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 AgiWish/hermes-skills-zh --skill prompt-optimize-zhgit clone --depth 1 https://github.com/AgiWish/hermes-skills-zhWrote 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/agiwish/hermes-skills-zh/prompt-optimize-zh)<a href="https://agentmods.dev/skills/agiwish/hermes-skills-zh/prompt-optimize-zh"><img src="https://agentmods.dev/badge/skills/agiwish/hermes-skills-zh/prompt-optimize-zh/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/agiwish/hermes-skills-zh/prompt-optimize-zh"><img src="https://agentmods.dev/badge/skills/agiwish/hermes-skills-zh/prompt-optimize-zh.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 | $0.00049 | $0.00809 |
| Opus 5 | $0.00024 | $0.00404 |
| Sonnet 5 | $0.00010 | $0.00162 |
| Haiku 4.5 | $0.00005 | $0.00081 |
Grade A, and why
prompt-optimize-zh 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 12d 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
Prompt 优化诊断 (prompt-optimize-zh)
When to Use
- "帮我看看这个 prompt 哪里有问题"
- "这个提示词输出很不稳定，怎么改"
- 大模型输出质量差、格式乱、幻觉多
/prompt-optimize-zh [你的 prompt]
Quick Reference
/prompt-optimize-zh [原始 Prompt 内容]
可选参数：
--model=claude # 针对 Claude 系列优化（默认）
--model=gpt4 # 针对 GPT-4o / GPT-4.1 优化
--model=deepseek # 针对 DeepSeek 优化
--focus=稳定性 # 重点解决输出不稳定
--focus=格式 # 重点解决格式混乱
--focus=准确性 # 重点解决幻觉和错误
Procedure
- 诊断原始 Prompt，检查以下维度：
| 维度 | 检查点 | 常见问题 |
|---|---|---|
| 角色设定 | 是否有明确的 persona | 没有角色 → 输出风格不稳定 |
| 任务描述 | 是否精确、无歧义 | 模糊 → 模型自由发挥 |
| 输出格式 | 是否明确格式要求 | 未指定 → 格式随机 |
| 约束条件 | 是否有明确的边界 | 无约束 → 过度延伸 |
| 示例 | 是否有 few-shot 示例 | 缺少示例 → 理解偏差 |
| 兜底逻辑 | 不确定时如何处理 | 无兜底 → 幻觉风险 |
- 输出诊断报告 + 优化版本
## Prompt 诊断报告
**原始 Prompt**：
[引用原始内容]
### 问题清单
- 🔴 [严重问题]：[说明为什么有问题]
- 🟡 [改进建议]：[说明优化方向]
- 🟢 [做得好的地方]：[保留的部分]
### 优化版本
[完整输出改写后的 Prompt]
### 改动说明
| 改动点 | 改动前 | 改动后 | 原因 |
|--------|--------|--------|------|
| 角色设定 | 无 | "你是一位..." | 稳定输出风格 |
| 格式约束 | 无 | "输出为JSON..." | 避免格式随机 |
| 兜底逻辑 | 无 | "如不确定..." | 降低幻觉风险 |
### 进阶建议
- [如果效果还不好，下一步可以尝试的方向]
Pitfalls
- 不要过度修改，保留原 Prompt 的核心意图
- 优化后的版本要明显比原版更短或更结构化
- 不同模型的最佳实践不同，要结合 --model 参数给出针对性建议
Verification
- 诊断覆盖所有 6 个维度
- 优化版本有完整可用的内容
- 每个改动有明确的理由
- 改动说明用对比格式清晰呈现
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.
- 12d ago First seen · 88 lines · 49 tokens per session scan A 5e7168614356
prompt-optimize-zh is a skill published in the GitHub repository AgiWish/hermes-skills-zh (5 stars, last pushed 3mo ago), licensed MIT. It adds 49 tokens to every session and 809 once invoked, about $0.0002 per session on Opus 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.
Other skills, from other repositories
seedance-vocab-zh
This skill should be used when the user asks for Chinese Seedance 2.0 prompt wording, Mandarin cinematic vocabulary, Chinese prompt compression, or translation of camera, lighting, action, VFX, audio, and production terms into Chinese.
hunt-llm-ai
Hunt LLM/AI feature bugs — prompt injection, indirect injection, exfiltration viatool-use/markdown, ASCII smuggling, agentic AI security (OWASP Agentic Apps 2026, ASI01-ASI10). Patterns: direct injection ('ignore previous instructions'), indirect injection via documents/web pages/email the model reads, ASCII smuggling…
lijigang-skill
A Chinese-language approach to writing precise, highly structured prompts, sometimes using Lisp-like notation. It combines concise wording, philosophical questioning, and a process for defining roles, conditions, output formats, and revisions.
ai-image-prompts-skill
Recommend curated prompts from a 10,000+ real-world image generation prompt library. Works with ANY AI image model — Nano Banana Pro, Nano Banana 2, Seedream 5.0, GPT Image 1.5, Midjourney, DALL-E 3, Flux, Stable Diffusion, and more. Use this skill when users want to: Find proven image generation prompts (any model)…
ai-prompt-generator
A tool that creates or improves instructions for AI models. It offers prompt templates for approaches such as role-based instructions, examples, and step-by-step reasoning.
baoyu-skill
A Chinese-language approach to explaining AI tools and writing prompts—instructions that tell an AI what you want. It emphasizes step-by-step teaching, hands-on testing, plain-language technical explanations, and organized knowledge sharing.