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 HeroAshacker/wechat-content-pipeline --skill wechat-article-evaluatorgit clone --depth 1 https://github.com/HeroAshacker/wechat-content-pipelineWrote 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/heroashacker/wechat-content-pipeline/wechat-article-evaluator)<a href="https://agentmods.dev/skills/heroashacker/wechat-content-pipeline/wechat-article-evaluator"><img src="https://agentmods.dev/badge/skills/heroashacker/wechat-content-pipeline/wechat-article-evaluator/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/heroashacker/wechat-content-pipeline/wechat-article-evaluator"><img src="https://agentmods.dev/badge/skills/heroashacker/wechat-content-pipeline/wechat-article-evaluator.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00137 | $0.04961 |
| Opus 5.5 | $0.00055 | $0.01984 |
| Sonnet 5.5 | $0.00027 | $0.00992 |
| Haiku 4.5 | $0.00014 | $0.00496 |
Grade A, and why
wechat-article-evaluator 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 2mo 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 — 405 lines — stays where its author put it; the contents beside it link to each section on GitHub.
微信公众号文章质量评估器 (wechat-article-evaluator)
触发条件
- 评估文章, 文章打分, 文章质量评估
- 公众号文章评分, 爆文评估
- /wechat-article-evaluator <文件路径>
- 这篇文章能爆吗, 文章能打多少分
Instructions
Step 1: 获取文章内容
- 文件路径:
.md或.txt文件 → 使用 Read 工具读取 - 内联文本: 用户直接粘贴的文章内容
- 无输入: 提示用户提供文章内容或文件路径
Step 2: 预分析
快速扫描文章基本信息：
| 检查项 | 说明 |
|---|---|
| 标题 | 提取文章标题（首行 # 或第一行） |
| 字数 | 统计全文字数 |
| 段落数 | 统计段落结构 |
| 目标受众 | 根据内容推断目标读者群 |
Step 3: 五维度评分
逐一评估以下 5 个维度，每个维度 20 分，总分 100 分。 详细评分标准见下方「评估维度」章节。
Step 4: 生成评估报告
按照「输出格式」章节的模板输出完整报告，包含：
- 总分与等级
- 各维度详细评分（含进度条）
- 综合评价
- 具体改进建议（至少 3 条可操作建议）
质量等级
| 等级 | 分数 | 说明 |
|---|---|---|
| A+ | 90-100 | 爆文潜质 |
| A | 80-89 | 优质文章 |
| B | 70-79 | 合格文章 |
| C | 60-69 | 需要改进 |
| D | 50-59 | 较差 |
| F | <50 | 需要重写 |
评估维度
总分 100 分，5 个维度
| 维度 | 满分 | 核心关注 |
|---|---|---|
| 标题吸引力 | 20 | 记忆锚点、好奇心触发、简洁有力 |
| 情绪共鸣 | 20 | 真实感、打动人、代入感 |
| 结构完整性 | 20 | 逻辑通顺、节奏合理、首尾呼应 |
| 案例深度 | 20 | 具体细节、说服力、真实经历 |
| 爆文潜力 | 20 | 传播性、分享欲、受众匹配 |
维度 1: 标题吸引力 (20分)
| 子项 | 分值 | 评分标准 |
|---|---|---|
| 记忆锚点 | 7 | 标题是否包含具体数字/人物/场景，让人过目不忘。7=画面感极强，4=有亮点，2=平淡 |
| 好奇心触发 | 7 | 是否制造信息差/悬念/反常识。7=非点不可，4=有点想看，2=无感 |
| 简洁有力 | 6 | 字数15-25字为佳，无废字，节奏感好。6=精炼有力，3=略冗长，1=拖沓或过短 |
维度 2: 情绪共鸣 (20分)
| 子项 | 分值 | 评分标准 |
|---|---|---|
| 真实感 | 7 | 是否有真实的情感表达，非套路化鸡汤。7=真诚动人，4=尚可，2=假大空 |
| 打动力 | 7 | 能否触发读者情绪（感动/愤怒/共鸣/启发）。7=强烈共鸣，4=有触动，2=无感 |
| 代入感 | 6 | 读者能否把自己代入场景。6=身临其境，3=部分代入，1=旁观者视角 |
维度 3: 结构完整性 (20分)
| 子项 | 分值 | 评分标准 |
|---|---|---|
| 逻辑通顺 | 7 | 段落间因果/递进/转折是否自然。7=行云流水，4=基本通顺，2=跳跃混乱 |
| 节奏合理 | 7 | 长短段交替、张弛有度、不拖沓。7=节奏感强，4=尚可，2=平铺直叙 |
| 首尾呼应 | 6 | 开头吸引+结尾升华，形成闭环。6=完美闭环，3=有头有尾，1=虎头蛇尾 |
维度 4: 案例深度 (20分)
| 子项 | 分值 | 评分标准 |
|---|---|---|
| 具体细节 | 7 | 案例是否有时间/地点/人物/对话等细节。7=细节丰满，4=有细节，2=笼统空泛 |
| 说服力 | 7 | 案例能否有力支撑观点。7=无可辩驳，4=有说服力，2=牵强附会 |
| 真实经历 | 6 | 是否来自真实经历或可信来源。6=亲身经历，3=二手可信，1=编造感强 |
维度 5: 爆文潜力 (20分)
| 子项 | 分值 | 评分标准 |
|---|---|---|
| 传播性 | 7 | 内容是否自带传播属性（争议/共鸣/实用）。7=必转，4=想转，2=不想转 |
| 分享欲 | 7 | 读者转发时能否获得社交货币。7=转发涨身份，4=值得分享，2=无分享动力 |
| 受众匹配 | 6 | 内容与目标受众的匹配度。6=精准命中，3=部分匹配，1=受众模糊 |
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.
- 2mo ago First seen · 405 lines · 137 tokens per session scan A 86c7a4046e8f
wechat-article-evaluator is a skill published in the GitHub repository HeroAshacker/wechat-content-pipeline (12 stars, last pushed 8mo ago), licensed MIT. It adds 137 tokens to every session and 4,961 once invoked, about $0.0005 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.
wechat-article-evaluator compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| wechat-article-evaluatorHeroAshacker/wechat-content-pipeline | Skill | 12 | 8mo ago | MIT | A | 137 | Claude Code |
| imagegenopenai/codex | Skill | 133k | yesterday | Apache-2.0 | A | 113 | Codex |
| playwright-climicrosoft/playwright | Skill | 99k | yesterday | Apache-2.0 | A | 19 | Claude Code |
| local-ai-agentsmicrosoft/ai-agents-for-beginners | Skill | 79k | 4d ago | MIT | A | 200 | Claude Code, Codex |
| systematic-debuggingobra/superpowers | Skill | 313k | 3d ago | MIT | A | 21 | Claude Code |
| next-cache-components-adoptionvercel/next.js | Skill | 143k | yesterday | MIT | A | 95 | Claude Code |
| next-partial-prefetching-adoptionvercel/next.js | Skill | 143k | yesterday | MIT | A | 103 | Claude Code |