zenstory-ai/oh-story-claudecode / skills/story-setup
story-setup
Flagged网文写作工具集基础设施部署与检查。为 Claude Code / OpenCode / Codex / Google Antigravity / ZCode / OpenClaw / Reasonix 提供内置适配;Web AI / 通用 Agent 可走 skills + AGENTS.md 文件模式。触发方式:/story-setup、$story-setup、「准备写书」「帮我搭一下环境」「配置写作项目」「检查写作环境」。
references/deploy-generic.md
View on GitHub# 通用 Web AI / 其他 Agent 部署
`target_cli` 含 `generic` 时,由 SKILL.md Phase 2 完整读取并依次执行本文件。路径检查、幂等重跑、残留清理、部署标记、模板占位符、项目指令合并和报告遵循 SKILL.md 的公共规则。
## 部署清单(机械可检查)
| Source path | Target path | Owner class | Merge mode | Validation check |
|-------------|-------------|-------------|------------|------------------|
| `skills/story-setup/references/generic/AGENTS.md.tmpl` | `AGENTS.md` | user+managed | managed block merge | contains generic story skill routing sections |
| repository `skills/{browser-cdp,story*}/` | `skills/{browser-cdp,story*}/` | story-setup managed for known skill names | replace known skill dirs only | 14 `SKILL.md` files exist; OpenClaw-compatible frontmatter |
| repository `skills/story-setup/references/agent-references/` | 随上一行整份 skill 拷贝落地,本行 no-op | story-setup managed | 不单独复制 | every reference resolves |
## 通用 Web AI / 其他 Agent 部署算法
通用路径面向可读取项目文件的 NarraFork、Web AI、自定义 Agent,只部署 `AGENTS.md` 与项目本地 `skills/`。原生 hooks/agents 不部署;检查按 skill 软约束执行,分工走 solo/direct fallback。
1. 复制仓库当前 `skills/` 下所有包含 `SKILL.md` 的 story skill 目录(14 个:`browser-cdp` 与 `story*`)到目标项目 `skills/{skill-name}/`;仅替换这些 story-setup 管理的已知 skill 目录(`status: safe` 时按 SKILL.md 先清理各已知目录内源端已删除的旧文件),保留用户其他目录。项目副本是整份 skill 拷贝,agent references 只使用当前规范前缀 `skills/`。
2. 用 `skills/story-setup/references/generic/AGENTS.md.tmpl` 按 SKILL.md「项目指令合并」写入项目 `AGENTS.md`(`--host generic`)。
3. `.story-deployed` 的 `target_cli` 写入 `generic` 或多端组合;`references_dir` 对 generic 写 `skills/story-setup/references/agent-references`。
4. 安装报告提示项见下方「安装报告必须提示」。
## 验证
- 检查 `AGENTS.md` 含通用 story skill routing sections
- 检查 `skills/` 下 14 个 story skill 目录存在,且每个 `SKILL.md` 可读
- 按源目录相对路径核对 `skills/story-setup/references/agent-references/`,含子目录
## 安装报告必须提示
generic 不部署平台专属 hooks/custom agents;大纲守卫、commit 提醒、session/compact 注入等硬拦截与多 agent 协作都按 skill 内软约束或 solo/direct fallback 执行。
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| reverse-engineer-anythingmorluto/reaReverse engineer native, managed, Electron/JavaScript, packaged, firmware, and browser targets with REA, and build agent environments (AgentEnv bundles) of web applications from a live instance or a capture, and of Linux desktop apps with a task from a request. Use shipped-artifact or requested runtime evidence to explain features, compare versions, decompile code, or guide a reconstruction. Skip REA for ordinary source-repository architecture analysis. | Stars: 472k | Updated | Claude CodeCodex | Unverified | Install |
| diagnosing-superpowersobra/superpowersUse when a superpowers session went wrong and your human partner wants to know why — repeated work, ignored plans, stumbles, poor results, a skill that didn't fire, "it took too long", "why is it so expensive", "what is it doing" — or wants to build a bug report for the superpowers maintainers, for the current session or a past one identified by id or path, on any harness. | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| dispatching-parallel-agentsobra/superpowersUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| executing-plansobra/superpowersUse when executing an implementation plan in the current session as the implementer yourself — your human partner chose inline execution, or no subagent tool is available | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |