AGENT SKILL

wechat-article-writer

Project-level WeChat article drafting workflow for turning source materials, repo intakes, product notes, screenshots, or existing markdown into a publishable Chinese公众号 draft. Use for writing, rewriting, evidence-gating, title options, platform adaptation, and image planning before optional publishing.

License 许可
MIT
所属仓库
EthanYoQ/Skill-hub
最近更新
2026-11-07
Stars
★ 11
Forks
5

01 前言 Front Matter

name
wechat-article-writer
description
Project-level WeChat article drafting workflow for turning source materials, repo intakes, product notes, screenshots, or existing markdown into a publishable Chinese公众号 draft. Use for writing, rewriting, evidence-gating, title options, platform adaptation, and image planning before optional publishing.

02 资源文件 1

03 SKILL.md 正文

WeChat Article Writer

Use this skill for the writing part of the project. Use wechat-mp-writer when the user also wants intake automation or publishing.

Required Context

Read these project files when drafting from product or repo material:

  • docs/content-agent/workflow.md
  • docs/content-agent/agent-prompt.md
  • docs/content-agent/rules/writing-rules.md if present and relevant
  • The source ledger or intake summary for the current article

Drafting Flow

  1. Normalize inputs.
    • Identify source files, URLs, screenshots, README files, and user notes.
    • Ask focused questions only when a missing fact would materially change the article.
  2. Build evidence.
    • Maintain verified, reasonable inference, unverified, and do-not-publish labels.
    • Do not turn unverified hypotheses into factual claims.
  3. Choose article angle.
    • Prefer product-backed, concrete workplace or technical value.
    • Avoid generic "AI tool recommendation" framing unless the user explicitly wants it.
  4. Write a WeChat draft.
    • Start with a concrete scene, contradiction, or strong conclusion.
    • Keep paragraphs scannable without flattening depth.
    • Make the authorial "I" light and functional.
    • Use source-backed technical details and product decisions.
  5. Produce title options and visual plan.
    • Use wechat-title-strategist before selecting the final title.
    • Reject titles that are merely accurate but lack either depth or open-rate pull.
    • Avoid stale AI discourse ("别再写 Prompt", "Prompt 已死", generic "AI 时代来了") unless the article's evidence makes that phrasing newly valuable.
    • Use wechat-visual-director to create distinct cover/body visual routes.
    • Separate cover prompt from body illustration prompts.
    • Recommend screenshots where they carry more evidence than generated art.
  6. Run a final risk gate.
    • Remove secrets, private customer data, unverifiable superiority claims, and sensitive internal strategy.

Output Contract

Unless the user narrows the request, return or create:

  • Final WeChat title
  • Article markdown
  • Evidence notes for major claims
  • Cover direction
  • Body image plan
  • Self-review and remaining open questions

Do not publish from this skill directly; hand off to wechat-mp-writer or baoyu-post-to-wechat.

04 同仓库更多 Skills

EthanYoQ
EthanYoQ/Skill-hub

xhs-pharma-social-listening

Run evidence-disciplined Xiaohongshu social listening for foreign pharma employee pain points. Use when the user asks to collect and analyze notes/comments about pharma companies, aliases, roles, compliance, medical affairs, or AI topics, then produce a cited and scored sampled-insight report. Includes independent-evidence counting, MediaCrawler batch collection, and CAPTCHA/461 fallback to Agent Reach/OpenCLI.

Skill与智能体开发
★ 11
EthanYoQ
EthanYoQ/Skill-hub

healthcare-phi-compliance

Protected Health Information (PHI) and Personally Identifiable Information (PII) compliance patterns for healthcare applications. Covers data classification, access control, audit trails, encryption, and common leak vectors. Use when code touches PHI or PII in a healthcare system, or when auditing access control, audit trails, or leak vectors.

律师与法务Skill与智能体开发
★ 11
EthanYoQ
EthanYoQ/Skill-hub

healthcare-eval-harness

Patient safety evaluation harness for healthcare application deployments. Automated test suites for CDSS accuracy, PHI exposure, clinical workflow integrity, and integration compliance. Blocks deployments on safety failures. Use when a healthcare deployment must be gated on patient-safety tests for CDSS accuracy, PHI exposure, and workflow integrity.

Skill与智能体开发
★ 11
EthanYoQ
EthanYoQ/Skill-hub

healthcare-emr-patterns

EMR/EHR development patterns for healthcare applications. Clinical safety, encounter workflows, prescription generation, clinical decision support integration, and accessibility-first UI for medical data entry. Use when building EMR or EHR features such as encounter workflows, prescription generation, or clinical data entry UI.

Skill与智能体开发
★ 11
EthanYoQ
EthanYoQ/Skill-hub

healthcare-cdss-patterns

Clinical Decision Support System (CDSS) development patterns. Drug interaction checking, dose validation, clinical scoring (NEWS2, qSOFA), alert severity classification, and integration into EMR workflows. Use when building clinical decision support — drug interaction checks, dose validation, clinical scoring, or alert severity.

Skill与智能体开发
★ 11
EthanYoQ
EthanYoQ/Skill-hub

dxy-task-clarify

用户的请求含糊、缺背景、缺资料说明、缺读者或用途时使用。先用少量带选项的追问把任务问清楚,写成任务卡,用户确认后再执行。尤其适用于医生、科研人员和药企各岗位的工作,例如「帮我分析一下这些数据」「帮我准备明天的拜访」「写个总结」「做个 PPT」「回一下这封邮件」「整理一下会议纪要」「整理一下这些文献」「帮我准备下周的讲课」「写个病例汇报」「帮我写个提示词」。用户说「先问我」「帮我理清需求」「我不知道怎么描述」「我不会问 AI」时也使用。用途、资料、读者都已说清的请求,纯翻译,以及写代码、改代码,不使用。

Skill与智能体开发
★ 11