[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M77Y5GSP9GVVF5ZTBDFR4VG8":3,"skill-same:01M77Y5GSP9GVVF5ZTBDFR4VG8":47},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":16,"categories":17,"keywords":18,"publishedAt":19,"linkOnly":20,"markdownContent":21,"markdownBody":22,"frontMatter":23,"refName":24,"commitSha":25,"skillDirectory":26,"forksCount":27,"repositoryHtmlUrl":28,"repositoryHomepageUrl":29,"ownerHtmlUrl":30,"ownerBlogUrl":6,"ownerDescription":31,"updatedAt":32,"install":33,"resources":46},"01M77Y5GSP9GVVF5ZTBDFR4VG8","wechat-sendmedia",null,"send images and files to a wechat conversation through openclaw's wechat channel. use when the user asks to send a local image, send a screenshot, send a downloaded file, or send any media\u002Ffile back to the current wechat chat or an optional recipient. optimized for openclaw builds where the gateway parses MEDIA:file:\u002F\u002F tokens from plain text instead of json media envelopes.","Lord1Egypt\u002Fawesome-skill-forge","Lord1Egypt","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F99746359?v=4","01M7592YDNT0XK9WJ0T2MQVPDN","Mohamed Mounir Ali AL Keshita","01M75GRFNHC8VZNWEB8DKDE433",3,"MIT","https:\u002F\u002Fgithub.com\u002FLord1Egypt\u002Fawesome-skill-forge\u002Fblob\u002Fmaster\u002Fcommunity\u002Fclawhub\u002Fw\u002Fwechat-sendmedia\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: wechat-sendmedia\ndescription: send images and files to a wechat conversation through openclaw's wechat channel. use when the user asks to send a local image, send a screenshot, send a downloaded file, or send any media\u002Ffile back to the current wechat chat or an optional recipient. optimized for openclaw builds where the gateway parses MEDIA:file:\u002F\u002F tokens from plain text instead of json media envelopes.\n---\n\n# Wechat Sendmedia\n\nUse this skill only for the `openclaw-weixin` channel.\n\n## Core rule\n\nFor outbound media, prefer the **plain-text MEDIA token** format, not a JSON envelope.\n\nReturn the final assistant message as plain text like this:\n\n```text\n发送成功\n- 类型：图片 | 文件\n- 路径：\u003Cabsolute path>\n- 接收人：当前会话 | \u003Crecipient>\n\nMEDIA:file:\u002F\u002F\u002Fabsolute\u002Fpath\u002Fto\u002Ffile.png\n```\n\nWhy: newer OpenClaw gateway builds parse media only from text directives such as `MEDIA:file:\u002F\u002F\u002F...`. If you return JSON like `{ \"mediaUrl\": \"file:\u002F\u002F\u002F...\" }`, the gateway may forward that JSON as plain text and no image\u002Ffile will be delivered.\n\n## Never do this\n\nDo not rely on these formats as the primary output:\n\n```json\n{\n  \"text\": \"这是你要的图片\",\n  \"mediaUrl\": \"file:\u002F\u002F\u002Ftmp\u002Fx.png\"\n}\n```\n\nor:\n\n```json\n{\n  \"text\": \"...\",\n  \"mediaUrl\": \"MEDIA:file:\u002F\u002F\u002Ftmp\u002Fx.png\"\n}\n```\n\nThese may be displayed to the user as literal text.\n\n## Supported tasks\n\nHandle these tasks:\n\n- Send a local image file to WeChat.\n- Take a browser or desktop screenshot, then send it.\n- Send a non-image file such as a PDF, text file, archive, or document.\n- Send to the current conversation by default.\n- Send to a specific recipient only if the user explicitly provides one.\n- Return `发送成功` or `发送失败` plus actionable diagnostics.\n\n## Inputs\n\nInterpret the request into:\n\n- `file_path`: absolute local path to an existing file, or a screenshot path produced earlier.\n- `recipient`: optional. Default `当前会话`.\n- `caption`: optional short note for the human-readable confirmation text.\n- `source_kind`: `image` or `file`.\n\nIf the user asks for a screenshot first, obtain the screenshot file before sending.\n\n## Output contract\n\n### Success outcome\n\nReturn plain text only:\n\n```text\n发送成功\n- 类型：图片\n- 路径：\u002Ftmp\u002Fbrowser-shot.png\n- 接收人：当前会话\n\nMEDIA:file:\u002F\u002F\u002Ftmp\u002Fbrowser-shot.png\n```\n\nRules:\n\n- The `MEDIA:file:\u002F\u002F...` directive must be on its own line.\n- Use an absolute local path.\n- Use `图片` for common image types and `文件` for everything else.\n- Keep the confirmation short.\n- Do not wrap the final reply in JSON unless the host explicitly requires JSON. For current OpenClaw builds, plain text is the safe default.\n\n### Failure outcome\n\nReturn:\n\n```text\n发送失败\n- 可能原因：\u003Cone line summary>\n- 建议：\u003Cnext step>\n\n调试信息:\n- file_path: \u003Cpath>\n- exists: true|false\n- recipient: \u003Crecipient>\n- upload_url: \u003Cvalue or n\u002Fa>\n- upload_url_host: \u003Cvalue or n\u002Fa>\n- encrypted_param_length: \u003Cnumber or 0>\n- sendmessage_status: \u003Cvalue or n\u002Fa>\n- sendmessage_response: \u003Craw text or n\u002Fa>\n- context_token_present: true|false\n- media_type_guess: image|file|unknown\n```\n\n## Workflow\n\n1. Resolve the user's intent.\n2. Ensure the target file exists.\n3. Run `scripts\u002Femit_media_reply.py` to validate the file and build the plain-text reply payload.\n4. Return the script's `reply_text` value as the assistant message.\n5. If a send attempt fails or the user reports a failed send, run `scripts\u002Fweixin_debug_send.js` to produce targeted diagnostics.\n6. Summarize the result in Chinese.\n\n## File-type decision rules\n\nTreat these as images by default:\n\n- `.png`, `.jpg`, `.jpeg`, `.gif`, `.webp`, `.bmp`\n\nTreat everything else as files.\n\n## Recipient rules\n\n- If the user says `发给我` and the current task came from WeChat, use `当前会话`.\n- Only override the recipient if the user explicitly names another receiver.\n- If a concrete user id is unavailable, keep `recipient` as `当前会话` in the confirmation text and let the host runtime map it to the current chat.\n\n## Troubleshooting rules\n\nWhen debugging an OpenClaw WeChat media failure, prefer concrete evidence over guesses.\n\nCommon causes to mention only when supported by the debug output:\n\n- File path does not exist.\n- Host runtime treated the reply as plain text because no `MEDIA:` token was present.\n- Missing context token for the current chat.\n- Upload URL not returned.\n- `x-encrypted-param` missing or unexpectedly short.\n- `sendmessage` returned empty body or non-success JSON.\n- Token\u002Fsession mismatch between runtime state and on-disk account data.\n- Wrong route used: JSON envelope or slash command text instead of `MEDIA:file:\u002F\u002F...`.\n\n## Examples\n\n### Example: screenshot request\n\nFinal reply:\n\n```text\n发送成功\n- 类型：图片\n- 路径：\u002Ftmp\u002Fbrowser-shot.png\n- 接收人：当前会话\n\nMEDIA:file:\u002F\u002F\u002Ftmp\u002Fbrowser-shot.png\n```\n\n### Example: document request\n\nFinal reply:\n\n```text\n发送成功\n- 类型：文件\n- 路径：\u002FUsers\u002Fexample\u002FDesktop\u002Freport.pdf\n- 接收人：当前会话\n\nMEDIA:file:\u002F\u002F\u002FUsers\u002Fexample\u002FDesktop\u002Freport.pdf\n```\n\n## Resources\n\n- Use `scripts\u002Femit_media_reply.py` to validate a path and build `reply_text`.\n- Use `scripts\u002Fweixin_debug_send.js` to collect failure diagnostics.\n- See `references\u002Fopenclaw-weixin-notes.md` for compatibility notes.\n","# Wechat Sendmedia\n\nUse this skill only for the `openclaw-weixin` channel.\n\n## Core rule\n\nFor outbound media, prefer the **plain-text MEDIA token** format, not a JSON envelope.\n\nReturn the final assistant message as plain text like this:\n\n```text\n发送成功\n- 类型：图片 | 文件\n- 路径：\u003Cabsolute path>\n- 接收人：当前会话 | \u003Crecipient>\n\nMEDIA:file:\u002F\u002F\u002Fabsolute\u002Fpath\u002Fto\u002Ffile.png\n```\n\nWhy: newer OpenClaw gateway builds parse media only from text directives such as `MEDIA:file:\u002F\u002F\u002F...`. If you return JSON like `{ \"mediaUrl\": \"file:\u002F\u002F\u002F...\" }`, the gateway may forward that JSON as plain text and no image\u002Ffile will be delivered.\n\n## Never do this\n\nDo not rely on these formats as the primary output:\n\n```json\n{\n  \"text\": \"这是你要的图片\",\n  \"mediaUrl\": \"file:\u002F\u002F\u002Ftmp\u002Fx.png\"\n}\n```\n\nor:\n\n```json\n{\n  \"text\": \"...\",\n  \"mediaUrl\": \"MEDIA:file:\u002F\u002F\u002Ftmp\u002Fx.png\"\n}\n```\n\nThese may be displayed to the user as literal text.\n\n## Supported tasks\n\nHandle these tasks:\n\n- Send a local image file to WeChat.\n- Take a browser or desktop screenshot, then send it.\n- Send a non-image file such as a PDF, text file, archive, or document.\n- Send to the current conversation by default.\n- Send to a specific recipient only if the user explicitly provides one.\n- Return `发送成功` or `发送失败` plus actionable diagnostics.\n\n## Inputs\n\nInterpret the request into:\n\n- `file_path`: absolute local path to an existing file, or a screenshot path produced earlier.\n- `recipient`: optional. Default `当前会话`.\n- `caption`: optional short note for the human-readable confirmation text.\n- `source_kind`: `image` or `file`.\n\nIf the user asks for a screenshot first, obtain the screenshot file before sending.\n\n## Output contract\n\n### Success outcome\n\nReturn plain text only:\n\n```text\n发送成功\n- 类型：图片\n- 路径：\u002Ftmp\u002Fbrowser-shot.png\n- 接收人：当前会话\n\nMEDIA:file:\u002F\u002F\u002Ftmp\u002Fbrowser-shot.png\n```\n\nRules:\n\n- The `MEDIA:file:\u002F\u002F...` directive must be on its own line.\n- Use an absolute local path.\n- Use `图片` for common image types and `文件` for everything else.\n- Keep the confirmation short.\n- Do not wrap the final reply in JSON unless the host explicitly requires JSON. For current OpenClaw builds, plain text is the safe default.\n\n### Failure outcome\n\nReturn:\n\n```text\n发送失败\n- 可能原因：\u003Cone line summary>\n- 建议：\u003Cnext step>\n\n调试信息:\n- file_path: \u003Cpath>\n- exists: true|false\n- recipient: \u003Crecipient>\n- upload_url: \u003Cvalue or n\u002Fa>\n- upload_url_host: \u003Cvalue or n\u002Fa>\n- encrypted_param_length: \u003Cnumber or 0>\n- sendmessage_status: \u003Cvalue or n\u002Fa>\n- sendmessage_response: \u003Craw text or n\u002Fa>\n- context_token_present: true|false\n- media_type_guess: image|file|unknown\n```\n\n## Workflow\n\n1. Resolve the user's intent.\n2. Ensure the target file exists.\n3. Run `scripts\u002Femit_media_reply.py` to validate the file and build the plain-text reply payload.\n4. Return the script's `reply_text` value as the assistant message.\n5. If a send attempt fails or the user reports a failed send, run `scripts\u002Fweixin_debug_send.js` to produce targeted diagnostics.\n6. Summarize the result in Chinese.\n\n## File-type decision rules\n\nTreat these as images by default:\n\n- `.png`, `.jpg`, `.jpeg`, `.gif`, `.webp`, `.bmp`\n\nTreat everything else as files.\n\n## Recipient rules\n\n- If the user says `发给我` and the current task came from WeChat, use `当前会话`.\n- Only override the recipient if the user explicitly names another receiver.\n- If a concrete user id is unavailable, keep `recipient` as `当前会话` in the confirmation text and let the host runtime map it to the current chat.\n\n## Troubleshooting rules\n\nWhen debugging an OpenClaw WeChat media failure, prefer concrete evidence over guesses.\n\nCommon causes to mention only when supported by the debug output:\n\n- File path does not exist.\n- Host runtime treated the reply as plain text because no `MEDIA:` token was present.\n- Missing context token for the current chat.\n- Upload URL not returned.\n- `x-encrypted-param` missing or unexpectedly short.\n- `sendmessage` returned empty body or non-success JSON.\n- Token\u002Fsession mismatch between runtime state and on-disk account data.\n- Wrong route used: JSON envelope or slash command text instead of `MEDIA:file:\u002F\u002F...`.\n\n## Examples\n\n### Example: screenshot request\n\nFinal reply:\n\n```text\n发送成功\n- 类型：图片\n- 路径：\u002Ftmp\u002Fbrowser-shot.png\n- 接收人：当前会话\n\nMEDIA:file:\u002F\u002F\u002Ftmp\u002Fbrowser-shot.png\n```\n\n### Example: document request\n\nFinal reply:\n\n```text\n发送成功\n- 类型：文件\n- 路径：\u002FUsers\u002Fexample\u002FDesktop\u002Freport.pdf\n- 接收人：当前会话\n\nMEDIA:file:\u002F\u002F\u002FUsers\u002Fexample\u002FDesktop\u002Freport.pdf\n```\n\n## Resources\n\n- Use `scripts\u002Femit_media_reply.py` to validate a path and build `reply_text`.\n- Use `scripts\u002Fweixin_debug_send.js` to collect failure diagnostics.\n- See `references\u002Fopenclaw-weixin-notes.md` for compatibility notes.\n",{"name":5,"description":7},"master","4aa004da461d820f4ea5499e58eb8d196cf99016","community\u002Fclawhub\u002Fw\u002Fwechat-sendmedia",0,"https:\u002F\u002Fgithub.com\u002FLord1Egypt\u002Fawesome-skill-forge","https:\u002F\u002Fskill-explorer-rho.vercel.app","https:\u002F\u002Fgithub.com\u002FLord1Egypt","Unbreakable. Unstoppable. Unmatched⚡.\r\n Speaker of machine tongues 🤖  | World-builder of decentralized dreams 🌐 | Defender of the digital realm🛡️.","2026-06-10 08:21:01",{"source":8,"skillName":5,"commands":34,"prompt":44,"zipAvailable":45},[35,38,41],{"tool":36,"command":37},"npx","npx skills add Lord1Egypt\u002Fawesome-skill-forge --skill wechat-sendmedia",{"tool":39,"command":40},"bunx","bunx skills add Lord1Egypt\u002Fawesome-skill-forge --skill wechat-sendmedia",{"tool":42,"command":43},"pnpm","pnpm dlx skills add Lord1Egypt\u002Fawesome-skill-forge --skill wechat-sendmedia","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FLord1Egypt\u002Fawesome-skill-forge\u002Fblob\u002Fmaster\u002Fcommunity\u002Fclawhub\u002Fw\u002Fwechat-sendmedia\u002FSKILL.md",true,[],[48,55,62,69,76,83],{"skillNo":49,"name":50,"nameZh":6,"description":51,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":52,"categories":53,"keywords":54,"publishedAt":19},"01M785WKJB99G3STR1NF9NRTJW","youtube-content","YouTube transcripts to summaries, threads, blogs.","https:\u002F\u002Fgithub.com\u002FLord1Egypt\u002Fawesome-skill-forge\u002Fblob\u002Fmaster\u002Fskills\u002Fyoutube-content\u002FSKILL.md",[],[],{"skillNo":56,"name":57,"nameZh":6,"description":58,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":59,"categories":60,"keywords":61,"publishedAt":19},"01M785WEFHB0G2S9YA6EPR3H0E","xurl","X\u002FTwitter via xurl CLI: post, search, DM, media, v2 API.","https:\u002F\u002Fgithub.com\u002FLord1Egypt\u002Fawesome-skill-forge\u002Fblob\u002Fmaster\u002Fskills\u002Fxurl\u002FSKILL.md",[],[],{"skillNo":63,"name":64,"nameZh":6,"description":65,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":66,"categories":67,"keywords":68,"publishedAt":19},"01M785W98EDN4EFJXJPMQEHCRC","touchdesigner-mcp","Control a running TouchDesigner instance via twozero MCP — create operators, set parameters, wire connections, execute Python, build real-time visuals. 36 native tools.","https:\u002F\u002Fgithub.com\u002FLord1Egypt\u002Fawesome-skill-forge\u002Fblob\u002Fmaster\u002Fskills\u002Ftouchdesigner-mcp\u002FSKILL.md",[],[],{"skillNo":70,"name":71,"nameZh":6,"description":72,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":73,"categories":74,"keywords":75,"publishedAt":19},"01M785W5S9FP3QBH2V191E025P","test-driven-development","TDD: enforce RED-GREEN-REFACTOR, tests before code.","https:\u002F\u002Fgithub.com\u002FLord1Egypt\u002Fawesome-skill-forge\u002Fblob\u002Fmaster\u002Fskills\u002Ftest-driven-development\u002FSKILL.md",[],[],{"skillNo":77,"name":78,"nameZh":6,"description":79,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":80,"categories":81,"keywords":82,"publishedAt":19},"01M785W2AS08NSSH9YATCV6FJB","teams-meeting-pipeline","Operate the Teams meeting summary pipeline via Hermes CLI — summarize meetings, inspect pipeline status, replay jobs, manage Microsoft Graph subscriptions.","https:\u002F\u002Fgithub.com\u002FLord1Egypt\u002Fawesome-skill-forge\u002Fblob\u002Fmaster\u002Fskills\u002Fteams-meeting-pipeline\u002FSKILL.md",[],[],{"skillNo":84,"name":85,"nameZh":6,"description":86,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":87,"categories":88,"keywords":89,"publishedAt":19},"01M785VXKW4T34BTP1SCHW1R7F","systematic-debugging","4-phase root cause debugging: understand bugs before fixing.","https:\u002F\u002Fgithub.com\u002FLord1Egypt\u002Fawesome-skill-forge\u002Fblob\u002Fmaster\u002Fskills\u002Fsystematic-debugging\u002FSKILL.md",[],[]]