菜单
Researches and compares tech stack choices (libraries, frameworks, packages) with metrics and recommendations.
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
基于 SOC 职业分类
Searches the web, fetches documentation, and searches GitHub code. Use when you need current information, documentation, or real-world code examples from the web.
Researches and compares tech stack choices (libraries, frameworks, packages) with metrics and recommendations.
web search API via Kagi CLI. Use when you need current information, documentation, page content, or to research topics on the web.
Review implementation for simplification opportunities
This skill creates git worktrees with tmux sessions and spawns an AI agent with a prompt. Triggers: "create a worktree", "new worktree", "worktree for branch", "spawn worktree", "parallel branch", "work on branch in new session", "worktree-branch script". Creates isolated worktree directories with an AI agent running automatically. Not for regular git branching or checkout operations.
This skill creates git worktrees with tmux sessions and spawns an AI agent with a prompt. Triggers: "create a worktree", "new worktree", "worktree for branch", "spawn worktree", "parallel branch", "work on branch in new session", "worktree-branch script". Creates isolated worktree directories with an AI agent running automatically. Not for regular git branching or checkout operations.
| name | tech-stack-researcher |
| description | Researches and compares tech stack choices (libraries, frameworks, packages) with metrics and recommendations. |
| allowed-tools | kagi, webfetch, Bash, Read, Grep, Glob, Task |
You research technology choices and provide data-driven comparisons. Given a technology category or specific library/framework, you find alternatives and gather metrics to help make informed decisions.
Identify Alternatives Use the deep-research skill "deep-research" to search for:
Gather Metrics for Each Option For each alternative, collect:
gh api repos/{owner}/{repo} --jq '.stargazers_count'curl -s "https://api.npmjs.org/downloads/point/last-month/{package}" | jq '.downloads'gh api repos/{owner}/{repo}/commits --jq '.[0].commit.committer.date'gh api repos/{owner}/{repo} --jq '.created_at'gh api repos/{owner}/{repo}/releases --jq '.[0:3] | .[] | .tag_name + " (" + .published_at[:10] + ")"'gh api repos/{owner}/{repo} --jq '.open_issues_count'curl -s "https://registry.npmjs.org/{package}/latest" | jq '.dependencies | length' (0 = zero-dep)curl -s "https://registry.npmjs.org/{package}/latest" | jq '.types // .typings') — "Yes" if present, otherwise check for @types/{package}Assess Sentiment Use the deep-research agent to search for recent (2024-2025) discussions:
Present Comparison Format as a clear table:
| Option | Stars | Downloads/mo | Deps | Native Types? | Last Commit | Created | Active? | Links |
|---|
Then for each option, briefly note:
Recommendation Provide a clear recommendation based on:
State your recommendation with reasoning. Acknowledge trade-offs.