Ralph
opentabs-dev/opentabs
Plan work and generate ralph task files for autonomous execution.
案例雷达。给一个新东西(新工具/新概念/新生态),扫一遍生态找好玩的真实案例,重点是抓"真物"(截图/源码/演示)而不是 GitHub 主页,输出可浏览的 HTML 案例集。当用户说"看看大家用 X 做了什么"、"扫一下 X 生态"、"市面上 X 有什么新玩法"、"给我看 X 的真物案例"、"/case-radar"时触发。不适合:① 已有明确目标的深度调研(使用可用的调研工具直接研究)②…
$ npx skills add yunshu0909/yunshu_skillshub --skill case-radar -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install yunshu0909/yunshu_skillshub case-radar --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/yunshu0909/yunshu_skillshub.git skills-src && mkdir -p .claude/skills && cp -r skills-src/visualization/case-radar .claude/skills/case-radar && rm -rf skills-srcUse ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.
Claude Code skills documentation · loads skills from .claude/skills/
Install the "case-radar" agent skill from https://github.com/yunshu0909/yunshu_skillshub/tree/master/visualization/case-radar into .claude/skills/case-radar/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "case-radar", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/yunshu0909/yunshu_skillshub/tree/master/visualization/case-radarType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add yunshu0909/yunshu_skillshub --skill case-radar -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install yunshu0909/yunshu_skillshub case-radar --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/yunshu0909/yunshu_skillshub.git skills-src && mkdir -p .agents/skills && cp -r skills-src/visualization/case-radar .agents/skills/case-radar && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "case-radar" agent skill from https://github.com/yunshu0909/yunshu_skillshub/tree/master/visualization/case-radar into .agents/skills/case-radar/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "case-radar", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add yunshu0909/yunshu_skillshub --skill case-radar -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install yunshu0909/yunshu_skillshub case-radar --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/yunshu0909/yunshu_skillshub.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/visualization/case-radar .cursor/skills/case-radar && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "case-radar" agent skill from https://github.com/yunshu0909/yunshu_skillshub/tree/master/visualization/case-radar into .cursor/skills/case-radar/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "case-radar", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/yunshu0909/yunshu_skillshub.git --path visualization/case-radar--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add yunshu0909/yunshu_skillshub --skill case-radar -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install yunshu0909/yunshu_skillshub case-radar --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/yunshu0909/yunshu_skillshub.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/visualization/case-radar .gemini/skills/case-radar && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "case-radar" agent skill from https://github.com/yunshu0909/yunshu_skillshub/tree/master/visualization/case-radar into .gemini/skills/case-radar/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "case-radar", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install yunshu0909/yunshu_skillshub case-radarInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add yunshu0909/yunshu_skillshub --skill case-radar -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/yunshu0909/yunshu_skillshub.git skills-src && mkdir -p .github/skills && cp -r skills-src/visualization/case-radar .github/skills/case-radar && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "case-radar" agent skill from https://github.com/yunshu0909/yunshu_skillshub/tree/master/visualization/case-radar into .github/skills/case-radar/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "case-radar", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add yunshu0909/yunshu_skillshub --skill case-radar -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install yunshu0909/yunshu_skillshub case-radar --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/yunshu0909/yunshu_skillshub.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/visualization/case-radar .opencode/skills/case-radar && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "case-radar" agent skill from https://github.com/yunshu0909/yunshu_skillshub/tree/master/visualization/case-radar into .opencode/skills/case-radar/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "case-radar", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
case-radar案例雷达。给一个新东西(新工具/新概念/新生态),扫一遍生态找好玩的真实案例,重点是抓"真物"(截图/源码/演示)而不是 GitHub 主页,输出可浏览的 HTML 案例集。当用户说"看看大家用 X 做了什么"、"扫一下 X 生态"、"市面上 X 有什么新玩法"、"给我看 X 的真物案例"、"/case-radar"时触发。不适合:① 已有明确目标的深度调研(使用可用的调研工具直接研究)②…
Case Radar is an agent skill from yunshu0909/yunshu_skillshub. 案例雷达。给一个新东西(新工具/新概念/新生态),扫一遍生态找好玩的真实案例,重点是抓"真物"(截图/源码/演示)而不是 GitHub 主页,输出可浏览的 HTML 案例集。当用户说"看看大家用 X 做了什么"、"扫一下 X 生态"、"市面上 X 有什么新玩法"、"给我看 X 的真物案例"、"/case-radar"时触发。不适合:① 已有明确目标的深度调研(使用可用的调研工具直接研究)② 写文章/出 PRD(用 writing-assistant / prd-test-writer)③ 单纯求知不需要 HTML(直接问就好)。
Its SKILL.md is about 1.9k tokens, which your agent loads only when the skill is triggered. The skill folder holds 5 other files (for example `reference/_how-to-extend.md`, `reference/html-template-spec.md` and `reference/recon-heuristics.md`).
It sits in Product & Project Management, covering PRD writing and Browser automation. It works with GitHub. The repository describes itself as: 云舒精选的 Claude Code Skills 集合,提升开发和产品管理效率. The licence is MIT.
6 steps, taken from the step headings in SKILL.md.
Read from SKILL.md and the folder at commit da0d31f. It shows what the files ask for, not the result of running them.
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
Shell commands in SKILL.md call:
ghcurlbrewFrom the folder's file list and the shell code blocks in SKILL.md.
No URLs in SKILL.md. Its commands use gh and curl, which can reach the network depending on how they are called.
From URLs in SKILL.md, links to its own repository left out.
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Case Radar loads about 1.9k tokens when it runs. Until then it costs about 70 tokens; SKILL.md has 479 words of instructions outside code blocks.
Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.
The automated check found no risky patterns in SKILL.md.
Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.
The full file from yunshu0909/yunshu_skillshub at commit da0d31f, republished under its MIT licence (© yunshu0909). 479 words, ~1,874 tokens.
.claude/skills/case-radar/SKILL.md (or your agent's skills folder). This skill also uses 4 other files; get the full folder from GitHub.AskUserQuestion、Agent、Read 等名称对应询问、子 agent 与文件读取能力,使用当前平台的等效工具。没有结构化问答工具时,用一条消息问清缺失参数;已有答案直接继承。没有子 agent 能力时,由主 agent 完成扫描。
把"想了解新东西"这件事从"读三手 SEO 文" → "拿到一手真物(截图/源码/演示)"。
输入:一个新东西的名字 + 一句话上下文("我想用来做 X")。 输出:一份可浏览的 HTML 案例集,每张卡都配真实物料(不是文字描述)。
核心信念:菜单一文不值,菜才是真东西。GitHub repo 主页是文件列表(菜单),README 里的截图、商店页的安装数、SKILL.md 的原文段落、产品落地页的真实建站效果——才是真东西(菜)。
| 阶段 | 名称 | 目标 | 主要工具 |
|---|---|---|---|
| 0 | 环境自检 | 确认 agent-browser 装了 + 主题清晰 | Bash + 对话 |
| 1 | scan | 多渠道扫信源,列出候选案例 | WebSearch / Agent(不重新发明,直接调用) |
| 2 | recon | 给每个候选侦察"真物位置"——核心增值 | 读 reference/recon-heuristics.md |
| 3 | capture | 拉真物(curl 直接资源 + agent-browser 截图) | curl + agent-browser |
| 4 | embed | 套 HTML 模板输出 | 参考 reference/html-template-spec.md |
每一步都可中断。用户随时可以说"停"、"跳过这一步"、"回到上一步"。
command -v agent-browserbrew install agent-browser && agent-browser install。装完回来。" 终止。注意:
agent-browser install会下 Chrome 二进制(~169 MB)。如果在中国大陆,可能下载失败。但实测即使 install 卡住,agent-browser 也能复用机器上已有的 Playwright Chromium(~/Library/Caches/ms-playwright/)。所以即使 install 报错,先试一下agent-browser open https://example.com,能跑就跳过 install。
gh auth statusgh auth login,终止用 AskUserQuestion 一次性问完,不要反复 ping-pong:
⚠️ 这一步不要扩展成讨论会。3 个问题问完就动手。如果用户答不上某条,给一个合理默认值(用途默认"三种都要",范围默认"锚定一个生态"),继续。
不重新发明——直接调 WebSearch 或起一个 Agent 跑扫描。
如果案例可能 >20 个,用 Agent 工具起一个 general-purpose subagent 并行跑扫描,避免污染主上下文。Prompt 关键点:
[标题](URL) — 1 句话简介 + 为什么值得深挖scan agent 跑完后,不要立刻全部进 recon。先把信源清单给用户,让她:
⚠️ 如果用户说"全部都要",提醒她:v2 实测 35 案例 grid 是"断崖式注意力低谷"——读者读到 35 时已经累了。建议精读 5-7 个,其余作为索引保留。最终决定权在用户。
这是 Case Radar 的独家增值。其他阶段都被现有 Skill 覆盖,唯独"判断每个案例的真物在哪种栖息地"这一步是新的。
读 reference/recon-heuristics.md 获得 7 种"真物栖息地"的判别模式。
对精读单里每个候选案例,问自己:
把每个案例的"真物位置"写下来——这是 capture 阶段的施工图。
反 checklist 化提醒:recon-heuristics 是 patterns 集合,不是 checklist。某个案例的真物可能在 7 种栖息地之外的第 8 种位置。保留发现新栖息地的可能,发现了就更新 heuristics 文件。
按 recon 阶段的施工图,对每个精读案例抓真物。
curl -sLo screenshots/cases/<name>.<ext> "<url>"适合:README 里已有的 screenshots/ examples/ assets/ 目录里的图、GIF、demo 视频。无浏览器渲染开销,不会有边框/黑条。
适合:SKILL.md 原文、配置文件、changelog 关键段落。
gh api repos/<owner>/<repo>/contents/<path>/SKILL.md --jq '.content' | base64 -d把关键段落(10-30 行)保留到 screenshots/cases/<name>-skillmd.txt,HTML 里用 <pre> 块呈现。
适合:产品落地页(Next.js SPA)、官方商店页(如 Anthropic plugin store)、长博客全页。
agent-browser open <url>
agent-browser wait 2000 # 等 JS 渲染
agent-browser screenshot --full screenshots/cases/<name>-fullpage.png⚠️ agent-browser 默认把截图存到调用时的当前目录,不是参数路径——要么 cd 进 screenshots/cases,要么截完用 mv。
不要硬凑。这种案例不进精读单,降级回普通卡片层(只显示文字描述 + 链接)。装饰图比无图更糟——v2 复盘已经验证(NeoLab 那张纯封面图被 4 个视角里 2 个点名说是"装饰层")。
参考 reference/html-template-spec.md 的视觉规范和层级标签系统。
<工作目录>/<主题简称>-案例集-YYYY-MM-DD.html例:skills-生态创意案例集-2026-05-14.html
图片路径用相对路径:screenshots/cases/<file> —— HTML 在原位置打开就能加载。
[Header] 标题 + 一句话 lede + 层级标签图例 + 升级说明(如有 v2)
[工具 Spotlight] 如果 capture 阶段重度使用了某个工具(如 agent-browser),单独 spotlight
[精读卡] 5-7 张富卡片,每张有真物 hero + 妙在 + 为什么是你 + 大 CTA
[Next Step] 3-5 个可选下一步(不下结论,给用户选)⚠️ 不要加"生态全景 3 大热门"、"6 大分组 grid"这种结构层——v2 复盘已经验证这些是"AI 让自己显得完成度高"的装饰层。如果用户特别要全景图,作为可选附加层。
参考 reference/html-template-spec.md。默认轻量 3 层:事实层 / AI 推测层 / 你的判断区。复杂版(加 共识层、真物层)作为可选,不强加。
✅ 案例雷达扫描完成!
- 扫描案例:[N] 个,精读 [M] 个
- 真物物料:[K] 件(X 张截图 + Y 段源码 + Z 个对比图)
- HTML:[相对路径]
- agent-browser 用量:[A] 次截图 + [B] 次 navigate
Next:
- 在浏览器中打开 HTML 查看效果
- 如发现某张精读卡的真物没抓到位,告诉我哪张,单独重抓
- 如想把某个案例拆成短文/图文,告诉我文字描述能讲什么、图能讲什么,永远先要图。菜单一文不值,菜才是真东西。 截不到真物的案例,降级到普通卡片层,不要硬塞装饰图。
一手源(官方/作者)/ 二手优质(深度玩家)/ 三手中文(有独立观察的),三层之外的 SEO 文、awesome 集市、纯翻译稿一律砍掉。
35 个全做精读会让读者"断崖式注意力低谷"。精读单是用户拍的板,不是 AI 全包——把候选清单给用户选,不要自作主张全部深加工。
reference/recon-heuristics.md 是 patterns 集合,给 Claude 灵活选取。如果某案例的真物在 patterns 之外,记下来更新 heuristics——这个 Skill 应该越用越锋利。
用户随时可以说"停"、"跳过"、"换主题"。不要一口气从 scan 跑到 embed 不给反应机会——v2 实测每一步都需要用户拍板。
读 reference/workflow-anti-patterns.md。这个 Skill 容易落入"建工具不做事"陷阱——它的真正价值取决于用户能不能把案例集变成行动(写文章、做实验、定方向),不取决于 HTML 多精美。
这一段是 4 视角诊断后留下的自我提醒。Skill 跑得动 ≠ Skill 该被点开。
读 reference/workflow-anti-patterns.md 末尾的"4 个反向信号"判断。简版:
用户:扫一下 MCP 生态最新玩法
Skill:
→ 0.1 ✅ agent-browser 装好
→ 0.2 ✅ gh 已登录
→ 0.3 问 3 个对齐问题(用途 / 范围 / 1 个其他)
→ 1.1 起 scan agent,跑 5-8 分钟拉回 32 个候选 + 扫描印象
→ 1.2 用户从 32 个里挑 6 个精读
→ 2 对 6 个跑 recon,判别每个的真物位置
→ 3 拉真物(curl 5 个直接图 + gh 拉 3 段 SKILL.md + agent-browser 截 2 个落地页)
→ 4 出 HTML
→ 5 ✅ 完成用户:之前那个 Skills 生态扫得怎么样了
Skill:
→ 找最近的 case-radar 输出文件
→ 报告当前状态:scan 已完成(35 个)/ recon 完成 7 个 / capture 完成 4 个
→ 问用户从哪一步继续用户:我准备写一篇关于 Cursor 0.50 的文章,先扫一下生态
Skill:
→ ⚠️ 触发"反向信号 #2":用户已在写文章
→ 反问:"你需要的是案例集 HTML 还是几张关键截图直接放进文章?"
- 案例集 → 继续走全流程
- 几张截图 → 跳过 scan + embed,直接进 capture,用 agent-browser 抓你指定的 URLrecon 阶段发现某 Skill 的真物是一段 YouTube demo 视频字幕。
heuristics 文件没列这种栖息地。
Skill:
→ 用 agent-browser 抓字幕(snapshot -i 拿 YouTube 字幕面板)
→ 完成 capture 后,提示用户:"本次发现新栖息地:YouTube 字幕。
是否更新 recon-heuristics.md 加入第 8 种栖息地?"
→ 用户确认 → 更新 reference 文件reference/recon-heuristics.mdreference/html-template-spec.mdreference/workflow-anti-patterns.mdreference/_how-to-extend.md© yunshu0909, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
SKILL.md and 4 other files in visualization/case-radar of yunshu0909/yunshu_skillshub.
Open the folder on GitHubat commit da0d31f
Case Radar next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Case Radar this skillyunshu0909/yunshu_skillshub | 768 | — | ~1.9k | Automated safety check: Pass | MIT | |
| Ralphopentabs-dev/opentabs | 968 | — | ~157 | Automated safety check: Pass | MIT | |
| CCPM Project Managementautomazeio/ccpm | 8.4k | — | ~1.1k | Automated safety check: Pass | MIT | |
| Ouroboros PM InterviewQ00/ouroboros | 6.2k | — | ~5.7k | Automated safety check: Pass | MIT | |
| To Issuessmallnest/pigo | 479 | — | ~1.9k | Automated safety check: Pass | MIT | |
| Write A Prdbestofjs/bestofjs | 3.1k | 1 repos | ~722 | Automated safety check: Pass | MIT |
opentabs-dev/opentabs
Plan work and generate ralph task files for autonomous execution.
automazeio/ccpm
Runs a spec-driven workflow from PRD to epic to GitHub issues to parallel agents, with status, standup and blocked-work reports from bundled scripts.
Q00/ouroboros
Runs a guided product-manager interview that classifies each question automatically and produces a Product Requirements Document.
smallnest/pigo
Decompose a PRD and/or SPEC into implementable Issues and create them in your chosen platform (GitHub, Local, or Baidu iCafe).
bestofjs/bestofjs
Create a PRD through user interview, codebase exploration, and module design, then submit as a GitHub issue.
snarktank/compound-product
Convert a PRD markdown file to prd.json for execution. An agent skill from snarktank/compound-product.
yunshu0909/yunshu_skillshub
让 Codex 与 Claude Code 通过本机 CLI 组成“主执行者 + 独立审查者”的对称协作闭环。用于用户要求两个模型一起完成、交叉校核、独立审查、修到 ACK,或任务涉及产品需求收敛、复杂方案、跨模块开发、迁移、安全、重要重构和高质量交付时;无论从 Codex 还是 Claude Code 启动,都由当前模型主持,并完整调用另一方完成需求挑战、方案门禁、实现冷审和最终验收。
yunshu0909/yunshu_skillshub
配图助手 - 把文章/模块内容转成统一风格、少字高可读的 16:9 信息图提示词;先定“需要几张图+每张讲什么”,再压缩文案与隐喻,最后输出可直接复制的生图提示词并迭代。
yunshu0909/yunshu_skillshub
和用户一起敲定一个前端页面的整页方案(三层法:先定这页给用户什么,再定含哪几样怎么排,最后才是长什么样),最后打成一个定稿包(含高保真全状态与交互流程图)交给开发。触发:用户对一个页面说「想重做 / 重新设计 / 整页不对 / 太满 / 说不清具体改哪」,或「我们讨论一下这页怎么设计」。覆盖三种情形:① 已有页面整页重做;②「替换」——新方案占用同一个入口(同一路由 /…
yunshu0909/yunshu_skillshub
和用户一起把一个功能「看不见的部分」敲定:数据存哪、谁写谁读、怎么加载、怎么保存、默认值和升级、核心执行规则、出问题时怎么办、旧东西怎么迁。每条规则带编号、案例和状态(已定 / 方案里有但你没拍板 / 待你定 / AI 定),用户只回答带案例的新选择题、过目没拍过板的规则;给用户看的是按「你会问的问题」分组的问答卡片(最绕的逻辑配可点的模拟器);最后请另一家模型只读查边界,问题闭环后封成后端逻辑…
yunshu0909/yunshu_skillshub
带用户精读一篇文章/文档并真正学透(不是出摘要)。五步:抽干货 → 切讲次 → 每讲跑「学-考-讲」循环 → 对号入座 → 实操+测验+讲错题+蒸馏。每讲产出 HTML 课件 + 笔记落盘;讲完必考一次,用户复述后必须挑不精确处拧紧;抽象概念上可交互演示(能点能跑);全程用用户自己的业务场景当案例;学完出多题型自动判分测验卷,最后把收获蒸馏回用户的工具。核心触发条件是用户要的是"学会"而不是"要…
yunshu0909/yunshu_skillshub
Issue 池全生命周期管理(开发范式 v1 规划段)。核心是一条 issue 驱动的流程:用户随手丢想法,你把糊的 issue 变成能开工的 task——产出的是“问题定义”,不是“解决方案实现”;载体就是仓库根的 ISSUES.md。五个动作:记、并、拆、转、pending。规划规模只区分 single-task(一个版本能交付)与 roadmap(需要多批滚动),不得使用…
Works with
案例雷达。给一个新东西(新工具/新概念/新生态),扫一遍生态找好玩的真实案例,重点是抓"真物"(截图/源码/演示)而不是 GitHub 主页,输出可浏览的 HTML 案例集。当用户说"看看大家用 X 做了什么"、"扫一下 X 生态"、"市面上 X 有什么新玩法"、"给我看 X 的真物案例"、"/case-radar"时触发。不适合:① 已有明确目标的深度调研(使用可用的调研工具直接研究)②…. Case Radar is an agent skill from yunshu0909/yunshu_skillshub.
Case Radar fits situations like: tasks that involve PRD writing; tasks that involve Browser automation.
Run `npx skills add yunshu0909/yunshu_skillshub --skill case-radar -a claude-code`. Or copy the skill folder (visualization/case-radar in yunshu0909/yunshu_skillshub) into .claude/skills/case-radar in your project. Claude Code loads it when a task matches its description.
Run `npx skills add yunshu0909/yunshu_skillshub --skill case-radar -a codex`. Or copy the skill folder (visualization/case-radar in yunshu0909/yunshu_skillshub) into .agents/skills/case-radar in your project. Codex loads it when a task matches its description.
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add yunshu0909/yunshu_skillshub --skill case-radar -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/case-radar, .gemini/skills/case-radar, .github/skills/case-radar and .opencode/skills/case-radar in your project.
Going by SKILL.md and its folder, Case Radar needs the command-line tools its instructions call (gh, curl and brew).
SKILL.md contains no URLs. Its commands use gh and curl, which can reach the network depending on how they are called. This is read from the text; nothing was executed.
Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.
Case Radar is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
About 1.9k tokens (SKILL.md is roughly 7.5k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.
Skills that share tags, products or a category with Case Radar: Ralph (opentabs-dev/opentabs, 968 stars), CCPM Project Management (automazeio/ccpm, 8.4k stars), Ouroboros PM Interview (Q00/ouroboros, 6.2k stars) and To Issues (smallnest/pigo, 479 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
yunshu0909 (a GitHub user) maintains it in yunshu0909/yunshu_skillshub, which has 768 GitHub stars. The repository holds 25 skills in this directory. The repository was last updated on October 6, 2026.
Source: yunshu0909/yunshu_skillshub on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.