文本提及网络访问
2 次命中此源文件行包含 URL 或网络客户端。应检查目标地址、发送的数据和信任边界;静态文本无法证明实际发生了网络活动。 该规则在收集文本中命中 2 处;此处列出 2 个代表位置。命中文本可能只是文档,分析器没有执行它。
技能研究档案
After you give a substantive answer or draft that the user may act on — advice or recommendations, drafted artifacts such as goals, plans, pitches, proposals, or emails, estimates or projections, analysis or interpretation of data, factual claims they may rely on, or a multi-step argument — invoke this skill BEFORE finalizing your reply and then, if it applies, append 2-3 short follow-up questions, each tied to something specific in what you just produced, that help the user check key facts, probe the reasoning or assumptions, and notice missing context. Do this at most once per conversation. Skip it when the user asked a trivial how-to or simple lookup, wants a purely educational explanation, asked you only to format, convert, or assemble a file from content they provided, is writing code they will run, is doing creative writing or casual chat, or already asked you to double-check, cite, or review — the skill file explains these boundaries and the exact output format.
After you give a substantive answer or draft that the user may act on — advice or recommendations, drafted artifacts such as goals, plans, pitches, proposals, or emails, estimates or projections, analysis or interpretation of data, factual claims they may rely on, or a multi-step argument — invoke this skill BEFORE finalizing your reply and then, if it applies, append 2-3 short follow-up questions, each tied to something specific in what you just produced, that help the user check key facts, probe the reasoning or assumptions, and notice missing context. Do this at most once per conversation. Skip it when the user asked a trivial how-to or simple lookup, wants a purely educational explanation, asked you only to format, convert, or assemble a file from content they provided, is writing code they will run, is doing creative writing or casual chat, or already asked you to double-check, cite, or review — the skill file explains these boundaries and the exact output format.
Skill Atlas editorial review · editorial-preview-1.0.0
discernment-nudge 是一个以固定源码快照收录的 Claude Code Skill。本编辑预览总结其声明用途、文件结构和可复核的风险线索;它不是受控任务评估。
对所收集的 SKILL.md 及辅助文本/代码进行确定性静态分析。机器辅助候选和发现等待人工编辑复核;不评估动态行为或效果。
文件清单来自记录提交中的采集源码。路径与大小属于结构观察,不代表质量评价。
skills/discernment-nudge/LICENSE.txt引用11.1 KBskills/discernment-nudge/SKILL.md指令10.3 KB{
"name": "discernment-nudge",
"description": "After you give a substantive answer or draft that the user may act on — advice or recommendations, drafted artifacts such as goals, plans, pitches, proposals, or emails, estimates or projections, analysis or interpretation of data, factual claims they may rely on, or a multi-step argument — invoke this skill BEFORE finalizing your reply and then, if it applies, append 2-3 short follow-up questions, each tied to something specific in what you just produced, that help the user check key facts, probe the reasoning or assumptions, and notice missing context. Do this at most once per conversation. Skip it when the user asked a trivial how-to or simple lookup, wants a purely educational explanation, asked you only to format, convert, or assemble a file from content they provided, is writing code they will run, is doing creative writing or casual chat, or already asked you to double-check, cite, or review — the skill file explains these boundaries and the exact output format.\n",
"license": "Complete terms in LICENSE.txt"
}此工作流根据源码材料重建表面顺序。除非明确记录受控评估,否则它属于暂定解读,而非真实运行轨迹。
阅读触发条件,判断该 Skill 是否匹配当前任务。
选中 Skill 后,Claude Code 读取完整 SKILL.md。
仅在文档流程需要时读取参考资料或运行脚本。
产出请求的交付物,并按来源描述的验收标准进行验证。
静态发现用于提示安装前需要检查的位置,不能证明一项技能安全、恶意或有效。
收集的文本中有 2 项确定性词法发现需要复核。发现可能仅位于文档中,不证明已执行或可被利用;仅含二进制的文件未扫描。
此源文件行包含 URL 或网络客户端。应检查目标地址、发送的数据和信任边界;静态文本无法证明实际发生了网络活动。 该规则在收集文本中命中 2 处;此处列出 2 个代表位置。命中文本可能只是文档,分析器没有执行它。
安装前应复核源码证据与运行时权限。
发现、激活与资源层具有不同含义。只有使用指定官方方法并记录模型的运行时,才显示精确数值。
在管线使用明确模型执行官方精确计数之前,包括文件清单在内的所有 token 值均为 null。
未使用要求的官方方法记录 token 测量。本档案不会用字符数、文件大小或估计值替代。
该技能仅具备以上标明的证据。不声称任何任务成功率、token 效率、延迟或质量优势。
/plugin marketplace add anthropics/skills
/plugin install example-skills@anthropic-agent-skills在 Claude Code 中确认该 Skill 出现在已安装列表中,然后运行下方代表性提示词。
Use the discernment-nudge skill to help with this task. First summarize what the skill will do, then execute its documented workflow and show the source-linked evidence for each major decision.
Read the discernment-nudge skill files at https://github.com/anthropics/skills/tree/e4bb5d960d87126ff3b3a8af1a104b7db67560ba/skills/discernment-nudge/SKILL.md. Explain its workflow, required tools, permissions and the main risks before I decide whether to install it.
研究结论编辑预览:本档案具备完整研究版式;受控评估将在部署后另行安排。
档案是对公开工件的限时阅读,而非背书。请通过来源链接检查确切的上游材料。
e4bb5d960d87126ff3b3a8af1a104b7db67560ba仅对提供的文件进行确定性词法解析、YAML frontmatter 校验、文件清单、来源描述的工作流程提取和启发式暂定分类。由机器生成;无 LLM、执行、动态测试或人工编辑批准。