/install airadar
Thesis
Treat today’s AI tooling and GitHub traction as complementary data streams for technological momentum: the stories, raises, and features that command attention and the repos whose star graphs are climbing fastest together reveal where value, community trust, and experimentation are accelerating. The purpose of this skill is to keep that thesis front and center—every summary should answer “why does this tool/repo matter now?” and “what does its trajectory say about the broader AI ecosystem?”
Workflow
- Collect the canonical signals: prioritize AI-only tools or apps with news hooks (big raises, novel features, product launches, or widespread hype). For GitHub, retrieve trending lists or star history (
GitHub Explore,octoverse, etc.) to identify repos showing rapid-star growth or new surges in contributions. - Evaluate momentum vs. noise: for each item, note the concrete trigger (e.g., funding round, major feature, notable integration, release notes) and pair it with a metric (funding amount, feature scope, star velocity, ecosystem mentions). Highlight why the story feels like a game changer or an inflection point.
- Frame the insight: weave a short thesis paragraph (~1-2 sentences) that links the tool/app news to the repo signal—e.g., “As
project Xreceives €XXM, its GitHub repo moved into the top trending slot, suggesting the community is rallying behind that capability.” - Structure the output: separate sections for “Tools & Apps” and “GitHub Radar,” each listing 3–5 items with bullets for the what/why/metric. End with a “What to Watch” note that flags one emerging pattern or repo to revisit soon.
- Source transparently: cite URLs or data (news links, GitHub URLs, star counts) next to each bullet so follow-up research is straightforward.
Style and Tone
- Be analytical, not just descriptive. Use verbs like “signals,” “reinforces,” “propels,” and “tests” to keep the prose active.
- Keep each entry concise (2–3 sentences) but layered: mention the news, what changed, and the broader implication.
- If a tool or repo contradicts the thesis (e.g., hype without traction), note that tension rather than ignoring it.
When to Trigger
Invoke this skill whenever a user wants an update on AI tools, apps, or GitHub movements, especially if they ask for “interesting” or “fast-growing” innovations, big raises, or “game changing” features. It also applies when they request analytical summaries that connect product moves with developer momentum.
- 确保已安装 OpenClaw(本地或 Docker 部署)
- 在对话框中输入安装命令:
/install airadar - 安装完成后,直接呼叫该 Skill 的名称或使用
/airadar触发 - 根据 Skill 的参数说明提供必要输入,即可获得结构化输出
ai-github-radar 是什么?
Tracks and analyzes AI-native tools and GitHub repos with fast growth or major updates to reveal emerging trends in AI workflows and ecosystems. 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件,目前累计下载 1259 次。
如何安装 ai-github-radar?
在 OpenClaw 或 Claude Code 对话框中运行命令「/install airadar」即可一键安装,无需额外配置。
ai-github-radar 是免费的吗?
是的,ai-github-radar 完全免费(开源免费),可自由下载、安装和使用。
ai-github-radar 支持哪些平台?
ai-github-radar 跨平台运行,可在任意部署了 OpenClaw / Claude Code 的环境中使用(cross-platform)。
谁开发了 ai-github-radar?
由 Yuri(@lopushok9)开发并维护,当前版本 v1.0.0。