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 ryanzhao1011/workframe --skill prompt-designgit clone --depth 1 https://github.com/ryanzhao1011/workframeWrote 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/ryanzhao1011/workframe/prompt-design)<a href="https://agentmods.dev/skills/ryanzhao1011/workframe/prompt-design"><img src="https://agentmods.dev/badge/skills/ryanzhao1011/workframe/prompt-design.svg" alt="Measured on agentmods" 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 | $0.00034 | $0.01321 |
| Opus 5 | $0.00017 | $0.00660 |
| Sonnet 5 | $0.00007 | $0.00264 |
| Haiku 4.5 | $0.00003 | $0.00132 |
Grade A, and why
prompt-design 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 7d 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 — 179 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Prompt 设计技能
适用场景
- 为新场景设计 Prompt
- 优化现有 Prompt(准确性/稳定性/成本)
- 将业务需求转化为 AI 交互方案
五步流程
第 1 步:场景分析
在设计 Prompt 前,先澄清场景:
| 维度 | 核心问题 |
|---|---|
| 目标用户 | 谁会使用这个 Prompt 生成的输出? |
| 使用场景 | 在什么业务流程中被调用? |
| 期望输出 | 输出的格式、长度、质量要求? |
| 约束条件 | 不能输出什么?安全/合规/品牌要求? |
| 成本/延迟 | 对响应时间和 token 成本的要求? |
信息不足时使用 [待确认: {说明}] 占位。
第 2 步:Prompt 架构设计
按分层架构设计:
┌─────────────────────────────────┐
│ System Instruction(系统指令) │
│ - 角色定义 │
│ - 能力边界 │
│ - 输出格式约束 │
│ - 安全红线 │
├─────────────────────────────────┤
│ Context Injection(上下文注入) │
│ - 业务数据 │
│ - 历史对话 │
│ - 检索结果 │
├─────────────────────────────────┤
│ User Instruction(用户指令) │
│ - 具体任务 │
│ - 用户输入 │
└─────────────────────────────────┘
每层的设计要点:
| 层级 | 设计要点 |
|---|---|
| System | 角色明确、能力清晰、格式严格、红线不可越 |
| Context | 结构化、去噪、按相关性排序 |
| User | 具体、可操作、避免歧义 |
第 3 步:变量接口定义
把 Prompt 中需要动态替换的部分抽象为变量:
variables:
- name: user_input
type: string
required: true
description: "用户输入的原始文本"
max_length: 2000
- name: style_tone
type: enum
required: false
default: "neutral"
values: ["formal", "casual", "neutral"]
description: "输出文本的语气"
设计原则:
- 变量名自解释
- 类型明确,有范围约束
- 必填/选填标注
- 默认值安全
第 4 步:版本管理
每个 Prompt 方案标注版本信息:
## Prompt: {name} v{version}
- **版本**:v1.2
- **上一版本**:v1.1
- **变更理由**:{为什么改}
- **与前版差异**:
- 新增:{...}
- 修改:{...}
- 删除:{...}
- **预期影响**:{对输出质量、成本、延迟的预期影响}
第 5 步:风险评估
评估 Prompt 的潜在风险:
| 风险类型 | 检查点 |
|---|---|
| Prompt 注入 | 用户输入能否突破 System 指令? |
| 输出失控 | 是否可能输出违规/有害/错误内容? |
| 幻觉 | 是否有机制防止编造事实? |
| 边界行为 | 极端输入(超长/空/非预期格式)如何处理? |
| 成本失控 | 是否有 token 上限?是否可能陷入循环? |
| 敏感信息 | System Prompt 是否可能被泄露给用户? |
输出模板
# Prompt 方案:{name} v{version}
## 1. 场景分析
- 目标用户:{...}
- 使用场景:{...}
- 期望输出:{...}
- 约束条件:{...}
## 2. 架构设计
### System Instruction
{system prompt}
### Context Schema
{context template}
### User Instruction Template
{user prompt template}
## 3. 变量接口
{variables yaml}
## 4. 版本信息
{version info}
## 5. 风险评估
{risk table}
## 6. 示例
### 输入
{example input}
### 期望输出
{example output}
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.
- 7d ago First seen · 179 lines · 34 tokens per session scan A 74012e58efcc
prompt-design is a skill published in the GitHub repository ryanzhao1011/workframe (4 stars, last pushed 20d ago), licensed MIT. It adds 34 tokens to every session and 1,321 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
ai-automation
Workflow automation skills using AI. Build chatbots, automate repetitive tasks, integrate LLMs into pipelines, design intent-based assistants. Triggers on: chatbot, automation, workflow, AI agent, RAG, LLM integration, intent recognition, conversation design.
optimize
Rephrase a rough prompt to follow prompt-engineering best practices WITHOUT changing its meaning, then show it for review without executing. Use when the user runs /petprompt:optimize or asks to rewrite/clean up/optimize their prompt before running it.
cursor-prompting
Prompt shaping rules for delegated cursor-agent tasks.
agent-orchestration-improve-agent
Systematic improvement of existing agents through performance analysis, prompt engineering, and continuous iteration.
prompt-cookbook
Build a prompt cookbook for one company's actual vertical and roles rather than generic examples. Each recipe names the job it does, who runs it, the prompt itself, what good output looks like, and how to tell when it went wrong. Written for people who have never written a prompt and will not read documentation about…
pentest-llm
LLM application red team — OWASP LLM Top 10, prompt injection, RAG poisoning, MCP server abuse, agent tool abuse, jailbreak testing advisory. Triggers on LLM red team, prompt injection, jailbreak, RAG poisoning, OWASP LLM Top 10, MCP abuse, agent tool abuse, AI security testing.