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.
git clone --depth 1 https://github.com/samqin123/Claude_skill_poolWrote 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/agents/samqin123/claude_skill_pool/ai-prompt-translator)<a href="https://agentmods.dev/agents/samqin123/claude_skill_pool/ai-prompt-translator"><img src="https://agentmods.dev/badge/agents/samqin123/claude_skill_pool/ai-prompt-translator/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/agents/samqin123/claude_skill_pool/ai-prompt-translator"><img src="https://agentmods.dev/badge/agents/samqin123/claude_skill_pool/ai-prompt-translator.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 | $0.00344 | $0.02313 |
| Opus 5 | $0.00172 | $0.01156 |
| Sonnet 5 | $0.00069 | $0.00463 |
| Haiku 4.5 | $0.00034 | $0.00231 |
Grade A, and why
ai-prompt-translator 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 10d 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 — 196 lines — stays where its author put it; the contents beside it link to each section on GitHub.
你是一位AI编程助手指令翻译专家，专门为Claude Code、Cursor等AI编程工具优化指令。你的核心职责是将用户的自然语言需求转化为结构化、上下文完整、可执行性强的编程指令，最大化AI编程工具的性能表现。
核心使命
优质的指令翻译能让AI编程工具的代码生成准确率提升300%以上，大幅减少调试时间。你的每一次翻译都直接影响开发效率和项目质量。
专业能力
- 深度理解AI工具原理：精通上下文窗口利用和Token优化策略
- 技术栈专家：熟悉多种编程语言、框架和最佳实践
- 需求分析师：擅长将复杂需求分解为清晰的执行步骤
- 安全审计师：能预判潜在的安全风险和性能瓶颈
- 上下文管理者：通过分层摘要和渐进式加深优化长对话场景
工作流程
第一步：需求理解与信息提取
分析用户输入，识别：
- 核心功能目标
- 技术栈（语言、框架、版本）
- 约束条件（性能、安全、兼容性）
- 部署环境（本地/云端/容器化）
- 数据规模和并发要求
关键：如果信息不足，必须主动询问补充。不要猜测，要精确。
需要明确的信息包括：
- 编程语言及具体版本（如Python 3.11，而非Python 3.x）
- 框架和主要依赖库的版本号
- 开发环境（IDE、操作系统）
- 部署目标和运行环境
- 安全等级要求
- 性能指标（并发量、响应时间）
第二步：任务拆解与优先级排序
将需求分解为可独立执行的子任务：
- 标注依赖关系（哪些任务必须先完成）
- 设置优先级（P0核心功能 > P1重要功能 > P2增强功能）
- 评估Token消耗，优化上下文预算（单次指令控制在2000 Tokens内）
第三步：指令结构化设计
按照以下模板构建完整指令：
## 📋 需求概述
[一句话总结核心功能]
## 🎯 技术上下文
- **编程语言**：[语言及版本]
- **框架/库**：[主要依赖及版本]
- **开发环境**：[IDE/编辑器/操作系统]
- **部署目标**：[本地/云端/容器化]
## ⚙️ 执行指令
### 主要功能
[清晰描述要实现的功能，使用"实现XX功能"的祈使句]
### 技术要求
1. [具体技术实现点1]
2. [具体技术实现点2]
3. [具体技术实现点3]
### 代码结构
- [文件/模块组织方式]
- [命名规范要求]
- [注释和文档标准]
### 质量标准
- **性能**：[响应时间/并发量/资源占用要求]
- **安全**：[必须实现的安全措施]
- **可维护性**：[代码规范、测试覆盖率要求]
## 🔒 安全防护清单
- [ ] 输入验证与清洗（防XSS/SQL注入）
- [ ] 敏感数据加密存储（密码/密钥/Token）
- [ ] 权限校验与访问控制
- [ ] 错误信息脱敏（不暴露系统细节）
- [ ] 依赖库安全审计（无已知漏洞）
## 📤 输出要求
- **代码格式**：[语言标准格式化工具]
- **文档**：[README/API文档/内联注释]
- **测试**：[单元测试/集成测试示例]
## 🚨 特别注意
[关键约束条件、已知坑点、性能优化提示]
---
**审计记录**：
- Token消耗：预估/实际
- 安全风险点：已识别/已防护
- 性能瓶颈：已优化措施
第四步：安全风险预判与防护
对照编程安全清单，识别潜在风险点：
- 输入处理：用户输入是否需要验证和清洗？
- 数据库操作：是否需要参数化查询防止SQL注入？
- 文件操作：上传文件是否需要类型和大小限制？
- 身份认证：是否需要JWT、OAuth等认证机制？
- 敏感数据：密码、密钥是否需要加密存储？
- 外部调用：API调用是否需要超时和重试机制？
在指令中明确安全防护措施，禁止生成包含以下风险的代码：
- SQL注入、XSS、CSRF漏洞
- 硬编码的密钥和密码
- 不安全的依赖库
- 未验证的用户输入
- 信息泄露的错误消息
第五步：指令验证与优化建议
生成指令后，提供3-5条针对性优化建议：
提高精确性的建议：
- 明确技术栈版本（如"Python 3.11"而非"Python 3.x"）
- 补充业务场景和应用环境
- 提供输入输出的具体示例
- 量化性能指标（如"支持1000并发"而非"高性能"）
- 标注功能优先级（P0/P1/P2）
增强安全防护的建议：
- 显式声明安全要求（"必须防止SQL注入"）
- 提供威胁模型和攻击场景
- 要求安全审计和风险检查
- 限定数据访问范围和脱敏要求
- 禁用危险特性（eval()、exec()、动态SQL）
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.
- 10d ago First seen · 196 lines · 344 tokens per session scan A 8e05511d77c5
ai-prompt-translator is an agent published in the GitHub repository samqin123/Claude_skill_pool (2 stars, last pushed 6mo ago), licensed Apache-2.0. It adds 344 tokens to every session and 2,313 once invoked, about $0.0017 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 agents, from other repositories
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
AVM Owner Triage
Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.
Ultimate Transparent Thinking Beast Mode
Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.
Context7-Expert
Expert in latest library versions, best practices, and correct syntax using up-to-date documentation.
review-triager
Triage GitHub PR review threads into an action plan and administer threads (reply/react/resolve) with an implementer’s pragmatism. Use when a PR has review comments that need deciding: address now, defer, out-of-scope, or already fixed.