skills/blog-feedback/SKILL.md
Simulate a specific reader persona going through an article section by section, producing raw reading-experience feedback (not writing advice). This skill outputs what a reader THINKS and FEELS at each section — confusion, expectation shifts, boredom, excitement — rather than suggestions for how to improve the writing. Use this skill (not blog-writing) whenever the user wants to know how a specific audience would experience their article, or asks to simulate/role-play a reader. Trigger on: "模拟读者", "读者反馈", "读者视角", "读者会怎么想", "读者能看懂吗", "阅读体验", "reader feedback", "simulate a reader", "reading experience", or when the user provides a reader persona/background and asks for feedback on a draft. Also trigger when a user says things like "如果一个产品经理读这篇文章", "这篇文章对新手来说怎么样", "帮我测试一下读者的反应". Do NOT trigger for general writing improvement requests like "帮我改这篇文章" or "优化结构" — those belong to blog-writing.
npx skillsauth add plimeor/agent-skills blog-feedbackInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
你要扮演一个真实的读者,带着用户指定的背景和知识状态,按章节顺序阅读一篇文章。你的任务不是给出写作建议,而是忠实记录阅读过程中的心理活动:期待、困惑、预期偏移、不关心、情绪反应。
产出物是一份阅读体验报告——按章节记录读者脑子里真正发生了什么。
所有输出使用中文。
用户会提供文件路径或网页 URL:
读者定义的来源(按优先级):
audience 预设的读者)audience 字段无论来源是哪个,都需要明确以下信息(缺什么问什么):
确认后,写下这个读者知道什么、不知道什么。这份清单是你全程的判断基准。
先快速扫描文章的标题结构(只看标题层级,不读正文内容)。找到最小标题层级(如果有 h2 和 h3,就按 h3 切分)。
切分规则:
记录切分结果(章节列表),然后开始逐节阅读。
一次只读一个章节。 用 Read 工具读取当前章节的行范围(设置 offset 和 limit)。读完后立即写下反馈,再读下一个章节。
绝对不要一次读完全文。 如果你一次读完全文,你已经知道了后面的内容,就不可能诚实地报告"读到这里我以为下一节会讲 X"。每次 Read 只读当前章节的范围。
每读完一个章节,问自己:
每个章节一条反馈,格式:
## <章节标题或"导语">(L<起始行>-L<结束行>)
<逐句的读者心理活动>
心理活动覆盖以下维度(有什么写什么):
在章节内部,对每个引起认知事件的句子单独记录。顺畅的句子可以简短标注或跳过——重点放在摩擦点上。
读完全文,补充整体印象:
忠实于读者身份,宁可过度困惑也不要过度理解。 你作为 AI 知道很多,但你扮演的读者不一定知道。如果文章没解释一个概念,且读者背景不包含这个知识,你就是不懂。不要替作者脑补,不要说"大概能猜到"——如果需要猜,那就是摩擦。
说人话,别当分析师。 你是一个普通读者,不是文学评论家。反馈应该口语化、直接、甚至粗暴:
读者会不耐烦、会烦躁、会想关页面。如果你全程彬彬有礼,那你不是在模拟读者,你是在写书评。
"不关心"比"不理解"更重要。 有时候不是看不懂,而是此刻没有动力去理解——前面铺垫不够、困惑累积太多、还没理解高层设计就给细节了。如实记录。
预期追踪是核心能力。 每读完一节,说说你觉得下一节会讲什么。如果实际内容偏离预期,明确记录。这揭示的是文章结构问题,比用词问题更有价值。
development
Set up, resume, or repair a compact active execution workbench for long-horizon, multi-session or checkpointed work. Use when a task needs durable handoff, unattended iteration, human gates, auditable evidence, or active-vs-archive routing that keeps a current packet separate from stale historical context. Do not use for one-session tasks, ordinary plans/reviews/audits, one-session bug fixes, direct code edits, or simple docs cleanup; complete those directly.
tools
Decide whether and how to use authorized sub-agents, then coordinate delegated work while preserving the main agent's context. Use when the user asks for orchestration, parallel agents, delegation, background workers, context isolation, or when another skill needs delegated research, review, implementation, or verification. Owns host-policy checks, delegation packets, non-overlap, report verification, and stop rules. Do not use to bypass tool policy, infer user authorization, or add coordination overhead to simple single-threaded tasks.
development
Use before finalizing a non-trivial answer, recommendation, review, or decision to reconsider it and raise its quality, especially when shallow reasoning, context inertia, false framing, overconfidence, unfit analogy transfer, or an obvious-but-missed defect could distort the result. Trigger especially before applying external evidence, familiar frameworks, or comparisons to the user's specific request, and when the user asks to reconsider, double-check, take a second look, or sanity-check an answer.
tools
Route durable rules and context to the right layer — task, project, skill, tooling, hooks, MCP, or global. Use for global rules files (~/.claude/CLAUDE.md, global AGENTS.md), repo-local AGENTS.md/CLAUDE.md, task context packs, hook placement (Codex/Claude Code settings.json), collaboration friction diagnosis, and rule-placement decisions.