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 konglong87/methodology-skills --skill prompt-enhancergit clone --depth 1 https://github.com/konglong87/methodology-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/konglong87/methodology-skills/prompt-enhancer)<a href="https://agentmods.dev/skills/konglong87/methodology-skills/prompt-enhancer"><img src="https://agentmods.dev/badge/skills/konglong87/methodology-skills/prompt-enhancer/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/konglong87/methodology-skills/prompt-enhancer"><img src="https://agentmods.dev/badge/skills/konglong87/methodology-skills/prompt-enhancer.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 | $0.00024 | $0.04311 |
| Opus 5 | $0.00012 | $0.02155 |
| Sonnet 5 | $0.00005 | $0.00862 |
| Haiku 4.5 | $0.00002 | $0.00431 |
Grade A, and why
prompt-enhancer 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 11d 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 — 587 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Prompt Enhancer - 需求细化与方案探索
前置协议
强制触发规则
触发时机:goal-oriented 创建目标后(强制)
触发条件(满足任一即触发):
- ✅ 用户需求模糊(单句请求、缺少上下文)
- ✅ 用户需求不完整(缺少关键维度)
- ✅ 用户需求有歧义(多种理解可能)
- ✅ 用户需求缺少成功标准
- ✅ 复杂任务(涉及多个模块/系统)
例外情况:
- 用户明确表示"按你的理解执行"
- 需求已经非常清晰明确
- 用户在调整已有目标
Overview
prompt-enhancer 是强制前置技能,负责需求细化和方案探索。通过结构化提问,确保充分理解用户需求,探索多种可行方案,避免理解偏差和执行返工。
核心能力:
- 需求细化:澄清模糊点、发现隐藏需求、明确范围边界
- 方案探索:头脑风暴多种方案、分析优劣势、风险评估
- 确认机制:每个关键点问用户3-4个问题确认理解
核心原则:澄清优先,行动在后。猜测定浪费,提问才高效。
关键价值:
- 避免理解偏差,减少返工
- 充分论证方案,选择最优解
- 发现隐藏需求,避免遗漏
- 节省 token 和时间
When to Use
强制使用场景:
- 用户需求模糊或不完整
- 复杂任务(涉及多个模块/系统)
- 需求有歧义或多种理解可能
- 缺少成功标准或约束条件
不使用场景:
- 用户明确表示"按你的理解执行"
- 需求已经非常清晰明确
- 用户在调整已有明确目标
- 简单的澄清性问题本身
The Process
digraph prompt_enhancer {
rankdir=TB;
"接收用户需求" [shape=box, style=filled, fillcolor="#c8e6c9"];
"识别需求类型" [shape=box, style=filled, fillcolor="#bbdefb"];
"需求细化(3-4问题)" [shape=box, style=filled, fillcolor="#fff9c4"];
"用户确认需求" [shape=diamond, style=filled, fillcolor="#e1bee7"];
"方案探索(头脑风暴)" [shape=box, style=filled, fillcolor="#ff9800"];
"多方案对比分析" [shape=box, style=filled, fillcolor="#ff9800"];
"用户选择方案" [shape=diamond, style=filled, fillcolor="#e1bee7"];
"生成需求方案工件" [shape=box, style=filled, fillcolor="#81c784"];
"传递给后续技能" [shape=doublecircle, style=filled, fillcolor="#81c784"];
"接收用户需求" -> "识别需求类型";
"识别需求类型" -> "需求细化(3-4问题)";
"需求细化(3-4问题)" -> "用户确认需求";
"用户确认需求" -> "方案探索(头脑风暴)" [label="确认"];
"用户确认需求" -> "需求细化(3-4问题)" [label="调整"];
"方案探索(头脑风暴)" -> "多方案对比分析";
"多方案对比分析" -> "用户选择方案";
"用户选择方案" -> "生成需求方案工件" [label="选择"];
"用户选择方案" -> "方案探索(头脑风暴)" [label="重新探索"];
"生成需求方案工件" -> "传递给后续技能";
}
步骤1:识别需求类型
快速识别请求类型,应用对应的细化框架:
| 需求类型 | 关键词 | 必问维度 |
|---|---|---|
| 功能开发 | "做个功能"、"实现XX" | 平台、技术栈、用户、数据、认证 |
| 架构设计 | "设计系统"、"重构架构" | 规模、性能、可扩展性、技术选型 |
| 性能优化 | "优化性能"、"提升速度" | 目标指标、优化范围、优先级 |
| Bug修复 | "修复bug"、"解决错误" | 复现步骤、影响范围、优先级 |
| UI/界面 | "设计界面"、"做个页面" | 设备、风格、用户、交互 |
| 数据分析 | "分析数据"、"生成报告" | 数据源、分析维度、输出格式 |
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.
- 11d ago First seen · 587 lines · 24 tokens per session scan A 68a45998d5a0
prompt-enhancer is a skill published in the GitHub repository konglong87/methodology-skills (5 stars, last pushed 1mo ago), licensed MIT. It adds 24 tokens to every session and 4,311 once invoked, about $0.0001 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
omh-llm-app-dev
This is a Hermes-native llm-app-dev workflow skill.
omh-model-setup
This is a Hermes-native model-setup workflow skill.
omh-model-optimization
This is a Hermes-native model-optimization workflow skill.
model-onboarding
Onboard a new model generation or sibling into oh-my-hermes: probe router recognition, research the official contract, write trait-to-counter calibration, place routing in both lanes, price from documented list only, gate machine config on a served route, prove with the gates, close with a benchmark pair. Use when a…
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.
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.