|
npx skills add https://github.com/jackbauerxu/workbuddy-xhs-skills --skill wb-xhs-schedule-review
Before using any external program, browser automation, package, API client, or local script, apply ../RUNTIME_UPDATE_POLICY.md. Check the current version, automatically install or update a missing or outdated dependency to the latest stable supported version, run its diagnostic, and only then continue. Text-only work needs no installation. Never use sudo or claim success without verification.
> "排期 + 复盘,让它帮你记。"
>
> — 文子, X Article, 2026-07-06
> "小红书前10条 = 系统画像建立期。"
>
> — yanliudreamer, X Article, 2026-06-29
> "内容节奏不是发得快,而是创作、储备、发布之间的配速。"
>
> — yanliudreamer, X Article《0基础小红书教程(下)|从0到1万粉:内容节奏怎么排?》, 2026-07-29
小红书冷启动不是单篇内容问题,而是连续发布和反馈问题。排期解决“今天发什么、什么时候发、发哪类”;复盘解决“数据说明了什么、下一周怎么改”。本 skill 还要先判断内容管线是否健康:有输入(素材)、有加工(选题/初稿/视觉 Brief)、有库存(可发布缓冲)、有输出(按阶段发布)。固定发帖频率不是目标,内容库存和反馈闭环才是。
文章建议把新号分成阶段:先让账号行为自然,再让平台识别标签,再逐渐稳定内容和商业转化。每周记录曝光、点击、点赞、收藏、评论、分享、涨粉等指标,并让 WorkBuddy 把结论写回记忆。
yanliudreamer 系列补充了冷启动实验节奏:前 10 条是系统画像建立期,建议组合自我背景/经历、方法/经验、踩坑/反思、情绪/观点;定位不要只靠想,而要用 10-20 条内容验证。复盘时不要只问“爆没爆”,而要判断系统是否认识你、哪类内容更容易被推荐、哪类内容更容易被互动和关注。
排期和复盘合在一起,才能把内容系统从灵感驱动变成数据驱动。
dbskill 的保存/恢复/报告思路可以转译成小红书运营记忆:每周不只产出排期,还要把“验证过的内容类型、禁用表达、评论区需求、下周实验假设”写回账号档案。这样下一轮不是重新开始,而是在上一轮证据上继续迭代。
xhs-visual-director-skill 补充了图文生产节奏:排期不只安排发什么,还要安排哪条做单图、哪条做 6-8 页图文、哪天出视觉确认图、哪天批量出最终图、哪周复盘封面点击和内页收藏。
本次新增的内容节奏模型见 content-rhythm-model.md。它把增长拆成“拉新 → 建立信任 → 强化标签”的循环,并用四个阶段的比例假设帮助排期:0–1000 试错,1000–5000 放大,5000–10000 建立系统,10000+ 形成飞轮。比例是起始实验,不是平台规则;每轮只根据真实数据调整少量变量。
wb-xhs-topic-bank 的区别: 选题库负责产生候选内容,本 skill 负责安排节奏和复盘数据。wb-xhs-humanize-compliance 的区别: 去 AI 味处理单篇发布质量,本 skill 处理多篇内容的周期表现。0–1000 试错、1000–5000 放大、5000–10000 系统化或 10000+ 飞轮阶段;同时为本轮内容标注主要任务:拉新、建立信任或强化标签。inventory_days < 7 时标记库存风险;< 3 时优先补库存、复用已验证主题或降低发布承诺,不把固定日更当成完成标准。input_slots、processing_slots、inventory_days、planned_outputs,并说明安全默认值或未知项。0–1000: 可从每周 5–7 条开始测试,起始比例 40% 经验/方法、30% 踩坑/反思、30% 观点/情绪;重点是找高反馈内容,不把数字写成硬规则。1000–5000: 找出表现最好的 3 条,起始比例 50% 已验证主题延伸、30% 同类优化、20% 新题测试;优先把有效结构做成系列。5000–10000: 起始比例 60% 主赛道、20% 爆款复刻优化、20% 轻测试;建立固定栏目、系列、公开过程、失败复盘和长期项目更新。10000+: 迭代爆款、固定栏目、评论区互动、合集/知识库和内容互相带流量,不强行套统一比例。ratio_hypothesis,并列出验证指标与调整条件。10. 复盘增长循环并处理人设垂直
main_account_extension、secondary_account_candidate 和判断理由。11. 无灵感时启动兜底题
12. 生成周度运营报告
排期只在确认后交给视觉流程“生产日期、审核日期、已确认的发布形态和复盘约束”;如无此类信息,传递 constraints: []。不改派到变现定位,不输出 execution_mode、已选视觉专家、输出路径、持久化状态或未知字段。视觉路由器拥有这些运行时决策。
用户只要求 7 天、30 天或首 10 条排期时,select wb-xhs-schedule-review alone。可在排期中使用 [主题]、[人群] 等占位符和一个最小确认问题;不要为了补全占位符而同时调用选题库,也不改派到定位。
references/content-rhythm-model.md。Guide users through a structured workflow for co-authoring documentation. Use when user wants to write documentation, proposals, technical specs, decision docs, or similar structured content. This workflow helps users efficiently transfer context, refine content through iteration, and verify the doc works for readers. Trigger when user mentions writing docs, creating proposals, drafting specs, or similar documentation tasks.
Intelligently organizes your files and folders across your computer by understanding context, finding duplicates, suggesting better structures, and automating cleanup tasks. Reduces cognitive load and keeps your digital workspace tidy without manual effort.
Generates creative domain name ideas for your project and checks availability across multiple TLDs (.com, .io, .dev, .ai, etc.). Saves hours of brainstorming and manual checking.
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.
Implements Manus-style file-based planning for complex tasks. Creates task_plan.md, findings.md, and progress.md. Use when starting complex multi-step tasks, research projects, or any task requiring >5 tool calls.
Creative research ideation and exploration. Use for open-ended brainstorming sessions, exploring interdisciplinary connections, challenging assumptions, or identifying research gaps. Best for early-stage research planning when you do not have specific observations yet. For formulating testable hypotheses from data use hypothesis-generation.
Comprehensive GitHub project management with swarm-coordinated issue tracking, project board automation, and sprint planning
Interview the user relentlessly about a plan or design until reaching shared understanding, resolving each branch of the decision tree. Use when user wants to stress-test a plan, get grilled on their design, or mentions "grill me".
Take jackbauerxu/wb-xhs-schedule-review from the repository into ~/.claude/skills for personal
use, or into .claude/skills inside a project.
The agent identifies a skill by the name field in its header. Two skills with the
same name cannot sit side by side — one of them will be ignored.