english-evaluation
English Evaluation
Overview
Always reply in Chinese. Only if the user's message is fully in English, append a short Chinese evaluation and a numeric score.
Behavior Rules
- Answer the user's question in Chinese.
- Only when the user's message is fully in English (ignore punctuation, digits, emojis, whitespace), append a brief Chinese evaluation and a 1–10 score.
- Ignore media references for detection: if the message includes or mentions media files (especially images/videos), do not use media paths, file names, MIME/type labels, or upload status text as detection input.
- Chinese media file names must not block triggering: even when image/video file names contain Chinese, still allow this skill to trigger based on the user's typed text.
- Ignore URLs for detection: do not use URL strings as detection input; URLs containing Chinese must not block triggering.
- If the user's message is not fully in English, do not add any evaluation or score.
- Be strict and concise: prefer native-like, idiomatic phrasing; point out unnatural wording.
- Provide 1–3 specific improvement notes (micro-edits allowed; no full rewrite unless asked). If the score is below 9/10, also give a short, more natural alternative (1–2 sentences). If the score is 9/10 or higher, do not provide a rewrite.
English Detection
More from yanyang1116/skills
openclaw-channel-file-send
Send an existing local file to the current chat using OpenClaw's official media send API for the active channel. Use this whenever the user asks to send a file, deliver a local document, forward a local image, upload any existing file into the conversation, or uses casual phrasing like “发我”, “传给我”, “丢给我”, “send me the file”, or “send it over”. Prefer this skill even when the user does not mention APIs, channels, or media explicitly, as long as they want the file to actually arrive in the conversation. Do not use reply attachments or read-file attachments for this workflow.
7codex-deep-search
Deep web search using Codex CLI for complex queries that need multi-source synthesis. Use when web_search (Brave) returns insufficient results, when the user asks for in-depth research, comprehensive analysis, or says "deep search", "详细搜索", "帮我查一下", or when a topic needs following multiple links and cross-referencing sources.
6openclaw-channel-screenshot-send
Capture a fresh screenshot and send it into the current chat using OpenClaw's official media send API for the active channel. Use this whenever the user asks to screenshot the screen and send it, capture then send, send the current screen, send a screenshot here, upload the screen into chat, or uses casual phrasing like “发我截图”, “把屏幕发来”, “send it over”, or “丢到聊天里”. Prefer this skill even when the user does not mention APIs, channels, or media explicitly, as long as they want the screenshot to actually arrive in the conversation. Do not use read-image reply attachments for this workflow.
4openclaw-private-skills-manager
>
4openclaw-codex-deep-search
Deep web search using Codex CLI for complex queries that need multi-source synthesis. Use when web_search (Brave) returns insufficient results, when the user asks for in-depth research, comprehensive analysis, or says "deep search", "详细搜索", "帮我查一下", or when a topic needs following multiple links and cross-referencing sources.
3channel-file-send
Send an existing local file to the current chat using OpenClaw's official media send API for the active channel. Use this whenever the user asks to send a file, deliver a local document, forward a local image, upload any existing file into the conversation, or uses casual phrasing like “发我”, “传给我”, “丢给我”, “send me the file”, or “send it over”. Prefer this skill even when the user does not mention APIs, channels, or media explicitly, as long as they want the file to actually arrive in the conversation. Do not use reply attachments or read-file attachments for this workflow.
2