菜单
Explains a visible chart by identifying axes, trends, outliers, and the practical takeaway while flagging missing context. Use when the user shares a chart, graph, plot, or data visualization — bar, line, pie, scatter — and asks what it shows, means, or whether the data supports a decision.
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
基于 SOC 职业分类
Answers a question grounded in the selected text or visible page, researching further when the page falls short, always evidence-backed and never invented. Use when the user highlights a passage or is on a page and asks "what does this mean", "answer this", "where does it say", or any who/what/why/how question about that content.
Turns REST API documentation into a runnable curl, fetch, or code example with required headers, request body, and placeholders for secrets. Use when the user wants to generate a request from API docs, an endpoint, or a Swagger/OpenAPI spec — "give me a curl for this", "show a fetch example", "how do I call this API".
Translates selected text and explains the idioms, cultural nuance, key terms, and phrasing that should not be read literally. Use when the user says "translate this", "in Spanish/French/Japanese/etc.", "what does this mean", "explain this phrase", or wants foreign-language text rendered with the context behind it.
Turns an event page, calendar invite, email, or notes into key details, an agenda, a preparation checklist, and follow-up reminders. Use when the user wants to prepare for a meeting, event, or appointment, or asks for meeting prep, an agenda, or a prep checklist before an upcoming event.
Writes captions, accessibility alt text, and short image or page descriptions tailored to the visible content and audience. Use when the user asks to "describe this image", "write alt text", "caption this", or needs screen reader text, a11y descriptions, image descriptions, or social captions.
Converts a code snippet from one programming language to another while preserving behavior and flagging library, runtime, and type-system differences. Use when the user asks to translate, port, rewrite, or convert code between languages — "port this to Python", "rewrite in Rust", "convert Java to Go".
| name | chart-explainer |
| description | Explains a visible chart by identifying axes, trends, outliers, and the practical takeaway while flagging missing context. Use when the user shares a chart, graph, plot, or data visualization — bar, line, pie, scatter — and asks what it shows, means, or whether the data supports a decision. |
| author | surfmind |
| metadata | {"icon":"ChartNoAxesCombined","tags":["data","research"]} |
Explain the chart, graph, or plot the way a careful analyst would — what the axes measure, the trend and its size, the outliers, and the one takeaway that answers the user's likely question. Work only from what's visible in the chart, the user's selected text, or tool results; don't infer exact numbers you can't read off the chart, and don't treat a correlation as a cause.
Return concise headings and include these sections when they fit: What the chart shows, Main takeaway, Notable details, Caveats, Questions to verify. Preserve important names, numbers, links, dates, and currencies. Be specific but don't overclaim; if the visible context is insufficient, say what's missing and give the best supported next step. Respond in the same language as the user's request.
Chart (a line chart titled "Monthly active users"):
X-axis: Jan–Dec 2025. Y-axis: MAU in thousands, starting at 80, not 0. One line rising from ~120k in Jan to ~180k in Dec, with a dip to ~110k in July. No source or sample note.
Explanation:
What the chart shows: Monthly active users across 2025, climbing from ~120k to ~180k — about a 50% gain over the year.
Main takeaway: Steady growth, but the trend isn't smooth; one sharp mid-year drop interrupts it.
Notable details: July dips to ~110k — the lone outlier, roughly a 40% fall before recovering. The Y-axis starts at 80k, not 0, which visually exaggerates the slope.
Caveats: No source, definition of "active," or sample size is shown, so the absolute numbers can't be verified. The truncated axis overstates the gain at a glance.
Questions to verify: What caused the July drop (outage, seasonality, tracking change)? How is "active" defined, and is the data first-party?
