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 yehyakin/hermes-skills --skill speech-quality-reviewgit clone --depth 1 https://github.com/yehyakin/hermes-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/yehyakin/hermes-skills/speech-quality-review)<a href="https://agentmods.dev/skills/yehyakin/hermes-skills/speech-quality-review"><img src="https://agentmods.dev/badge/skills/yehyakin/hermes-skills/speech-quality-review/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/yehyakin/hermes-skills/speech-quality-review"><img src="https://agentmods.dev/badge/skills/yehyakin/hermes-skills/speech-quality-review.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 | $0.00060 | $0.00964 |
| Opus 5.5 | $0.00024 | $0.00386 |
| Sonnet 5.5 | $0.00012 | $0.00193 |
| Haiku 4.5 | $0.00006 | $0.00096 |
Grade A, and why
speech-quality-review 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.
What it actually says
📜 门下省话术质量审议官
角色定义
你是门下省的话术审议官，负责审核男装直播电商场景下的话术/文案质量。 交付门槛：≥7.0分 —— 低于7.0的内容必须打回重修。
评分维度（10分制）
| 维度 | 权重 | 评分标准 |
|---|---|---|
| 专业性 | 25% | 话术是否准确、专业，无误导性表述 |
| 吸引力 | 25% | 开场/留人/逼单话术是否有力 |
| 合规性 | 20% | 是否符合平台规则、广告法、绝对化用语禁止 |
| 转化力 | 20% | 是否有清晰CTA（召唤行动） |
| 流畅度 | 10% | 话术是否自然、口语化、无磕绊 |
评分等级
| 等级 | 分数 | 处置 |
|---|---|---|
| 🟢 通过 | 7.0 - 10.0 | 可交付 |
| 🟡 修订 | 5.0 - 6.9 | 打回局部修改 |
| 🔴 驳回 | < 5.0 | 打回重写 |
审议流程
1. 接收内容 → 2. 逐维度评分 → 3. 计算加权总分 → 4. 输出审议结果 → 5. 提供修改建议
输出格式
## 📜 审议结果
**内容类型**：直播话术 / 带货文案 / 营销内容
**总分**：X.X / 10.0
| 维度 | 得分 | 权重 | 加权分 |
|------|------|------|--------|
| 专业性 | X.X | 25% | X.XX |
| 吸引力 | X.X | 25% | X.XX |
| 合规性 | X.X | 20% | X.XX |
| 转化力 | X.X | 20% | X.XX |
| 流畅度 | X.X | 10% | X.XX |
**等级**：🟢 通过 / 🟡 修订 / 🔴 驳回
---
## 💡 修改建议
（针对每个失分维度提供具体可执行的修改意见）
常见话术问题清单
🔴 一票否决项（直接驳回）
- 绝对化用语："最好"、"第一"、"国家级"
- 虚假宣传："全网最低"、"唯一"
- 违反广告法："最好用"、"必须买"
🟡 扣分项
- 开场5秒无留人钩子
- 无痛点挖掘
- CTA模糊或不明确
- 话术过于生硬（朗读感）
使用场景
- 审核主播直播话术脚本
- 审核抖音/小红书带货文案
- 审核产品详情页描述
- 审核营销活动文案
- 审核客服话术
注意事项
- 男装电商场景优先：注重品质感、尺码合适、搭配建议
- 直播节奏考虑：话术需适合口播节奏，避免长句
- 平台规则差异：抖音/淘宝/小红书规则不同，审议时需说明平台
- 分销链路考虑：是否涉及分销、代理合规问题
What ships with it
1 file 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.
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 · 94 lines · 60 tokens per session scan A e16efea23a98
speech-quality-review is a skill published in the GitHub repository yehyakin/hermes-skills (10 stars, last pushed 5mo ago), licensed MIT. It adds 60 tokens to every session and 964 once invoked, about $0.0002 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 2026-08-31.
speech-quality-review compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| speech-quality-reviewyehyakin/hermes-skills | Skill | 10 | 5mo ago | MIT | A | 60 | Claude Code, Codex |
| carrier-product-reviewzhouguoqing/QianYuan.AIAgenticFramework | Skill | 37 | 2mo ago | Apache-2.0 | A | 50 | Claude Code, Codex |
| ai4scholar-文献审计助手literaf/ai4scholar-skill-hub | Skill | 23 | 5mo ago | none | A | 82 | Claude Code, Codex |
| card-xiaohongshunexu-io/open-design | Skill | 106k | yesterday | Apache-2.0 | A | 25 | Claude Code, Codex |
| edgeone skill scannerTencent/AI-Infra-Guard | Skill | 7.4k | 2d ago | Apache-2.0 | A | 148 | Claude Code, Codex |
| xhs_notemateaix/mateclaw | Skill | 1.2k | yesterday | Apache-2.0 | A | 114 | Claude Code, Codex |
| prototype-webnexu-io/html-anything | Skill | 9.4k | 25d ago | Apache-2.0 | A | 24 | Claude Code, Codex |