|
npx skills add https://github.com/jackbauerxu/workbuddy-xhs-skills --skill wb-xhs-account-profile
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 Check the current version, automatically install or update a missing or outdated dependency to the latest stable supported version, run its diagnostic, and only then continue.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.
> "让它认识你。"
>
> — 文子, X Article, 2026-07-06
> "早期内容垂直,中期人设垂直。"
>
> — yanliudreamer, X Article, 2026-06-07
> "从 0 到 1 万粉,本质是找到方向、建立标签、积累信任。"
>
> — 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
WorkBuddy 的价值不只是回答一次问题,而是长期协作。长期协作的前提是它知道账号是谁、说什么、不说什么、为什么可信、已经验证过什么。
账号档案要把定位、变现模式、人设语气、内容边界、已有数据和对标公式写成可读取文件。这样每次生成选题、标题、正文或复盘时,Agent 不必重新猜测用户身份。
yanliudreamer 系列补充了小红书的个人 IP 特性:用户关注的不只是观点,而是“这个人是谁、如何生活、为什么可信、我是否向往或认同”。因此账号档案不能只写内容赛道,还要写真实经历、信任资产、成长线、生活方式边界和人设延展规则。
一个好账号档案既是风格指南,也是边界文件、信任名片和运营日志。
dbskill 的内容和文风诊断补充了两个字段:个人语言样本、可信主张清单。前者记录用户真实会说的话、不会说的话、常用句式;后者记录用户能证明的观点、结果、案例和 offer。后续改稿、选题和复盘都应回到这两类资产。
xhs-visual-director-skill 补充了“视觉身份档案”:账号档案不仅要记住怎么说话,也要记住图文长什么样。视觉身份包括默认画幅、主风格、辅助风格、色彩令牌、字体令牌、封面规则、内页组件、禁用风格和视觉参考。
内容节奏文章进一步要求档案保存三类长期资产:方向资产(我持续解决什么问题)、标签资产(用户和平台如何记住我)、信任资产(我亲自经历过什么、能证明什么)。档案还应记录内容管线的输入、加工、库存与输出状态,让“稳定更新”来自可管理的系统,而不是每天等待灵感。
wb-xhs-monetization-backsolve 的区别: 定位 skill 产出方向,本 skill 把方向固化成记忆文件。wb-xhs-topic-bank 的区别: 本 skill 定义账号约束,选题库在这些约束内生产题目。main_topics、persona_extensions、secondary_account_candidates 和每个判断的“为什么仍然像同一个人”。direction_assets: 主赛道、持续解决的问题、不能随意漂移的内容边界。label_assets: 系列、固定栏目、核心主题词、稳定视觉和用户形成的记忆点。trust_assets: 真实经历、方法、失败复盘、作品/结果、评论区认可和可以公开的证据。input_slots、processing_slots、inventory_days、planned_outputs,让档案能支持排期,而不只是描述风格。账号档案.md,包含定位卡、方向/标签/信任资产、个人语言样本、可信主张、语气规则、视觉身份、禁区、内容栏目、对标公式、数据日志、内容管线和人设延展规则。10. 建立更新机制
用户没有提供定位也直接要求“给我账号档案/写入记忆”时,不要只退回收集流程。先输出 账号档案.md(可用草案):所有未知字段明确写 unknown,包含定位、目标用户、变现、可信资产、语言样本、可证明主张、内容规则、视觉身份和周更新机制;同时给出可复制的记忆写入指令。
若当前环境没有真实记忆写入能力,明确记录 memory_write_status: not_called,不能声称已经写入。草案可用,但未知项必须在后续确认后再替换。
Integration with protocols.io API for managing scientific protocols. This skill should be used when working with protocols.io to search, create, update, or publish protocols; manage protocol steps and materials; handle discussions and comments; organize workspaces; upload and manage files; or integrate protocols.io functionality into workflows. Applicable for protocol discovery, collaborative protocol development, experiment tracking, lab protocol management, and scientific documentation.
Analyzes job descriptions and generates tailored resumes that highlight relevant experience, skills, and achievements to maximize interview chances
Generate Excalidraw diagrams from natural language descriptions. Use when asked to "create a diagram", "make a flowchart", "visualize a process", "draw a system architecture", "create a mind map", or "generate an Excalidraw file". Supports flowcharts, relationship diagrams, mind maps, and system architecture diagrams. Outputs .excalidraw JSON files that can be opened directly in Excalidraw.
Build and distribute Expo development clients locally or via TestFlight
Use when you have a written implementation plan to execute in a separate session with review checkpoints
Data structure for annotated matrices in single-cell analysis. Use when working with .h5ad files or integrating with the scverse ecosystem. This is the data format skill—for analysis workflows use scanpy; for probabilistic models use scvi-tools; for population-scale queries use cellxgene-census.
Benchling R&D platform integration. Access registry (DNA, proteins), inventory, ELN entries, workflows via API, build Benchling Apps, query Data Warehouse, for lab data management automation.
Comprehensive molecular biology toolkit. Use for sequence manipulation, file parsing (FASTA/GenBank/PDB), phylogenetics, and programmatic NCBI/PubMed access (Bio.Entrez). Best for batch processing, custom bioinformatics pipelines, BLAST automation. For quick lookups use gget; for multi-service integration use bioservices.
Take jackbauerxu/wb-xhs-account-profile 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.