本文へ移動
cccskills
無料GitHub で公開

wechat-mp-writer

Project-level workflow for turning GitHub repositories, URLs, local product materials, or markdown drafts into WeChat Official Account articles and draft-box submissions. Use when the user asks to write, adapt, illustrate, verify, or publish a WeChat/公众号 article, especially from a GitHub repo or existing technical/product material.

EthanYoQ/Skill-hub
インストール方法を見る

含まれるファイル（2）

  • SKILL.md3.6 KB
  • agents/openai.yaml264 B

SKILL.md（原文）

インストールする前に、エージェントに与えられる指示の中身を確認できます。

WeChat MP Writer

Use this skill as the project orchestrator. It adapts the Hermes workflow to Codex and this repository.

Local Resources

  • Project workflow: docs/github-to-wechat-codex-workflow.md
  • Content agent: docs/content-agent/workflow.md and docs/content-agent/agent-prompt.md
  • Setup check: tools/github-to-wechat/check-config.ps1
  • GitHub intake: tools/github-to-wechat/fetch-github-repo.ps1
  • URL intake: tools/github-to-wechat/url-to-markdown.ps1
  • Publish wrapper: tools/github-to-wechat/publish-markdown-to-wechat.ps1
  • Project Skill configs: .baoyu-skills/*/EXTEND.md
  • Visual direction: wechat-visual-director

Workflow

  1. Run or mentally apply setup checks.
    • If publishing is requested, run tools/github-to-wechat/check-config.ps1.
    • If only writing is requested, do not block on the SSH key.
    • Never print API keys or tokens.
  2. Intake source material.
    • For GitHub repositories, use fetch-github-repo.ps1 to save repo metadata, README, and a source ledger.
    • For generic pages, use url-to-markdown.ps1.
    • For local files, list the provided files and cite paths.
  3. Establish evidence.
    • Label claims as verified, reasonable inference, unverified, or do-not-publish.
    • If evidence is insufficient, provide known facts, candidate hypotheses, verification paths, and temporary safe wording only.
  4. Draft the article.
    • Follow the project content agent workflow.
    • Use wechat-title-strategist before locking the article title.
    • Keep the visible line: concrete pain -> product solution -> AI/technical judgment.
    • Avoid traffic-first writing, generic AI-tool review tone, invented adoption claims, and unverified business impact.
  5. Plan visuals before generating.
    • Use wechat-visual-director before any image-generation Skill.
    • Use baoyu-cover-image only for the cover.
    • Use baoyu-article-illustrator for body visuals.
    • Prefer real screenshots for UI, CLI, repository evidence, and product states.
    • Use Codex native image generation when available; do not route image work through another computer's Codex CLI.
    • Save final prompts before generating images.
  6. Publish only when the user wants a real WeChat draft.
    • Publish markdown, not pre-rendered HTML with base64 images.
    • Use remote-api via project config.
    • Personal subscription accounts can create drafts but require manual publish in WeChat backend.

Visual Direction

Do not make every image from the same cover template.

  • Architecture or workflow: flowchart/framework.
  • Business mechanism: editorial infographic/comparison.
  • Release or project history: timeline.
  • Product contrast: comparison matrix.
  • Workplace pain: scene illustration.
  • UI or repository proof: real screenshot.

Use mobile-readable body images, usually 3:4 or 4:3. Use 2.35:1 for covers.

Publishing Rules

  • Use .baoyu-skills/.env for credentials and keep it ignored.
  • Use baoyu-post-to-wechat through tools/github-to-wechat/publish-markdown-to-wechat.ps1.
  • Keep ordinary external links as bottom citations unless the user explicitly says otherwise.
  • Do not use --no-cite by default.
  • Do not claim publishing succeeded unless the command actually creates a draft and returns success.

レビュー

まだレビューはありません。使ってみた感想をお寄せください。

ログインしてレビューを書く

同じリポジトリのスキル

概要と使いどころ

aact-bulk-trials

無料

使用 AACT (Aggregate Analysis of ClinicalTrials.gov) PostgreSQL 数据仓库进行批量、历史、聚合性临床试验数据挖掘。Use this skill when the user requests bulk SQL analysis over the full clinical trials data warehouse — historical trial trends, disease landscapes, similar-design matching, or multi-year aggregations across hundreds of thousands of NCT records. 触发场景包括：AACT 查询、临床试验批量分析、PostgreSQL 试验数据、全量 NCT 检索、试验数据挖掘、历史试验分析、clinical trials data warehouse、SQL trials、bulk trial analysis、disease landscape、试验设计相似性匹配、跨年度聚合、sponsor/phase/country 多维统计。**与 clinical-trials-v2 差异**：本 skill 走批量 SQL · 离线大数据（PostgreSQL）；v2 走实时 API · 单查询。两者互补：单条 NCT 实时状态用 v2，百万级历史挖掘用本 skill。支持云端公共 PostgreSQL（aact-db.ctti-clinicaltrials.org · 零部署）和每日 dump 本地还原（高性能 · 离线）两种连接方式，自动检测优先用本地。跨平台（macOS/Linux/Windows）参数化 SQL 防注入，read-only 强制保护。

日本語の概要は準備中です。原文の説明を表示しています。

EthanYoQ/Skill-hub112026年10月5日 更新

aact-bulk-trials

無料

使用 AACT (Aggregate Analysis of ClinicalTrials.gov) PostgreSQL 数据库进行大批量临床试验历史分析与数据挖掘。触发场景包括：AACT 查询、临床试验批量分析、PostgreSQL 试验数据、全量 NCT 检索、试验数据挖掘、clinical trials data warehouse、疾病领域全景分析、设计相似试验匹配、跨年度试验趋势聚合。本 skill 通过 SQL 接口处理百万级试验记录，支持云端公共 PostgreSQL 服务（aact-db.ctti-clinicaltrials.org）和每日 dump 本地还原两种连接方式，自动检测并优先使用本地高性能模式。

日本語の概要は準備中です。原文の説明を表示しています。

EthanYoQ/Skill-hub112026年10月5日 更新

adaptive-quality-gate

無料

Use when work produces a deliverable, factual claim, dataset, code change, decision, publication, deployment, automation, or irreversible action whose failure would matter; when the user asks for a quality gate, acceptance criteria, QA, completeness, validation, audit, evidence, preflight, release readiness, or a definition of done; or before claiming completion on medium- or high-risk work. Automatically decide whether a formal gate is warranted, derive task-specific pass/fail criteria, gather evidence, and block unsupported completion. Make sure to use this skill even when the user does not say "quality gate" if consequential work needs acceptance criteria or completion evidence. Skip formal gating for trivial, reversible, low-impact requests.

日本語の概要は準備中です。原文の説明を表示しています。

EthanYoQ/Skill-hub112026年10月5日 更新

add-changeset

無料

Create a changeset file in .changeset/ that describes a user-facing change for the release notes

日本語の概要は準備中です。原文の説明を表示しています。

EthanYoQ/Skill-hub112026年10月5日 更新

add-competitor

無料

Add a new competitor to the AI Visibility Tool Directory — researches the tool, generates data, takes a screenshot, and inserts into the codebase

日本語の概要は準備中です。原文の説明を表示しています。

EthanYoQ/Skill-hub112026年10月5日 更新

add-lang

無料

Add tree-sitter language support to codegraph end-to-end — wire the grammar + extractor, write tests, then benchmark extraction quality and retrieval value on 3 popular real-world repos. Use when the user runs /add-lang <language> or asks to add/support a new language (e.g. Lua, Elixir, Zig, OCaml) in codegraph.

日本語の概要は準備中です。原文の説明を表示しています。

EthanYoQ/Skill-hub112026年10月5日 更新

EthanYoQ のスキルをすべて見る

このスキルの問題を報告する