双向同步，先评估风险再改。”" }, { "title": "默认执行流程", "body": "检查本地 LarkSync 服务与授权状态。\n配置低频下载策略（默认每天一次）。\n创建同步任务（默认 download_only）。\n按需触发一次立即同步，建立本地缓存基线。\n后续回答用户文档问题时，优先读取本地同步目录。" }, { "title": "命令入口", "body": "使用以下脚本作为统一入口（返回 JSON，便于自动化编排）：\n\npython integrations/openclaw/skills/larksync_feishu_local_cache/scripts/larksync_skill_helper.py check\npython integrations/openclaw/skills/larksync_feishu_local_cache/scripts/larksync_skill_helper.py configure-download --download-value 1 --download-unit days --download-time 01:00\npython integrations/openclaw/skills/larksync_feishu_local_cache/scripts/larksync_skill_helper.py create-task --name \"OpenClaw 每日同步\" --local-path \"D:\\\\Knowledge\\\\FeishuMirror\" --cloud-folder-token \"\" --sync-mode download_only\npython integrations/openclaw/skills/larksync_feishu_local_cache/scripts/larksync_skill_helper.py run-task --task-id \"\"\npython integrations/openclaw/skills/larksync_feishu_local_cache/scripts/larksync_skill_helper.py bootstrap-daily --local-path \"D:\\\\Knowledge\\\\FeishuMirror\" --cloud-folder-token \"\" --sync-mode download_only --download-value 1 --download-unit days --download-time 01:00 --run-now\n\nWSL 场景（OpenClaw 在 WSL，LarkSync 在 Windows）推荐入口：\n\n# 先做地址诊断（逐项显示 localhost / host.docker.internal / gateway / resolv nameserver）\npython integrations/openclaw/skills/larksync_feishu_local_cache/scripts/larksync_wsl_helper.py diagnose\n\n# 直接执行原有命令（自动探测可达地址；远程地址自动补 --allow-remote-base-url）\npython integrations/openclaw/skills/larksync_feishu_local_cache/scripts/larksync_wsl_helper.py check\npython integrations/openclaw/skills/larksync_feishu_local_cache/scripts/larksync_wsl_helper.py bootstrap-daily --local-path \"/mnt/d/Knowledge/FeishuMirror\" --cloud-folder-token \"\" --sync-mode download_only --download-value 1 --download-unit days --download-time 01:00 --run-now\n\n若全部候选地址不可达，优先确认 Windows 侧：\n\nLarkSync 已启动；\n若手动设置过 LARKSYNC_BACKEND_BIND_HOST=127.0.0.1，请改回 0.0.0.0 或移除该变量；\n防火墙已放行 WSL 网段到 TCP 8000。\n\n安全边界：\n\n未探测到 Windows 侧可达服务时，脚本会输出诊断信息并停止，不会自动在 WSL 安装依赖或启动后端。\n请先在 Windows 侧启动 LarkSync（安装包版或开发模式），确认 :8000 可达后再重试。\n注意：飞书 OAuth 首次授权仍需用户完成；授权完成后可进入日常低频同步运行。\n\n默认安全策略：\n\nbase-url 仅允许 localhost/127.0.0.1/::1，避免把云目录 token 发送到未知远端地址。\n只有在明确可信内网场景，才允许开启远程地址：\n\npython integrations/openclaw/skills/larksync_feishu_local_cache/scripts/larksync_skill_helper.py --base-url \"https://larksync.internal.example\" --allow-remote-base-url check" }, { "title": "约束与安全边界", "body": "未通过 check 之前，不执行任务创建或策略变更。\n未经用户明确同意，不把 download_only 自动切到 bidirectional。\n若用户要开启双向，必须先告知风险：\n\n本地误改可能上云；\n首次建任务可能触发下行/上行扫描；\n建议先在测试目录验证。" }, { "title": "失败处理", "body": "若接口返回 401/403：提示重新授权飞书并检查“用户身份权限”。\n若创建任务冲突（409）：自动复用同路径+同云目录的现有任务并回显任务 ID。\n若后端不可达：优先提示启动 LarkSync 安装包版托盘程序（开发者再使用 npm run dev）。" }, { "title": "输出规范", "body": "对用户：简明中文结论 + 下一步操作。\n对系统：保留 helper 脚本 JSON 原始输出，便于追踪与审计。" } ], "body": "LarkSync Feishu Local Cache Skill\n\n参考：\n\nOPENCLAW_AGENT_GUIDE.md：面向 OpenClaw 代理的自动执行 runbook（首次授权分支、无人值守分支、失败分支）\nEnglish Overview\nPurpose: sync Feishu documents to local markdown/files and let OpenClaw read local cache first.\nValue: fewer Feishu API calls, lower token consumption, and more stable retrieval latency.\nDefault mode: download_only with low-frequency schedule (daily by default).\nAdvanced mode: bidirectional and upload_only are supported when explicitly requested.\nTypical intents (EN)\n\"Set up a daily 01:00 sync from this Feishu folder to local cache.\"\n\"Check my current LarkSync auth and task status first.\"\n\"Switch this task to bidirectional sync and explain the risk.\"\n价值主张\n让 OpenClaw 的高频文档问答“走本地、不走云端接口”。\n把 API 调用从“每次问答触发”变成“低频定时同步触发”。\n在不改用户飞书使用习惯的前提下，直接获得更稳、更省的文档检索链路。\n适用目标\n目标：减少 OpenClaw 直接调用飞书 API 的频率，优先读取本地 Markdown/附件。\n默认策略：download_only + 每日低频同步（可自定义时间与周期）。\n进阶策略：支持 bidirectional（双向）和 upload_only，但仅在用户明确要求时启用。\nWindows 侧建议直接使用 LarkSync 安装包版运行服务，不需要源码构建。\n触发意图（示例）\n“把飞书生产测试文件夹每天 01:00 同步到本地，给我配置好。”\n“先检查 LarkSync 当前授权和同步任务状态。”\n“我想把这个目录切成双向同步，先评估风险再改。”\n默认执行流程\n检查本地 LarkSync 服务与授权状态。\n配置低频下载策略（默认每天一次）。\n创建同步任务（默认 download_only）。\n按需触发一次立即同步，建立本地缓存基线。\n后续回答用户文档问题时，优先读取本地同步目录。\n命令入口\n\n使用以下脚本作为统一入口（返回 JSON，便于自动化编排）：\n\npython integrations/openclaw/skills/larksync_feishu_local_cache/scripts/larksync_skill_helper.py check\npython integrations/openclaw/skills/larksync_feishu_local_cache/scripts/larksync_skill_helper.py configure-download --download-value 1 --download-unit days --download-time 01:00\npython integrations/openclaw/skills/larksync_feishu_local_cache/scripts/larksync_skill_helper.py create-task --name \"OpenClaw 每日同步\" --local-path \"D:\\\\Knowledge\\\\FeishuMirror\" --cloud-folder-token \"\" --sync-mode download_only\npython integrations/openclaw/skills/larksync_feishu_local_cache/scripts/larksync_skill_helper.py run-task --task-id \"\"\npython integrations/openclaw/skills/larksync_feishu_local_cache/scripts/larksync_skill_helper.py bootstrap-daily --local-path \"D:\\\\Knowledge\\\\FeishuMirror\" --cloud-folder-token \"\" --sync-mode download_only --download-value 1 --download-unit days --download-time 01:00 --run-now\n\n\nWSL 场景（OpenClaw 在 WSL，LarkSync 在 Windows）推荐入口：\n\n# 先做地址诊断（逐项显示 localhost / host.docker.internal / gateway / resolv nameserver）\npython integrations/openclaw/skills/larksync_feishu_local_cache/scripts/larksync_wsl_helper.py diagnose\n\n# 直接执行原有命令（自动探测可达地址；远程地址自动补 --allow-remote-base-url）\npython integrations/openclaw/skills/larksync_feishu_local_cache/scripts/larksync_wsl_helper.py check\npython integrations/openclaw/skills/larksync_feishu_local_cache/scripts/larksync_wsl_helper.py bootstrap-daily --local-path \"/mnt/d/Knowledge/FeishuMirror\" --cloud-folder-token \"\" --sync-mode download_only --download-value 1 --download-unit days --download-time 01:00 --run-now\n\n\n若全部候选地址不可达，优先确认 Windows 侧：\n\nLarkSync 已启动；\n若手动设置过 LARKSYNC_BACKEND_BIND_HOST=127.0.0.1，请改回 0.0.0.0 或移除该变量；\n防火墙已放行 WSL 网段到 TCP 8000。\n\n安全边界：\n\n未探测到 Windows 侧可达服务时，脚本会输出诊断信息并停止，不会自动在 WSL 安装依赖或启动后端。\n请先在 Windows 侧启动 LarkSync（安装包版或开发模式），确认 :8000 可达后再重试。\n注意：飞书 OAuth 首次授权仍需用户完成；授权完成后可进入日常低频同步运行。\n\n默认安全策略：\n\nbase-url 仅允许 localhost/127.0.0.1/::1，避免把云目录 token 发送到未知远端地址。\n只有在明确可信内网场景，才允许开启远程地址：\npython integrations/openclaw/skills/larksync_feishu_local_cache/scripts/larksync_skill_helper.py --base-url \"https://larksync.internal.example\" --allow-remote-base-url check\n\n约束与安全边界\n未通过 check 之前，不执行任务创建或策略变更。\n未经用户明确同意，不把 download_only 自动切到 bidirectional。\n若用户要开启双向，必须先告知风险：\n本地误改可能上云；\n首次建任务可能触发下行/上行扫描；\n建议先在测试目录验证。\n失败处理\n若接口返回 401/403：提示重新授权飞书并检查“用户身份权限”。\n若创建任务冲突（409）：自动复用同路径+同云目录的现有任务并回显任务 ID。\n若后端不可达：优先提示启动 LarkSync 安装包版托盘程序（开发者再使用 npm run dev）。\n输出规范\n对用户：简明中文结论 + 下一步操作。\n对系统：保留 helper 脚本 JSON 原始输出，便于追踪与审计。" }, "trust": { "sourceLabel": "tencent", "provenanceUrl": "https://clawhub.ai/gooderno1/larksync-feishu-local-cache", "publisherUrl": "https://clawhub.ai/gooderno1/larksync-feishu-local-cache", "owner": "gooderno1", "version": "0.1.6", "license": null, "verificationStatus": "Indexed source record" }, "links": { "detailUrl": "https://openagent3.xyz/skills/larksync-feishu-local-cache", "downloadUrl": "https://openagent3.xyz/downloads/larksync-feishu-local-cache", "agentUrl": "https://openagent3.xyz/skills/larksync-feishu-local-cache/agent", "manifestUrl": "https://openagent3.xyz/skills/larksync-feishu-local-cache/agent.json", "briefUrl": "https://openagent3.xyz/skills/larksync-feishu-local-cache/agent.md" } }