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/superPM --skill prompt-pegit clone --depth 1 https://github.com/konglong87/superPMWrote 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/superpm/prompt-pe)<a href="https://agentmods.dev/skills/konglong87/superpm/prompt-pe"><img src="https://agentmods.dev/badge/skills/konglong87/superpm/prompt-pe/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/superpm/prompt-pe"><img src="https://agentmods.dev/badge/skills/konglong87/superpm/prompt-pe.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 | $0.00047 | $0.06421 |
| Opus 5.5 | $0.00019 | $0.02568 |
| Sonnet 5.5 | $0.00009 | $0.01284 |
| Haiku 4.5 | $0.00005 | $0.00642 |
Grade A, and why
prompt-pe 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.
How it starts
The opening of the file, as written. The whole thing — 667 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Prompt PE(提示词具象化增强器)
Overview
本技能只负责把自然语言需求澄清、具象化并结构化,不替代后续业务技能,也不自动进入任何 superPM 工作流。
核心原则:澄清优先,行动在后。猜测定浪费,提问才高效。
用户常见问题:
- 自然语言太笼统,缺少结构化思维
- 把 AI 当"一句话万能魔法神器"
- 关键信息缺失,导致反复沟通,浪费 token 和时间
当用户请求模糊时,AI 倾向于:
- 做假设而非提问
- 探索而非澄清
- 加速而非减速
本技能提供:
- 场景识别 - 快速识别请求类型(功能开发、UI设计、绘图等)
- 领域澄清模板 - 针对不同场景的结构化问题清单
- 系统化框架 - 5W1H 维度 + 优先级提问策略
目标是:帮助用户在早期完全明确需求和目的,高效率、节省能量、快乐使用 AI、节省 token。
When to Use
使用场景:
- 单句请求无上下文:"做个登录功能"
- 缺少关键维度:谁用?什么平台?为什么?有什么约束?
- 无成功标准:"优化代码"、"重构项目"
- 紧急+模糊:"快速修复 bug"、"赶紧优化"
- 用户期望 AI 自动理解一切
不使用场景:
- 需求清晰明确,包含足够上下文和约束
- 用户明确表示"先看看你的建议"
- 请求是澄清性问题本身
场景识别 (Scenario Recognition)
快速识别请求类型,应用对应的澄清模板:
| 场景类型 | 关键词/模式 | 必问维度 |
|---|---|---|
| 功能开发 | "做个功能"、"写个模块"、"实现XX" | 平台、技术栈、认证方式、数据存储 |
| UI/界面设计 | "设计界面"、"做个页面"、"UI" | 设备、风格、配色、交互、用户画像 |
| 图像生成 | "画个画"、"生成图片"、"AI绘图" | 风格、尺寸、主体、背景、色调、用途 |
| 代码优化 | "优化代码"、"提升性能" | 目标(性能/可读性/内存)、当前问题、成功标准 |
| Bug 修复 | "修复bug"、"报错了"、"有问题" | 错误信息、复现步骤、预期行为、影响范围 |
| 重构项目 | "重构项目"、"优化架构" | 动机、痛点、范围、约束、成功标准 |
| 数据分析 | "分析数据"、"统计XX" | 数据源、时间范围、维度、输出格式 |
识别后立即应用对应的澄清模板(见下节)。
领域特定澄清模板 (Domain-Specific Templates)
🎯 功能开发场景
示例: 用户说"帮我写一个登录功能"
必问问题:
1. **平台**: Web、移动端(iOS/Android)、桌面应用?
2. **认证方式**: 用户名密码、OAuth(Google/微信/GitHub)、手机验证码、SSO?
3. **技术栈**: 前端框架(React/Vue/Angular)?后端(Node/Java/Go/Python)?
4. **功能范围**:
- 仅登录?还是包含注册、登出、密码重置?
- 是否需要"记住我"、多设备登录、单点登录?
5. **安全要求**: 2FA、密码复杂度、登录失败锁定、防暴力破解?
6. **数据存储**: 数据库类型(MySQL/MongoDB/PostgreSQL)?Session 还是 JWT?
澄清效率对比:
- ❌ 不澄清直接做 → 假设 Web + 用户名密码 → 用户要的是移动端 OAuth → 全部返工
- ✅ 澄清 30 秒 → 明确移动端 + OAuth + JWT → 一次性做对,节省数小时
🎨 图像生成场景
示例: 用户说"帮我画一个画画"
必问问题:
1. **主体内容**: 画什么?人物、风景、物品、抽象艺术?
2. **画面风格**: 写实、卡通、油画、水彩、赛博朋克、日系动漫、像素风?
3. **尺寸比例**: 竖版(9:16)、横版(16:9)、方形(1:1)?具体像素?
4. **色调配色**: 暖色调、冷色调、黑白、高饱和、莫兰迪色?
5. **背景**: 纯色、渐变、具体场景(海边/城市/森林)?
6. **细节要求**: 光线(日光/夕阳/霓虹)、视角(正面/侧面/俯视)?
7. **用途**: 头像、海报、插画、产品图?(影响风格和质量要求)
澄清示例:
用户:帮我画一个画画
AI:我需要澄清几个关键点来精准创作:
1. **主体**: 人物、风景、还是抽象艺术?
2. **风格**: 写实、卡通、油画、赛博朋克、日系动漫?
3. **尺寸**: 竖版、横版、还是方形?
4. **色调**: 暖色、冷色、黑白、还是鲜艳色彩?
5. **用途**: 头像、海报、插画?(影响细节程度)
只需要回答这 5 个问题,我就能生成符合你期望的图像。
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 · 667 lines · 47 tokens per session scan A 82d78893d4de
prompt-pe is a skill published in the GitHub repository konglong87/superPM (84 stars, last pushed yesterday), licensed MIT. It adds 47 tokens to every session and 6,421 once invoked, about $0.0002 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 2026-10-15.
Other skills, from other repositories
multi-search
A web-search helper that chooses among DuckDuckGo, Tavily, Bing API, and Bing scraping based on the available network.
freeride
Manages free AI models from OpenRouter for OpenClaw. Automatically ranks models by quality, configures fallbacks for rate-limit handling, and updates openclaw.json. Optional Groq, Gemini and Cerebras free tiers are opt-in. Use when the user mentions free AI, OpenRouter, model switching, rate limits, or wants to reduce…
deepsafe-scan
Preflight security scanner for AI coding agents — scans deployment config, skills/MCP servers, memory/sessions, and AI agent config files (hooks injection) for secrets, PII, prompt injection, and dangerous patterns. Runs 4 model behavior probes (persuasion, sandbagging, deception, hallucination). Supports LLM-enhanced…
team-tasks
Coordinate multi-agent development pipelines using shared JSON task files. Use when dispatching work across dev team agents (code-agent, test-agent, docs-agent, monitor-bot), tracking pipeline progress, or running sequential/parallel workflows. Covers project init, task assignment, status tracking, agent dispatch via…
douyin-upload-mcp-skill
A guide for publishing videos and image-and-text posts through Douyin's creator website. Douyin is a Chinese social-media platform, and the guide uses its creator platform and available MCP tools.
mapick
Mapick — Skill recommendation & privacy protection for OpenClaw. Scans your local skills, suggests what you're missing, and keeps other skills from seeing your sensitive data.