4 Lines You Should Include in Your Claude Skill
4 Lines You Should Include in Your Claude Skill
你应该在 Claude 技能中加入的 4 行指令
Agentic AI 4 Lines You Should Include in Your Claude Skill Without these, Claude might end up being confidently wrong. Haden Pelletier Jun 14, 2026 8 min read
代理式 AI：你应该在 Claude 技能中加入的 4 行指令。如果没有这些，Claude 可能会表现得“自信地胡说八道”。作者：Haden Pelletier，2026 年 6 月 14 日，阅读时长 8 分钟。
A few weeks ago I was asked to do something new at work: Given a data dump of unstructured text data, give us a detailed PDF report of insights about what customers are saying about our products this quarter. So I wrote a clear prompt. Gave Claude a detailed set of instructions. Fed it the dataset. It gave me an output. I delivered it. But when the stakeholder and I reviewed the deliverable in depth, we noticed some increasingly unsettling things. Claude was confidently wrong.
几周前，我在工作中接到了一项新任务：根据一堆非结构化文本数据，提供一份详细的 PDF 报告，分析本季度客户对我们产品的评价。于是，我写了一个清晰的提示词，给 Claude 下达了详细的指令，并喂给了它数据集。它输出了结果，我提交了报告。但当我和利益相关者深入审查交付成果时，我们注意到了一些令人不安的情况：Claude 在“自信地胡说八道”。
Not wrong wrong, like hallucinating facts from nowhere. More like… overconfident wrong. It would generate a quarterly insight report and say something like: “Negative sentiment in the Dresses department increased 23% this quarter, indicating a significant shift in customer satisfaction that warrants immediate attention from the product team.” Sounds great. Except that spike was driven almost entirely by a single popular item that launched mid-quarter with a known sizing defect. One product. Not the whole department. Claude had no idea. And my prompt didn’t tell it to care.
这并非那种凭空捏造事实的错误，更像是……过度自信的错误。它会生成一份季度洞察报告，写道：“本季度连衣裙部门的负面情绪增加了 23%，这表明客户满意度发生了重大变化，需要产品团队立即关注。”听起来很棒，但问题在于，这个激增几乎完全是由一款在季度中期发布且存在已知尺码缺陷的热门商品引起的。仅仅是一个产品，而不是整个部门。Claude 对此一无所知，而我的提示词也没有要求它去关注这一点。
A Quarterly Customer Review Report Skill I’m going to walk you through a Claude skill I built that generates a quarterly customer sentiment report from unstructured product review text, delivered as a PDF to stakeholders. Obviously, I won’t be sharing the actual dataset I analyzed at work. The dataset I’m using is the Women’s E-Commerce Clothing Reviews dataset from Kaggle (CC0 license). It contains 23,000 real, anonymized customer reviews across clothing departments (Tops, Dresses, Bottoms, Jackets, and more) with text, star ratings, and product metadata. References to the company in the reviews have been replaced with “retailer.”
“季度客户评论报告”技能：我将带你了解我构建的一个 Claude 技能，它能从非结构化的产品评论文本中生成季度客户情绪报告，并以 PDF 形式交付给利益相关者。显然，我不会分享我在工作中分析的实际数据集。我使用的数据集是来自 Kaggle 的“女性电子商务服装评论”数据集（CC0 许可）。它包含 23,000 条真实的、匿名的客户评论，涵盖了各个服装部门（上衣、连衣裙、下装、夹克等），并附有文本、星级评分和产品元数据。评论中对公司的引用已被替换为“零售商”。
The skill should: Read a filtered slice of reviews for the current quarter, Group them by department, Identify trends & concerns, Write a professional summary PDF for the product leadership team.
该技能应实现：读取本季度筛选后的评论片段，按部门进行分组，识别趋势与关注点，并为产品领导团队撰写一份专业的 PDF 总结报告。
Here’s the original prompt: You are a data analyst generating a quarterly customer sentiment report for a women’s clothing e-commerce retailer. Given this quarter’s customer reviews (including review text, star ratings, and department), write a professional stakeholder report that includes: – An overall sentiment summary for the quarter – Key themes by department (Tops, Dresses, Bottoms, Jackets) – 2-3 standout insights from the review text – A brief recommendation for the product team. Be professional and clear. When you’re done with this task, please create a skill titled reviews-analysis and save your instructions in there.
这是最初的提示词：你是一名数据分析师，正在为一家女性服装电商零售商生成季度客户情绪报告。根据本季度的客户评论（包括评论文本、星级评分和部门），撰写一份专业的利益相关者报告，内容包括：——本季度的整体情绪总结；——各部门（上衣、连衣裙、下装、夹克）的关键主题；——从评论文本中提取的 2-3 个突出洞察；——给产品团队的简要建议。请保持专业和清晰。完成此任务后，请创建一个名为“reviews-analysis”的技能，并将你的指令保存在其中。
What “Confidently Wrong” Actually Looks Like: Here’s an example of what Claude produced with the naive skill above, on a quarter where the Dresses department had an influx of negative reviews: “Negative sentiment in the Dresses department increased significantly this quarter, with customers frequently citing fit and sizing issues. This suggests the retailer’s sizing standards may be drifting from customer expectations — a trend that, if unaddressed, could erode brand loyalty in this key category.”
什么是“自信地胡说八道”：以下是 Claude 使用上述简单技能在连衣裙部门出现大量负面评论的季度所生成的内容示例：“本季度连衣裙部门的负面情绪显著增加，客户频繁提到合身和尺码问题。这表明零售商的尺码标准可能偏离了客户的期望——如果这一趋势得不到解决，可能会削弱该关键类别中的品牌忠诚度。”
The real explanation? One dress (a single SKU) launched in Week 7 with a batch quality issue. The reviews were almost entirely about that one item. The rest of the Dresses department was performing fine. Claude didn’t necessarily invent anything. It just had no context for why the pattern existed. And without that context, it did what LLMs do: it filled the gap with the most plausible-sounding narrative.
真正的原因是什么？第七周推出的一款连衣裙（单一 SKU）存在批次质量问题。评论几乎全部针对那一件商品。连衣裙部门的其他产品表现良好。Claude 并没有凭空捏造，它只是缺乏关于这种模式为何存在的背景信息。而在缺乏背景的情况下，它做了大模型擅长的事：用最听起来合理的叙述填补了空白。
The Fix: 4 Lines You MUST Include. Line 1: Tell Claude What Context It’s Missing. You do NOT have access to product launch calendars, inventory records, promotional campaigns, or individual SKU-level history. Do NOT attribute department-level trends to brand-wide causes. Report patterns you observe in the text; do not explain why they exist unless the reviews themselves make it unambiguous.
解决方案：你必须加入的 4 行指令。第 1 行：告诉 Claude 它缺失了什么背景信息。你无法访问产品发布日历、库存记录、促销活动或单个 SKU 级别的历史记录。不要将部门级别的趋势归因于品牌层面的原因。报告你在文本中观察到的模式；除非评论本身明确说明，否则不要解释它们存在的原因。
This single instruction eliminates a huge category of confident wrongness. Without it, Claude will always reach for a strategic narrative because that’s what a good analyst does, and Claude is trying to be a good analyst. The problem is that a good analyst also knows what they don’t know. They say “We’re seeing elevated sizing complaints in Dresses this quarter. This may be isolated to a recent launch but we’d need SKU-level data to confirm.” Claude won’t say that unless you tell it to.
这一条指令消除了很大一部分“自信的错误”。如果没有它，Claude 总是会试图构建一个战略性的叙述，因为这是优秀分析师的做法，而 Claude 正试图成为一名优秀的分析师。问题在于，优秀的分析师也知道自己不知道什么。他们会说：“我们看到本季度连衣裙部门的尺码投诉有所增加。这可能是近期某次发布导致的孤立事件，但我们需要 SKU 级别的数据来确认。”除非你明确要求，否则 Claude 不会这样说。
Line 2: Define What “Significant” Actually Means. Claude loves the word “significant.” It uses it all the time. And it almost never defines it. Only flag a sentiment shift as “significant” if it represents a change of more than 15 percentage points in positive/negative ratio compared to the prior quarter, OR if a theme appears in more than 20% of reviews in a given department. For smaller signals, use language like “slight uptick” or “minor increase.” Do not use the word “notable” or “significant” for anything below these thresholds. Always report the actual number value for the shift along with your claim.
第 2 行：定义“显著”的真正含义。Claude 很喜欢“显著”这个词，它经常使用，却几乎从不定义它。只有当情绪变化与上一季度相比，正负比例变化超过 15 个百分点，或者某个主题在特定部门的评论中出现超过 20% 时，才将其标记为“显著”。对于较小的信号，请使用“轻微上升”或“小幅增加”等词汇。对于低于这些阈值的情况，不要使用“值得注意”或“显著”等词。在提出主张时，务必报告变化的实际数值。
You can adjust the 15% and 20% thresholds to whatever makes sense for your data. The point is to anchor Claude’s language to something real. Without this, Claude will call both a 3-review spike in complaints and a genuine 30-point sentiment drop “significant”. Your stakeholders will start to tune out. And when something actually significant happens, they won’t know it.
你可以根据数据的实际情况调整 15% 和 20% 的阈值。关键在于将 Claude 的语言锚定在真实的事物上。如果没有这一点，Claude 会把 3 条投诉的激增和 30 个百分点的真实情绪下降都称为“显著”。你的利益相关者会开始不再关注，当真正重要的事情发生时，他们反而会忽略。
Line 3: Force a Confidence Qualifier on Every Insight. Before each insight, include a confidence label in brackets: [Data-Supported], [Possible], or [Speculative]. Use [Data-Supported] only when the insight follows directly from the review text provided. Use [Possible] when the insight is a reasonable inference from the text. Use [Speculative] when you are making assumptions about causes or context that are not present in the review.
第 3 行：强制要求对每个洞察进行置信度标注。在每个洞察之前，加上括号内的置信度标签：[数据支持]、[可能] 或 [推测]。仅当洞察直接源自提供的评论文本时，使用 [数据支持]；当洞察是基于文本的合理推断时，使用 [可能]；当你对评论中未提及的原因或背景进行假设时，使用 [推测]。