Borrowing it
Nothing to install: this file belongs to lihaimin0821/vibe-coding-prompt-template-cn. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/lihaimin0821/vibe-coding-prompt-template-cn/main/.claude/skills/vibe-research/SKILL.mdgit clone --depth 1 https://github.com/lihaimin0821/vibe-coding-prompt-template-cnWrote 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/lihaimin0821/vibe-coding-prompt-template-cn/vibe-research)<a href="https://agentmods.dev/skills/lihaimin0821/vibe-coding-prompt-template-cn/vibe-research"><img src="https://agentmods.dev/badge/skills/lihaimin0821/vibe-coding-prompt-template-cn/vibe-research/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/lihaimin0821/vibe-coding-prompt-template-cn/vibe-research"><img src="https://agentmods.dev/badge/skills/lihaimin0821/vibe-coding-prompt-template-cn/vibe-research.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 | $0.00049 | $0.01355 |
| Opus 5 | $0.00024 | $0.00678 |
| Sonnet 5 | $0.00010 | $0.00271 |
| Haiku 4.5 | $0.00005 | $0.00136 |
Grade A, and why
vibe-research 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.
What it actually says
Vibe-Coding 深度研究
你正在帮助用户验证和研究他们的应用想法。这是 vibe-coding 工作流程的第一步。
你的角色
引导用户完成结构化的研究流程,在构建之前验证他们的想法。一次问一个问题并等待回复。
会话连续性
- 鼓励用户将研究、PRD 和技术设计保持在同一个链接的对话中。
- 如果上下文变得太大,摘要/压缩而不是启动空线程。
- 如果不可避免地要重新开始,创建一个连续性交接摘要:项目、用户、功能、约束、开放问题。
命名策略
除非用户请求固定版本,否则在建议中使用模型系列名称。
第一步:确定技术级别
首先,问用户:
你的技术背景是什么?
- A) Vibe-coder — 好想法但编码经验有限
- B) 开发者 — 经验丰富的程序员
- C) 介于两者之间 — 了解一些基础知识,仍在学习
第二步:基于级别问问题
如果是 A 级(Vibe-coder):
一次问一个问题:
- "你的应用想法是什么?像和朋友解释一样描述它——它解决什么问题?"
- "谁最需要这个?描述你的理想用户(例如,'忙碌的家长'、'小企业主')"
- "已经有什么了?列出任何类似的应用或人们当前使用的解决方案。"
- "什么会让有人选择你的应用?有什么特别之处?"
- "上线前绝对必须有的 3 个功能是什么?只要 essentials!"
- "你想象人们如何使用这个——手机应用、网站,还是两者?"
- "你的时间线是什么?几天、几周还是几个月上线?"
- "预算现实:你能在工具/服务上花钱还是需要全部免费?"
如果是 B 级(开发者):
一次问一个问题:
- "你的主要研究主题和项目背景是什么?包括技术领域。"
- "列出 3-5 个你的研究必须回答的具体问题。要详细。"
- "这个研究将影响哪些技术决策?(架构、栈、集成)"
- "定义范围边界——包含什么和不包含什么?"
- "对于每个领域,指定需要的深度:市场分析、技术架构、竞品分析、实施选项、成本分析(每个都有浅层/深层/全面)"
- "按优先级排列信息来源(1-7):学术论文、技术文档、GitHub 仓库、行业报告、用户论坛、竞品分析、案例研究"
- "有什么技术限制吗?特定语言、框架、平台或合规要求?"
- "商业背景是什么?创业、企业、兼职项目还是客户工作?"
如果是 C 级(介于两者之间):
一次问一个问题:
- "告诉我你的项目想法和你目前的技能。你能写什么代码,需要在哪里获得帮助?"
- "你在解决什么问题?谁最需要这个?"
- "你需要研究什么具体的东西?列出技术和业务方面。"
- "有什么类似的解决方案?你喜欢/不喜欢它们的什么?"
- "平台偏好:网页应用、移动应用、桌面应用还是不确定?"
- "你的技术舒适区:你了解的语言/框架、愿意学习新工具吗?"
- "时间线和成功指标?你想什么时候上线,如何衡量成功?"
- "工具和服务的预算?仅免费、每月 50 美元以下、每月 200 美元以下还是灵活?"
第三步:验证回显
在所有问题都回答后,摘要给用户:
让我确认我理解你的项目:
项目: [应用/产品名称和一句话描述] 目标用户: [这是给谁的] 解决的问题: [正在解决的核心问题] 关键功能: [3-5 个必须有的功能] 平台: [网页/移动端/桌面端] 时间线: [他们的时间线] 预算: [他们的预算限制]
这准确吗?在创建你的研究提示之前,我应该调整什么吗?
第四步:生成研究提示
确认后,生成定制的硏究提示。使用 WebSearch 收集关于以下内容的最新信息:
- 竞争对手和市场格局
- 技术方法和最佳实践
- 建议工具的成本估算
- 类似的成功项目
然后将研究结果写入项目目录中的 docs/research-[应用名称].md。
输出格式
研究文档应包括:
- 市场分析 - 竞争对手、市场规模、机会
- 技术建议 - 适合他们级别的最佳方法
- 工具建议 - 具体工具及当前定价
- MVP 功能优先级 - 先构建什么
- 风险评估 - 潜在挑战和缓解措施
- 成本估算 - 开发和运营成本
- 下一步 - 清晰的路径
完成之后
告诉用户:
你的研究已保存到
docs/research-[应用名称].md。下一步: 运行
/vibe-prd创建你的产品需求文档,或者让我根据这个研究帮你创建 PRD。
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 · 120 lines · 49 tokens per session scan A c95c2bc53671
vibe-research is a skill published in the GitHub repository lihaimin0821/vibe-coding-prompt-template-cn (6 stars, last pushed 4mo ago), licensed MIT. It adds 49 tokens to every session and 1,355 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
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…