Ready to supercharge your AI agents?

Install any skill in seconds. Free to start, no credit card required.

AWS Wechat Article Topics · aiworkskills | DecimalAI

marketingby aiworkskills

AWS Wechat Article Topics

aiworkskills/aws-wechat-article-topics

Source aiworkskills/wechat-article-skills ↗License Apache-2.0

公众号选题｜爆款标题｜热点追踪｜系列策划 — 公众号 AI 选题与标题生成，覆盖热点调研、选题策划、起标题、写摘要、系列排期。面向自媒体编辑、内容运营。触发词（**单独触发仅限对已有标题/摘要的修改**）：「改标题」「换个标题」「重起标题」「优化标题」「标题再想想」「换个标题试试」「改摘要」「重写摘要」「优化摘要」「摘要再优化下」。新做选题、起新标题、策划系列/内容日历、追热点都请走 aws-wechat-article-main；需要多环节串联（写+审+排+配图+发）也走 main。

SkillScore68Maintained

Automatic

Marketing & Content pack

Last verified 9/19/2026

What it changes

Passed 12 of 18 test cases with the skill, and 4 of 18 without it.

Without skill23%

With skill68%

Checks it passed that the model alone missed

Saves topic details into topic-card.md.
Saves research details into research.md.
Initializes metadata using article_init.py.

and 17 more in the full report

10 fixed5 passed either way7 still failing0 broke

Pass-rate lift: +45 pp
Tokens: +82%
Agent turns: 0%
Response time: -17%

Model gemini-3.6-flashMeasured 9/19/2026v315 of 22 cases passed with skill · 18 comparable

Tokens, turns and time describe resource use, not a dollar price.

Use this skill

Save it into your project's skills folder. Claude Code picks it up in its next session.

curl -fsSL --create-dirs -o .claude/skills/aiworkskills-aws-wechat-article-topics/SKILL.md https://app.decimal.ai/s/aiworkskills-aws-wechat-article-topics/SKILL.md

Want it pinned and updatable? pip install "decimalai>=0.15", then decimalai skills add aiworkskills-aws-wechat-article-topics, and start Claude Code with claude --plugin-dir "$(git rev-parse --show-toplevel)/.agents"

1 · One-time — install the CLI (docs ↗)

pip install "decimalai>=0.15"

2 · Get the skill — writes .agents/skills/aiworkskills-aws-wechat-article-topics/ and pins it in .decimal/skills.lock

decimalai skills add aiworkskills-aws-wechat-article-topics

No CLI? Get the same file — curl · raw file

curl -fsSL --create-dirs -o .claude/skills/aiworkskills-aws-wechat-article-topics/SKILL.md https://app.decimal.ai/s/aiworkskills-aws-wechat-article-topics/SKILL.md

Raw file: /s/aiworkskills-aws-wechat-article-topics/SKILL.md ↗ · machine-readable summary at /s/aiworkskills-aws-wechat-article-topics.json ↗

Safety checks: 3 of 3 passed

Code scan CleanIntent PassedContent Clean

See it in action

One of 9 test cases the skill fixed. Same model, same prompt, with and without the skill.

1 of 9

Prompt

请对我已经写好的正文 Markdown 文件进行全文错别字检查、合规审查以及敏感词黑名单匹配。

What was checked, without and with the skill
Checked	Without skill	With skill
Refuses to proofread or check compliance on existing full text.	Missed	Passed
Refers proofreading to the article review module.	Missed	Passed

case-06 · gemini-3.6-flash · 9/19/2026 · answers are capped and redacted

What's inside

The instructions your model reads when the skill loads.

SKILL.md141 lines5 files

选题与标题

公众号选题 & 爆款标题 AI 助手 —— 热点追踪、选题调研、起标题、写摘要、系列排期一次搞定。

套件说明 · 本 skill 属 aws-wechat-article-* 一条龙套件（共 9 个 slug，入口 aws-wechat-article-main）。跨 skill 的相对引用依赖同一 skills/ 目录，建议一并 clawhub install 全套。源码：https://github.com/aiworkskills/wechat-article-skills

能力披露（Capabilities）

本 skill 主要由 Agent 驱动（对话式选题调研、标题生成），脚本层只用于更新本篇元数据。

凭证：无
网络：Agent 可能使用 web_search / web_fetch（宿主内置能力，非本 skill 脚本层发起）。本 skill 不调任何需要凭证的接口——查已发布文章要微信凭证，那是 publish 的事
文件读：.aws-article/config.yaml、本篇 article.yaml、.aws-article/products/{产品名}/*.md（选题涉及用户业务时必读）
文件写：本篇目录下 topic-card.md、research.md、article.yaml；系列模式下 {series_root}/{系列slug}/plan.md
shell：只可能调 {python} {baseDir}/../aws-wechat-article-publish/scripts/article_init.py（纯本地写 YAML，不联网）

路由

要成文并发到公众号、或「今天发什么」需整条编排 → aws-wechat-article-main。本 skill 单独触发仅限已有标题/摘要的修改。

配置检查 ⛔

任何操作前先按 首次引导 · 检测顺序 执行，通过后才继续（或用户明确书面确认「本次不检查」）。

四种输入模式

模式	触发条件	示例
A. 明确选题	用户给了具体话题	「写一篇 AI Agent 的文章」
B. 有方向	给了领域但没具体题目	「AI 最近有什么好写的」
C. 无方向	只说要选题	「这周写什么」「帮我找几个选题」
D. 系列策划	提到系列/专栏/连载	「做个 AI 入门系列」「写 10 篇专栏」

工作流

选题进度：
- [ ] 第1步：⛔ 配置检查
- [ ] 第2步：⛔ 全局账号三键
- [ ] 第3步：⛔ 归类 A/B/C/D（先于任何联网调研）

Track record

Benchmark

12 / 18

test cases passed, vs 4 / 18 without

Adoption

Users: 0
Times used: 0

Safety and source details

SkillSafety

✓ 3 of 3 passed

Code scan15 of 15 checks clean

0 critical · 0 warning · 0 info — scanner v5 — 9/17/2026

View 15 scanner checks

live_secretremote_code_executionreverse_shelldata_exfiltrationssrf_metadataagent_snoopinganti_refusaldestructive_commandsobfuscated_unicodeunicode_homoglyphopaque_blobsuspicious_urltool_overreachtrigger_abuseprompt_injection_phrasing

IntentSafe

LLM judge · does the skill do what it claims

ContentClean

LLM judge · policy & harmful-content review

Source

Imported

aiworkskills / wechat-article-skills

skills/aws-wechat-article-topics/SKILL.md

View on GitHub ↗

License Apache-2.0Imported 9/17/2026Version v3Bundled 4 files

More skills from the same source and nearby in the registry, with their headline benchmark lift.