project-idea-validator

Compare original and translation side by side

🇺🇸

Original

English

🇨🇳

Translation

Chinese

Project Idea Validator — Discover What Already Exists Before You Build

项目创意验证工具 — 动手开发前先了解已有成果

You have access to the TinyFish CLI (

tinyfish

), a tool that runs browser automations from the terminal using natural language goals. This skill uses it to search GitHub and Dev.to in parallel, then synthesizes results into a gap analysis report.

你可以使用TinyFish CLI（

tinyfish

），这是一个通过自然语言目标在终端运行浏览器自动化的工具。本技能会用它并行搜索GitHub和Dev.to，然后将结果合成为差距分析报告。

Pre-flight Check (REQUIRED)

前置检查（必填）

Before making any TinyFish call, always run BOTH checks:

1. CLI installed?

PowerShell:

powershell

Get-Command tinyfish; tinyfish --version

bash/zsh:

bash

which tinyfish && tinyfish --version || echo "TINYFISH_CLI_NOT_INSTALLED"

If not installed, stop and tell the user:

Install the TinyFish CLI:
npm install -g @tiny-fish/cli

2. Authenticated?

powershell

tinyfish auth status

If not authenticated, stop and tell the user:

You need a TinyFish API key. Get one at: https://agent.tinyfish.ai/api-keys

Then authenticate:

Option 1 — CLI login (interactive):
tinyfish auth login
Option 2 — PowerShell (current session only):
powershell
$env:TINYFISH_API_KEY="your_api_key_here"
Option 3 — PowerShell (persist across sessions):
powershell
[System.Environment]::SetEnvironmentVariable("TINYFISH_API_KEY", "your_api_key_here", "User")
Then close and reopen PowerShell for it to take effect.

Option 4 — bash/zsh (Mac/Linux):
bash
export TINYFISH_API_KEY="your_api_key_here"
Option 5 — Claude Code settings: Add to
~/.claude/settings.local.json
:
json
{
  "env": {
    "TINYFISH_API_KEY": "your_api_key_here"
  }
}

Do NOT proceed until both checks pass.

在调用任何TinyFish命令前，务必完成以下两项检查：

1. 是否已安装CLI？

PowerShell：

powershell

Get-Command tinyfish; tinyfish --version

bash/zsh：

bash

which tinyfish && tinyfish --version || echo "TINYFISH_CLI_NOT_INSTALLED"

如果未安装，请停止操作并告知用户：

安装TinyFish CLI：
npm install -g @tiny-fish/cli

2. 是否已完成认证？

powershell

tinyfish auth status

如果未认证，请停止操作并告知用户：

你需要一个TinyFish API密钥。请前往以下地址获取：https://agent.tinyfish.ai/api-keys

然后进行认证：

选项1 — CLI登录（交互式）：
tinyfish auth login
选项2 — PowerShell（仅当前会话）：
powershell
$env:TINYFISH_API_KEY="your_api_key_here"
选项3 — PowerShell（跨会话持久化）：
powershell
[System.Environment]::SetEnvironmentVariable("TINYFISH_API_KEY", "your_api_key_here", "User")
然后关闭并重新打开PowerShell使设置生效。

选项4 — bash/zsh（Mac/Linux）：
bash
export TINYFISH_API_KEY="your_api_key_here"
选项5 — Claude Code设置： 添加至
~/.claude/settings.local.json
：
json
{
  "env": {
    "TINYFISH_API_KEY": "your_api_key_here"
  }
}

必须在两项检查都通过后才能继续。

What This Skill Does

本技能的功能

Given a project idea (e.g. "a CLI tool that converts Figma designs to Tailwind components"), this skill:

Searches GitHub for existing repos with similar purpose, tech stack, or keywords
Searches Dev.to for articles, tutorials, or project showcases covering the same problem

It then synthesizes findings into a structured gap analysis: what exists, how mature it is, and where the opportunity still lives.

给定一个项目创意（例如："将Figma设计转换为Tailwind组件的CLI工具"），本技能会：

在GitHub上搜索具有相似用途、技术栈或关键词的现有仓库
在Dev.to上搜索涵盖同一问题的文章、教程或项目展示

随后将结果合成为结构化的差距分析：已有哪些成果、领域成熟度如何，以及仍存在哪些机会。

Core Command

核心命令

bash

tinyfish agent run --url <url> "<goal>"

bash

tinyfish agent run --url <url> "<goal>"

Flags

标志

Flag	Purpose
`--url <url>`	Target website URL
`--sync`	Wait for full result (no streaming)
`--async`	Submit and return immediately
`--pretty`	Human-readable formatted output

标志	用途
`--url <url>`	目标网站URL
`--sync`	等待完整结果（无流式输出）
`--async`	提交后立即返回
`--pretty`	生成人类可读的格式化输出

Step-by-Step Workflow

分步工作流程

Step 1 — Search GitHub

步骤1 — 搜索GitHub

Search for existing repositories matching the idea. Run with

--sync

since you need the full list before synthesizing.

bash

tinyfish agent run --sync --url "https://github.com/search?q=<keywords>&type=repositories&s=stars&o=desc" \
  "Extract the top 10 search results as JSON: [{\"name\": str, \"owner\": str, \"description\": str, \"stars\": str, \"url\": str, \"last_updated\": str}]"

Example for a Figma-to-Tailwind CLI idea:

bash

tinyfish agent run --sync \
  --url "https://github.com/search?q=figma+tailwind+cli&type=repositories&s=stars&o=desc" \
  "Extract the top 10 repositories as JSON: [{\"name\": str, \"owner\": str, \"description\": str, \"stars\": str, \"url\": str, \"last_updated\": str}]"

搜索与创意匹配的现有仓库。使用

--sync

标志，因为你需要完整列表才能进行结果合成。

bash

tinyfish agent run --sync --url "https://github.com/search?q=<keywords>&type=repositories&s=stars&o=desc" \
  "Extract the top 10 search results as JSON: [{\"name\": str, \"owner\": str, \"description\": str, \"stars\": str, \"url\": str, \"last_updated\": str}]"

Figma转Tailwind CLI创意的示例：

bash

tinyfish agent run --sync \
  --url "https://github.com/search?q=figma+tailwind+cli&type=repositories&s=stars&o=desc" \
  "Extract the top 10 repositories as JSON: [{\"name\": str, \"owner\": str, \"description\": str, \"stars\": str, \"url\": str, \"last_updated\": str}]"

Step 2 — Search Dev.to

步骤2 — 搜索Dev.to

Search for articles and project posts covering the same problem space. Run in parallel with Step 1 results processing.

bash

tinyfish agent run --sync --url "https://dev.to/search?q=<keywords>" \
  "Extract the top 10 articles as JSON: [{\"title\": str, \"author\": str, \"tags\": [str], \"published_at\": str, \"url\": str, \"reactions\": str}]"

Example:

bash

tinyfish agent run --sync \
  --url "https://dev.to/search?q=figma+tailwind+component+generator" \
  "Extract the top 10 articles as JSON: [{\"title\": str, \"author\": str, \"tags\": [str], \"published_at\": str, \"url\": str, \"reactions\": str}]"

搜索涵盖同一问题领域的文章和项目帖子。与步骤1的结果处理并行执行。

bash

tinyfish agent run --sync --url "https://dev.to/search?q=<keywords>" \
  "Extract the top 10 articles as JSON: [{\"title\": str, \"author\": str, \"tags\": [str], \"published_at\": str, \"url\": str, \"reactions\": str}]"

示例：

bash

tinyfish agent run --sync \
  --url "https://dev.to/search?q=figma+tailwind+component+generator" \
  "Extract the top 10 articles as JSON: [{\"title\": str, \"author\": str, \"tags\": [str], \"published_at\": str, \"url\": str, \"reactions\": str}]"

Parallel Execution

并行执行

Steps 1 and 2 are independent — run them at the same time. Do NOT wait for GitHub before starting Dev.to.

Good — Parallel calls:

bash

undefined

步骤1和步骤2相互独立——应同时运行。不要等待GitHub搜索完成后再启动Dev.to搜索。

正确做法 — 并行调用：

bash

undefined

Fire both simultaneously

同时触发两个调用

tinyfish agent run --sync --url "https://github.com/search?q=<keywords>&type=repositories&s=stars&o=desc"
"Extract top 10 repositories as JSON: [{"name": str, "owner": str, "description": str, "stars": str, "url": str, "last_updated": str}]" &

tinyfish agent run --sync --url "https://dev.to/search?q=<keywords>"
"Extract top 10 articles as JSON: [{"title": str, "author": str, "url": str, "reactions": str}]" &

wait


**Bad — Sequential calls:**
```bash

tinyfish agent run --sync --url "https://dev.to/search?q=<keywords>"
"Extract top 10 articles as JSON: [{"title": str, "author": str, "url": str, "reactions": str}]" &

wait


**错误做法 — 顺序调用：**
```bash

Don't do this — wastes time and gives the same results

请勿这样做——浪费时间且结果相同

tinyfish agent run --url "https://github.com/..." "...also search Dev.to..."


Each source is its own call. Always.

---

tinyfish agent run --url "https://github.com/..." "...also search Dev.to..."


每个数据源都需要单独调用。务必遵守此规则。

---

Step 3 — Synthesize Into a Gap Analysis

步骤3 — 合成为差距分析报告

Once both sources return results, synthesize findings into this structure:

undefined

当两个数据源都返回结果后，将发现整理为以下结构：

undefined

Project Idea Validation: <idea title>

项目创意验证：<创意标题>

What Already Exists

已有成果

<project/article> — <what it does, stars/reactions, last active>
...

<项目/文章> — <功能介绍、星标/互动数、最后更新时间>
...

Maturity Assessment

成熟度评估

GitHub: <active / abandoned / fragmented>
Dev.to coverage: <heavy / moderate / sparse>

GitHub：<活跃 / 已废弃 / 碎片化>
Dev.to覆盖度：<密集 / 中等 / 稀疏>

Gaps & Opportunities

差距与机会

<specific gap #1>
<specific gap #2>
...

<具体差距1>
<具体差距2>
...

Verdict

结论

<1–2 sentences: is the space crowded, open, or ripe for a better take?>


Use the raw JSON from both sources as input. Do not hallucinate repo names, star counts, or article titles — only use what TinyFish returned.

---

<1-2句话：该领域是拥挤、开放还是值得推出更优方案？>


以两个数据源返回的原始JSON作为输入。请勿虚构仓库名称、星标数量或文章标题——仅使用TinyFish返回的内容。

---

Keyword Strategy

关键词策略

The quality of results depends heavily on your search terms. Before running, derive 2–3 keyword variants from the idea:

Idea	Primary keywords	Variant keywords
Figma-to-Tailwind CLI	`figma tailwind cli`	`figma css export` , `design token tailwind`
AI code review bot	`ai code review github`	`llm pull request` , `automated code feedback`
Markdown-to-Notion sync	`markdown notion sync`	`notion import cli` , `notion api markdown`

Run separate parallel calls for each variant if the first pass returns sparse results.

结果的质量很大程度上取决于搜索词。在运行搜索前，从创意中衍生2-3个关键词变体：

创意	核心关键词	变体关键词
Figma转Tailwind CLI	`figma tailwind cli`	`figma css export` , `design token tailwind`
AI代码审查机器人	`ai code review github`	`llm pull request` , `automated code feedback`
Markdown转Notion同步工具	`markdown notion sync`	`notion import cli` , `notion api markdown`

如果首次搜索结果稀疏，请针对每个变体分别进行并行调用。

Managing Runs

运行管理

bash

undefined

bash

undefined

List recent runs

列出最近的运行记录

tinyfish agent run list

Get a specific run by ID

通过ID获取特定运行记录

tinyfish agent run get <run_id>

Cancel a running automation

取消正在运行的自动化任务

tinyfish agent run cancel <run_id>

---

tinyfish agent run cancel <run_id>

---

Output

输出

The CLI streams

data: {...}

SSE lines by default. The final result is the event where

type == "COMPLETE"

and

status == "COMPLETED"

— the extracted data is in the

resultJson

field. Read the raw output directly; no script-side parsing is needed.

CLI默认会流式输出

data: {...}

格式的SSE行。最终结果是

type == "COMPLETE"

且

status == "COMPLETED"

的事件——提取的数据位于

resultJson

字段中。直接读取原始输出即可；无需在脚本端进行解析。