Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add aiworkskills/wechat-article-skills --skill aws-wechat-article-maingit clone --depth 1 https://github.com/aiworkskills/wechat-article-skillsWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/aiworkskills/wechat-article-skills/aws-wechat-article-main)<a href="https://agentmods.dev/skills/aiworkskills/wechat-article-skills/aws-wechat-article-main"><img src="https://agentmods.dev/badge/skills/aiworkskills/wechat-article-skills/aws-wechat-article-main/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/aiworkskills/wechat-article-skills/aws-wechat-article-main"><img src="https://agentmods.dev/badge/skills/aiworkskills/wechat-article-skills/aws-wechat-article-main.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00359 | $0.03971 |
| Opus 5.5 | $0.00144 | $0.01588 |
| Sonnet 5.5 | $0.00072 | $0.00794 |
| Haiku 4.5 | $0.00036 | $0.00397 |
Grade A, and why
aws-wechat-article-main scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 1mo ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 183 lines — stays where its author put it; the contents beside it link to each section on GitHub.
公众号运营总览
一键式公众号 AI 内容流水线 —— 从选题到上架 8 个子 skill 串联。
套件说明 ·
aws-wechat-article-*共 9 个 slug：main / topics / writing / review / formatting / images / publish / assets，外加aws-wechat-sticker。跨 skill 的相对引用依赖同一skills/根目录；推荐clawhub sync一次性全装。源码：https://github.com/aiworkskills/wechat-article-skills
Agent 执行：确定本 SKILL.md 所在目录为 {baseDir}。
能力披露（Capabilities）
本 skill 是编排入口，真正调用外部 API 的是子 skill（writing / images / publish / sticker / review）。本入口自身只跑 validate_env.py：
- 凭证：读
aws.env的各*_API_KEY与WECHAT_{N}_*，仅校验键存在且非空，值不用于任何网络请求 - 网络：本入口无外发；子 skill 有外发，见各自的能力披露
- 文件读写：
.aws-article/、本篇article.yaml - shell：仅
{python} {baseDir}/scripts/validate_env.py
整体套件会调用外部 LLM、图像与微信 API，并在调用时外发 API key 与本篇内容。
只装 main 一个时仍可做环境校验；进入流水线会因子 skill 缺失而 file not found。
配置检查 ⛔ BLOCKING
进入「全局账号约束」「本篇准备」及内容流水线之前，必须按 首次引导 完整走一遍「检测顺序」——判断 OS、探测 {python}、检查两份配置文件、跑 validate_env.py、创建预设目录。任一步失败不得继续。
那份文档同时是唯一的失败引导来源与行为约束（禁止自作主张、不得索取密钥）出处，本文件不再复述。
三个要点在这里说一次：
publish_method默认draft（publish.py full只写公众号草稿箱）。用户明确要求「发出去」才改published，或临时用full --publish。- 用户明确不接微信 → 先设
publish_method: none再过校验，之后full会直接跳过。 - 写作 / 图片模型是可选项，缺失时只警告、不阻断。
主要配置文件（不要混用）
| 文件 | 位置 | 作用 |
|---|---|---|
aws.env |
仓库根 | 只放密钥：*_API_KEY、WECHAT_N_APPID / WECHAT_N_APPSECRET（键名见 references/env.example.yaml） |
.aws-article/config.yaml |
仓库内 | 账号级非密钥配置：文风、选题边界、模型端点、微信槽位与 publish_method（模板见 references/config.example.yaml） |
article.yaml |
本篇目录 | 本篇发文元数据与状态：image_source（generated / user）、publish_completed（新建 false，发布闭环后 true） |
字段说明见 articlescreening-schema.md。
交互顺序
上一步完成再进下一步。 每步若缺必要输入（目录、元数据、主题、用户选择、发布意图），先问用户并取得确认；除非用户说明基于某个历史任务继续，那就按中间产物判断从哪个阶段接入。
1) 配置自检 ⛔
按上文完成检测顺序，validate_env.py 退出码 0 且预设目录已建，才能进下一步。
- 退出码 0 + 可选项警告 → 不阻断，直接进下一步，不得要求用户先配写作/图片模型。
- 退出码 1（微信不完整）→ 见 branches.md 第三节。
validate_env.py不检查article_category/target_reader/default_author，那三项在下一步查。
What ships with it
22 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- references/articlescreening-schema.md 6.1 KB
- references/branches.md 3.9 KB
- references/config.example.yaml 12 KB
- references/env.example.yaml 511 B
- references/first-time-setup.md 13 KB
- references/presets/closing-blocks/README.md 1011 B
- references/presets/closing-blocks/simple.example.md 66 B
- references/presets/cover-styles/README.md 1.1 KB
- references/presets/cover-styles/简约.example.md 656 B
- references/presets/image-styles/flat-vector.example.md 345 B
- references/presets/image-styles/README.md 881 B
- references/presets/review-rules.example.yaml 489 B
- references/presets/sticker-styles/default.example.md 244 B
- references/presets/sticker-styles/README.md 476 B
- references/presets/structures/listing.example.md 604 B
- references/presets/structures/README.md 976 B
- references/presets/title-styles/emotion.example.md 665 B
- references/presets/title-styles/README.md 898 B
- references/presets/title-styles/suspense.example.md 334 B
- references/writing-spec.example.md 1.2 KB
- scripts/validate_env.py 7.0 KB runs code
- skill.json 693 B
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 1mo ago Changed · -154 lines be6db653864c
- 1mo ago Changed · +8 lines 3e65b5dea97b
- 1mo ago Changed 54ee1399a4c0
- 2mo ago Changed · +24 lines c2bb7484d7f6
- 2mo ago First seen · 305 lines · 359 tokens per session scan A 00bf35df0964
aws-wechat-article-main is a skill published in the GitHub repository aiworkskills/wechat-article-skills (726 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 359 tokens to every session and 3,971 once invoked, about $0.0014 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
aws-wechat-article-main compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| aws-wechat-article-mainaiworkskills/wechat-article-skills | Skill | 726 | 1mo ago | Apache-2.0 | A | 359 | Claude Code, Codex |
| stop-slop-zhpencil20388-eng/stop-slop-zh | Skill | 54 | 5mo ago | MIT | A | 0 | Claude Code, Codex |
| shuorenhuatentenco/shuorenhua-zh-tw | Skill | 10 | 4mo ago | MIT | A | 130 | Claude Code, Codex |
| anti-slop-uaEverdarkk/anti-slop-ua | Skill | 1 | 3mo ago | MIT | A | 84 | Claude Code, Codex |
| thothNirvanaGuha/thoth | Skill | 4 | 4mo ago | MIT | A | 211 | Claude Code |
| article-qaweitzu-com/ai-article-factory | Skill | 5 | 5mo ago | Apache-2.0 | A | 105 | Claude Code |
| ai-article-factoryweitzu-com/ai-article-factory | Skill | 5 | 5mo ago | Apache-2.0 | A | 96 | Claude Code |