run
仓库创建 2026年6月23日最近提交 21 天前SkillHot 收录 20 天前
▸ 精选理由
把探索与证据聚合成可执行决策，适合产品/策略评估
▸ 风险提示
依赖 Claude CLI/桌面环境
这个 Skill 做什么
将 AI 用例想法变成研究档案、四份研究文档并产出 Proceed/Pivot/Narrow/Kill 决策
把一个 AI 用例想法变成一套可决策的研究产物：并行派出网页调研代理把证据汇入一份权威 dossier，生成四份供不同评审用的研究文档，最后在决策门做出 Proceed/Pivot/Narrow/Kill 的判定。适合在早期需要系统化验证商业与技术可行性的场景，用于决定是否推进或转向。特点是以 playbook.md 驱动、强调证据分层与并行检索，输出可审计的决策依据。
▸ 展开 SKILL.md 英文原文
Turn an AI Agent use-case idea (+ market) into a research dossier, four research docs, and a Proceed/Pivot/Narrow/Kill decision. Spawns parallel web-research worker agents, layers evidence (must-cite/infer/assumption) into a single dossier (source of truth), synthesizes four grill-input docs, then RENDERS A VERDICT at a Decision Gate. Does NOT design screens, map JTBD to UI, or build a screen-brief. Invoke as /usecase-factory:run <slug> [idea + market].
0
Stars
0
Forks
10
仓库内 Skill
+0
7 日增星
安装 / 使用
给你的 Agent 一句话（通用）
帮我安装这个 skill：https://raw.githubusercontent.com/Tritintruong114/usecase-factory/main/skills/run/SKILL.md或 curl 直取 SKILL.md
curl -fsSL "https://raw.githubusercontent.com/Tritintruong114/usecase-factory/main/skills/run/SKILL.md"SKILL.MD 节选查看完整文件 ↗
# Use-Case Factory — orchestrator router
This skill is a **thin router**. All execution logic lives in `playbook.md` next to this file (kept separate so it can be versioned and improved without touching the trigger contract).
## STEP 0 — read the playbook first (mandatory)
Before doing anything else, **read `playbook.md`** in this skill's directory (`${CLAUDE_PLUGIN_ROOT}/skills/run/playbook.md`) end to end. It is the official execution guide: the 8-step flow, the worker-agent specs, the evidence-class rules, the dossier contract, the Decision Gate decision tree, and the handoff rules. Do not run from this router alone — the router only names the steps; the playbook defines how to do themvia SKILL·HOT · 数据来自 GitHub 公开信息 · 原文版权归作者所有