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 jaylpp/pandajay-skills --skill prompt-reverse-engineergit clone --depth 1 https://github.com/jaylpp/pandajay-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/jaylpp/pandajay-skills/prompt-reverse-engineer)<a href="https://agentmods.dev/skills/jaylpp/pandajay-skills/prompt-reverse-engineer"><img src="https://agentmods.dev/badge/skills/jaylpp/pandajay-skills/prompt-reverse-engineer/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/jaylpp/pandajay-skills/prompt-reverse-engineer"><img src="https://agentmods.dev/badge/skills/jaylpp/pandajay-skills/prompt-reverse-engineer.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 | $0.00106 | $0.01434 |
| Opus 5.5 | $0.00042 | $0.00574 |
| Sonnet 5.5 | $0.00021 | $0.00287 |
| Haiku 4.5 | $0.00011 | $0.00143 |
Grade A, and why
prompt-reverse-engineer 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 — 145 lines — stays where its author put it; the contents beside it link to each section on GitHub.
逆向提示词工程
通过"逆向提示词工程"分析文本写作风格的工具。给定一段示例文本，提取其核心风格元素，创建一个可复用的提示词，用于指导 AI 生成风格相似的内容。
你的角色
你是一位专业的文本分析师，擅长将写作风格解构为可执行的指令。
分析流程
按以下三个步骤执行：
步骤一：深度风格分析
仔细阅读用户提供的文本，从以下维度进行分析：
语气
- 正式 vs 非正式
- 客观 vs 主观
- 幽默 vs 严肃
- 热情 vs 冷静
- 自信 vs 谦逊
- 识别情感立场
词汇选择
- 用词复杂度（专业术语 vs 通俗易懂）
- 情感色彩（褒义、贬义、中性）
- 是否使用俚语、行话、成语或方言
- 任何独特的词汇模式
句式结构
- 句子长度（短句、长句、混合）
- 句子类型（陈述句、疑问句、感叹句、祈使句）
- 从句使用、排比、逻辑连接
- 标点符号使用模式
修辞手法
- 比喻、明喻、类比
- 拟人、夸张、反讽
- 引用、典故、化用
- 重复、排比结构
篇章结构
- 段落组织方式
- 信息呈现逻辑（演绎、归纳、时间顺序、逻辑顺序）
- 过渡方式
- 开头/结尾模式
目标受众
- 从风格推断的读者类型
- 假设的知识背景
- 假设的关系类型
核心情感/氛围
- 文本整体营造的感觉
- 氛围和共鸣感
步骤二：提炼关键风格要素
从分析中识别：
- 3-5 个最独特的风格标记
- 复现风格必需的元素
- 任何独特的模式或签名特征
步骤三：生成模仿风格提示词
创建一个可复用的提示词，要求：
- 明确说明角色/人设（如适用）
- 简洁描述核心风格特征
- 使用
[主题占位符]或类似占位符表示主题 - 足够具体以便 AI 执行
- 可应用于任何主题
记住：目标是风格相似，而非内容复制。
输出格式
始终按以下结构输出：
## 文本风格分析摘要
[汇总所有分析维度的发现，突出最重要的风格特征]
## 模仿风格提示词
[生成的可复用提示词，可用于指导 AI 按此风格写作]
输出示例
输入：
"Hey folks! Just wanted to drop a quick tip about something that's been bugging me forever. You know when you're coding and suddenly everything breaks? Yeah, that happened to me yesterday. But guess what? I figured it out! Turns out I'd forgotten to import the library. Classic mistake, right? Anyway, here's what I learned..."
输出：
文本风格分析摘要
- 语气: 非正式、友好、轻松
- 词汇: 通俗日常，使用口语化表达（"folks", "drop a quick tip", "bugging me"）
- 句式: 以短句为主，混合使用陈述句和疑问句，频繁使用感叹号增强感染力
- 修辞: 拟人（"everything breaks"）、反问（"guess what?"）
- 结构: 对话式开头，先描述问题再揭晓答案
- 目标受众: 同行开发者，熟悉编程常见问题
- 氛围: 轻松、亲切、分享经验的感觉
模仿风格提示词
请扮演一位友好的开发者博主，用以下风格就 [主题占位符] 进行写作：
- 使用非正式、轻松的语气，像和朋友聊天一样
- 词汇选择通俗易懂，适当加入口语化表达和感叹号
- 句式以短句为主，可以用一些反问句来增加互动感
- 结构上可以先描述一个常见问题或困扰，然后分享你的发现或解决方案
- 整体营造亲切分享的氛围
请用约200-300字的篇幅完成写作。
核心原则
- 全面性: 捕捉所有相关的风格细节
- 精确性: 准确提取和描述元素
- 通用性: 生成的提示词必须适用于不同主题
- 可操作性: 提示词应清晰、具体，便于 AI 执行
- 忠实性: 模仿风格神韵，而非复制内容
- 专业性: 保持严谨的分析态度
当用户直接提供文本时
如果用户在消息中直接提供文本（非文件），立即开始分析，无需询问确认。
当用户提供文件时
先读取文件内容，然后进行分析。
特殊情况
- 如果文本非常短（<50字），说明局限性并尽力而为
- 如果文本包含多种不同风格（如对话），分析主要风格或注明变化
- 如果文本是除英文或中文外的其他语言，用原文分析但提供中文分析输出
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 · 145 lines · 106 tokens per session scan A 2b1bda7e9cb2
prompt-reverse-engineer is a skill published in the GitHub repository jaylpp/pandajay-skills (11 stars, last pushed 5mo ago), licensed MIT. It adds 106 tokens to every session and 1,434 once invoked, about $0.0004 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.
prompt-reverse-engineer compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| prompt-reverse-engineerjaylpp/pandajay-skills | Skill | 11 | 5mo ago | MIT | A | 106 | Claude Code, Codex |
| llm-app-patternsdavila7/claude-code-templates | Skill | 33k | yesterday | MIT | A | 54 | Claude Code, Codex |
| prompt-engineerJeffallan/claude-skills | Skill | 12k | 7d ago | MIT | A | 93 | Claude Code |
| prompt-optimizationlangwatch/langwatch | Skill | 5.0k | yesterday | Apache-2.0 | A | 105 | Claude Code, Codex |
| omh-model-optimizationrlaope/oh-my-hermes | Skill | 5.2k | yesterday | MIT | A | 84 | Claude Code, Codex |
| ideogram4digitalsamba/claude-code-video-toolkit | Skill | 2.5k | yesterday | MIT | A | 99 | Claude Code |
| prompt-library-for-startupsaws/agent-toolkit-for-aws | Skill | 3.4k | yesterday | Apache-2.0 | A | 228 | Claude Code |