Backend Expert
CaoMeiYouRen/caomei-auth
设计或实现后端 API、服务层、数据库读写、鉴权权限控制、输入校验、事务处理与错误处理时使用。用户提到 API、route、handler、server、auth、permission、drizzle、database、zod、Hono、Nuxt server routes、backend bug 修复时都应触发。
Effect v4 模式指南。当需要创建 Effect 服务、定义错误类型、编写 Effect 程序、管理 Layer 组合、或使用 Effect 封装异步操作时使用
$ npx skills add zhe-qi/clhoria-template --skill effect-v4 -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install zhe-qi/clhoria-template effect-v4 --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/zhe-qi/clhoria-template.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.agents/skills/effect-v4 .claude/skills/effect-v4 && 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 "effect-v4" agent skill from https://github.com/zhe-qi/clhoria-template/tree/main/.agents/skills/effect-v4 into .claude/skills/effect-v4/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "effect-v4", 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/zhe-qi/clhoria-template/tree/main/.agents/skills/effect-v4Type 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 zhe-qi/clhoria-template --skill effect-v4 -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install zhe-qi/clhoria-template effect-v4 --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/zhe-qi/clhoria-template.git skills-src && mkdir -p .agents/skills && cp -r skills-src/.agents/skills/effect-v4 .agents/skills/effect-v4 && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "effect-v4" agent skill from https://github.com/zhe-qi/clhoria-template/tree/main/.agents/skills/effect-v4 into .agents/skills/effect-v4/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "effect-v4", 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 zhe-qi/clhoria-template --skill effect-v4 -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install zhe-qi/clhoria-template effect-v4 --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/zhe-qi/clhoria-template.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/.agents/skills/effect-v4 .cursor/skills/effect-v4 && 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 "effect-v4" agent skill from https://github.com/zhe-qi/clhoria-template/tree/main/.agents/skills/effect-v4 into .cursor/skills/effect-v4/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "effect-v4", 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/zhe-qi/clhoria-template.git --path .agents/skills/effect-v4--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 zhe-qi/clhoria-template --skill effect-v4 -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install zhe-qi/clhoria-template effect-v4 --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/zhe-qi/clhoria-template.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/.agents/skills/effect-v4 .gemini/skills/effect-v4 && 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 "effect-v4" agent skill from https://github.com/zhe-qi/clhoria-template/tree/main/.agents/skills/effect-v4 into .gemini/skills/effect-v4/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "effect-v4", 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 zhe-qi/clhoria-template effect-v4Installs 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 zhe-qi/clhoria-template --skill effect-v4 -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/zhe-qi/clhoria-template.git skills-src && mkdir -p .github/skills && cp -r skills-src/.agents/skills/effect-v4 .github/skills/effect-v4 && 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 "effect-v4" agent skill from https://github.com/zhe-qi/clhoria-template/tree/main/.agents/skills/effect-v4 into .github/skills/effect-v4/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "effect-v4", 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 zhe-qi/clhoria-template --skill effect-v4 -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install zhe-qi/clhoria-template effect-v4 --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/zhe-qi/clhoria-template.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/.agents/skills/effect-v4 .opencode/skills/effect-v4 && 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 "effect-v4" agent skill from https://github.com/zhe-qi/clhoria-template/tree/main/.agents/skills/effect-v4 into .opencode/skills/effect-v4/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "effect-v4", 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.
effect-v4Effect v4 模式指南。当需要创建 Effect 服务、定义错误类型、编写 Effect 程序、管理 Layer 组合、或使用 Effect 封装异步操作时使用
Effect V4 is an agent skill from zhe-qi/clhoria-template. Effect v4 模式指南。当需要创建 Effect 服务、定义错误类型、编写 Effect 程序、管理 Layer 组合、或使用 Effect 封装异步操作时使用
Its SKILL.md is about 890 tokens, which your agent loads only when the skill is triggered. The skill folder holds 6 other files, including reference files (for example `references/anti-patterns.md`, `references/effect-composition.md` and `references/error-patterns.md`).
It sits in Databases. It works with Hono and Zod. The repository describes itself as: Production-ready Hono backend template that doubles as an AI agent harness — providing feedforward guides, feedback sensors, and progressive specialization to make AI coding… The licence is MIT.
Read from SKILL.md and the folder at commit 589f13e. 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.
No scripts in the folder and no shell commands in SKILL.md.
From the folder's file list and the shell code blocks in SKILL.md.
No URLs in SKILL.md.
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.
Effect V4 loads about 887 tokens when it runs, and up to ~9.3k if it reads all its reference files. Until then it costs about 23 tokens; SKILL.md has 228 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 zhe-qi/clhoria-template at commit 589f13e, republished under its MIT licence (© zhe-qi). 228 words, ~887 tokens.
.claude/skills/effect-v4/SKILL.md (or your agent's skills folder). This skill also uses 5 other files; get the full folder from GitHub.本 skill 为 Effect v4 (4.0.0-beta.48) 在本项目中的使用提供规范化指南。
Context.Service、Data.TaggedError、Layer)src/lib/infrastructure/effect/
├── index.ts # Barrel exports
├── errors.ts # Data.TaggedError 定义
├── services/ # Context.Service 定义
│ ├── db.ts # DbService
│ ├── logger.ts # LoggerService
│ └── bullmq.ts # BullMQService
└── layers/
└── live.ts # InfraLayer = Layer.mergeAll(...)| 类别 | DO | DON'T |
|---|---|---|
| Service 定义 | Context.Service<Self, Shape>()("tag") | Effect.Service (v3 API) |
| Service 构造 | Layer.succeed(Tag, instance) / Layer.effect(Tag, ...) | 在使用处 Effect.provide |
| 错误类型 | Data.TaggedError("Tag")<{ fields }> | Schema.TaggedError / 普通 Error |
| 错误处理 | catchTag / catchTags 按标签匹配 | catchAll / mapError 丢失类型 |
| 追踪函数 | Effect.fn("Service.method")(function* ...) | 匿名 generator 无追踪名 |
| 异步包装 | Effect.tryPromise({ try, catch }) | Effect 内部 raw await |
| 错误抛出 | yield* Effect.fail(new XxxError(...)) | Effect.gen 内 throw |
| Layer 组合 | Layer.mergeAll 平铺同级 | 深层嵌套 Layer.provide |
| Layer 链式 | Layer.provideMerge 增量组合 | 多层 Layer.provide(类型爆炸) |
| 执行边界 | Effect.runPromise 仅在 Hono handler 入口 | Service 内部 runPromise |
| v3 | v4 | 说明 |
|---|---|---|
Effect.Service<T>()("name", { accessors, dependencies, effect }) | Context.Service<T, Shape>()("name") + Layer.succeed/effect | Service 类只是标签,Layer 独立构造 |
accessors: true → Service.method() | yield* ServiceTag → service.method() | 先获取 service 实例再调方法 |
dependencies: [Dep.Default] | Layer.provide(depLayer) / Layer.provideMerge(depLayer) | 依赖关系在 Layer 组合时声明 |
Schema.TaggedError<T>()("tag", { fields }) | Data.TaggedError("tag")<{ fields }> | 不需要 Schema 字段,用 TS readonly |
HttpApiSchema.annotations({ status: 404 }) | Hono handler 中 c.json(Resp.fail(...), 404) | HTTP 状态码在路由层处理 |
Config.string("KEY") | import env from "@/env" | 项目用 Zod 验证的 env |
Effect.log("msg") | logger.info({ data }, "[Module]: msg") | 项目用 Pino |
Schema.Option(Schema.String) | field: string | null | 项目用 Drizzle/Zod 可空类型 |
Effect 在本项目中的定位是 基础设施编排层,不是全栈框架。边界清晰:
Hono Handler (async/await)
└─ Effect.runPromise(program) ← 边界:进入 Effect 世界
└─ Effect.gen(function* () {
const db = yield* DbService; ← 获取 service
const result = yield* Effect.tryPromise(...); ← 异步操作
return result;
})入口点(允许 Effect.runPromise):
Service 内部(禁止 Effect.runPromise):
Effect.Effect<A, E, R>yield* 组合其他 EffectEffect.tryPromise 包装异步© zhe-qi, 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 5 other files (references) in .agents/skills/effect-v4 of zhe-qi/clhoria-template.
Open the folder on GitHubat commit 589f13e
Effect V4 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 |
|---|---|---|---|---|---|---|
| Effect V4 this skillzhe-qi/clhoria-template | 193 | — | ~887 | Automated safety check: Pass | MIT | |
| Backend ExpertCaoMeiYouRen/caomei-auth | 220 | — | ~329 | Automated safety check: Pass | MIT | |
| Hono Idiomsirahardianto/awesome-agv | 157 | — | ~3k | Automated safety check: Pass | MIT | |
| Hono Routingsecondsky/claude-skills | 227 | — | ~3.6k | Automated safety check: Pass | MIT | |
| Typescript Idiomsirahardianto/awesome-agv | 157 | — | ~6.1k | Automated safety check: Pass | MIT | |
| Better Drizzlealmeidazs/better-drizzle | 348 | — | ~1.7k | Automated safety check: Pass | Apache-2.0 |
CaoMeiYouRen/caomei-auth
设计或实现后端 API、服务层、数据库读写、鉴权权限控制、输入校验、事务处理与错误处理时使用。用户提到 API、route、handler、server、auth、permission、drizzle、database、zod、Hono、Nuxt server routes、backend bug 修复时都应触发。
irahardianto/awesome-agv
Hono lightweight web framework patterns: type-safe route handlers, middleware composition, Zod validation, and RPC clients for Cloudflare Workers, Node, or Bun.
secondsky/claude-skills
Type-safe Hono APIs with routing, middleware, RPC. An agent skill from secondsky/claude-skills.
irahardianto/awesome-agv
TypeScript strict typing: type narrowing, discriminated unions, Zod runtime validation, generic utility types, and Vitest testing.
almeidazs/better-drizzle
Write, review, and debug code that uses better-drizzle, the typed repository layer over Drizzle ORM 1.x (better(db), client.users.findMany, paginate, cursor, upsertMany, relation include/connect…
ahpxex/open-dashboard
Everything about the data layer — pick one of six ready-to-run backend templates (TanStack Start + Drizzle + better-auth, Hono + Drizzle + better-auth, Hono + Prisma + better-auth, Hono + Drizzle +…
zhe-qi/clhoria-template
创建或修改 BullMQ 队列任务。当需要创建新队列、添加任务类型、注册 Worker、设置定时任务、或用户请求"添加后台任务/队列处理"时使用
zhe-qi/clhoria-template
创建或修改一个新的 API tier。当用户请求“新增 tier / 创建 partner tier / 新增 merchant 端 / 新增 tenant 端 / 新增 API 端 / 新增一套路由层”时使用。目标是在不修改框架核心的前提下,为新 tier 补齐配置、中间件、类型别名、路由入口和测试。
zhe-qi/clhoria-template
创建或修改 CRUD 模块。当需要创建新的增删改查 API、修改现有路由模块、添加新字段、新增接口、或用户请求"创建/修改 XX 管理"时使用
zhe-qi/clhoria-template
创建或修改数据库 Schema。当需要创建新表、修改表结构、定义字段、设置索引约束、或涉及 Drizzle ORM / drizzle-zod 操作时使用
zhe-qi/clhoria-template
Drizzle ORM v1 关系查询指南。当需要定义 Relations v2、编写关系查询、使用 through 多对多、预定义过滤器、或从旧版 Drizzle 迁移时使用
zhe-qi/clhoria-template
Enter explore mode - think through ideas, investigate problems, clarify requirements
Categories
Effect v4 模式指南。当需要创建 Effect 服务、定义错误类型、编写 Effect 程序、管理 Layer 组合、或使用 Effect 封装异步操作时使用. Effect V4 is an agent skill from zhe-qi/clhoria-template.
Effect V4 fits situations like: databases work in your project.
Run `npx skills add zhe-qi/clhoria-template --skill effect-v4 -a claude-code`. Or copy the skill folder (.agents/skills/effect-v4 in zhe-qi/clhoria-template) into .claude/skills/effect-v4 in your project. Claude Code loads it when a task matches its description.
Run `npx skills add zhe-qi/clhoria-template --skill effect-v4 -a codex`. Or copy the skill folder (.agents/skills/effect-v4 in zhe-qi/clhoria-template) into .agents/skills/effect-v4 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 zhe-qi/clhoria-template --skill effect-v4 -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/effect-v4, .gemini/skills/effect-v4, .github/skills/effect-v4 and .opencode/skills/effect-v4 in your project.
SKILL.md names no scripts, command-line tools or credentials: Effect V4 is instructions for the agent only.
SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. 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.
Effect V4 is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
About 887 tokens (SKILL.md is roughly 3.5k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 8.4k tokens, read only when the agent opens those files.
Skills that share tags, products or a category with Effect V4: Backend Expert (CaoMeiYouRen/caomei-auth, 220 stars), Hono Idioms (irahardianto/awesome-agv, 157 stars), Hono Routing (secondsky/claude-skills, 227 stars) and Typescript Idioms (irahardianto/awesome-agv, 157 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
zhe-qi (a GitHub user) maintains it in zhe-qi/clhoria-template, which has 193 GitHub stars. The repository holds 10 skills in this directory. The repository was last updated on July 30, 2026.
Source: zhe-qi/clhoria-template on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.