Creates API gateway endpoints in a FastAPI backend and encapsulates a unified calling layer in a uni-app frontend.
- GitHub stars
- 72
- Files
- 42
- Last commit
- Nov 10, 2026
- License
- MIT
- Allowed tools
- —
What does the lov-api-creator skill do?
lov-api-creator creates API gateway endpoints in a FastAPI backend and encapsulates a unified calling layer in a uni-app frontend.
Summary generated from the skill's SKILL.md.
About the lov-api-creator skill
Developers building applications that require centralized API management can use this tool to automate the setup of gateway endpoints and frontend communication layers. It functions by adding specific gateway endpoints and groupings to a FastAPI-based backend known as uni-api, while simultaneously creating a unified calling layer within a DCloud uni-app frontend project.
When an agent loads this skill, it performs a two-step workflow. First, it modifies the backend by creating business packages, routers, and registering them in the app groups configuration to produce a gateway endpoint list. Second, it uses that list to generate modular API files and a request wrapper in the frontend, including base URL and error handling logic. This process ensures that the frontend can communicate with the aggregated backend services through a consistent interface. The skill requires access to both a uni-api FastAPI repository and a uni-app frontend repository to function.
What an agent can do with it
- 1Integrate API gateway into uni-appA developer can request the integration of gateway capabilities directly into their existing uni-app project.
- 2Add backend gateway endpointsYou can instruct the agent to add backend aggregated interfaces or gateway endpoints for a specific application.
- 3Automate full-stack gateway setupThe skill can execute a complete pipeline that configures both the FastAPI backend and the uni-app frontend modules.
Written from the skill's SKILL.md. Every use case is checked against a quote from it.
How to install the lov-api-creator skill
Each command copies the skill folder into the client's skills directory. Restart the client or start a new session to load it.Install the lov-api-creator skill in Plugin
/plugin marketplace add lovstudio/skills /plugin install dev-tools@lovstudio
Install the lov-api-creator skill in Claude Code
~/.claude/skills/lov-api-creator/SKILL.md
$ npx degit lovstudio/skills/skills/api-creator ~/.claude/skills/lov-api-creatorInstall the lov-api-creator skill in Claude Code (project)
.claude/skills/lov-api-creator/SKILL.md
$ npx degit lovstudio/skills/skills/api-creator .claude/skills/lov-api-creatorInstall the lov-api-creator skill in Codex
~/.agents/skills/lov-api-creator/SKILL.md
$ npx degit lovstudio/skills/skills/api-creator ~/.agents/skills/lov-api-creatorInstall the lov-api-creator skill in Gemini CLI
~/.gemini/skills/lov-api-creator/SKILL.md
$ npx degit lovstudio/skills/skills/api-creator ~/.gemini/skills/lov-api-creatorInstall the lov-api-creator skill in Claude.ai
npx degit lovstudio/skills/skills/api-creator lov-api-creator && zip -r lov-api-creator.zip lov-api-creator # claude.ai → Customize → Skills → + → Create skill → Upload a skill → lov-api-creator.zip
Automated checks
Ran Nov 14, 2026Full report →Passed our automated checks. That is not a security audit: read the scripts before you let an agent run them. How checks work · What to fix for more points
- Source repository linked and reachablelovstudio/skills/skills/api-creator is public and reachablegithub.com/lovstudio/skills/tree/HEAD/skills/api-creator ↗Pass
- Open source license (OSI)MITspdx.org/licenses/MIT.html ↗Pass
- Commit or release in the last yearLast commit 2026-11-10github.com/lovstudio/skills/commits ↗Pass
- No download-and-run or credential theft in scripts5 of 6 scripts read; none of them downloads and runs code, the rest were not readFinding
- No hidden instructions in SKILL.mdNo override phrases, safeguard switches, credential requests or hidden charactersgithub.com/lovstudio/skills/blob/HEAD/skills/api-creator/SKI ↗Pass
- Pre-approved tools are scopedNo pre-approved tools; the agent asks before using onegithub.com/lovstudio/skills/blob/HEAD/skills/api-creator/SKI ↗Pass
- SKILL.md follows the Agent Skills formatthe description does not say when to use the skill; name "lov-api-creator" differs from the folder "api-creator"github.com/lovstudio/skills/blob/HEAD/skills/api-creator/SKI ↗Finding
SKILL.md
View on GitHub网关工坊 · Gateway Studio
开发某个 app 需要 API 网关能力时,本 Skill 在 uni-api(FastAPI 聚合网关)后端为该 app 创建网关
端点与 /docs 分组,并在对应 uni-app 前端项目封装统一调用层,让 app 通过网关访问聚合后的 API。
Triggers
Activate when
- 开发某个 app 时需要 API 网关能力,要求集成进 uni-api(FastAPI 聚合网关)后端。
- “帮我把网关能力集成到 uni-app 项目里”。
- “给 加后端聚合接口 / 网关端点”。
- "integrate an API gateway into my uni-app project".
- "create backend gateway endpoints for my app".
Do not activate when
- 只需为项目加单个第三方 AI 代理(如 Gemini 生图代理):交给
lov-install-zenmux-api。 - 重构已有后端里冗余的 API:交给
lov-refactor-api。 - 只是把现成网关或服务部署上线:交给
lov-deploy-to-vercel。 - 生成独立 App 工程或落地页:交给
lov-app-generator/lov-oh-my-landingpage。
User Profile (cross-session)
Every generated Skill is connected to the shared user-profile/v1 contract in
skill.yaml. Read the shared user, brand, workspace, preferences, and this
Skill's skills.<skill_id> namespace at the start of every run. Keep the source
portable: resolved personal values belong in the shared profile, never here.
When the user directly states a durable preference or brand fact, persist it
through scripts/profile_store.py and report the saved profile path. Put
Skill-specific values under records.<field>; use brand.<field> or
user.<field> for shared values. Do not persist inferred secrets or credentials.
See references/user-profile.md for the complete contract.
Skill Kit Modules
This repository is a self-contained Skill Kit. At Step 0, load and verify:
$SKILL_DIR/skills/backend/SKILL.md—lov-backend$SKILL_DIR/skills/frontend/SKILL.md—lov-frontend
kit.yaml is the machine-readable module and pipeline manifest. Every module
listed there must ship inside this repository.
Skill Group Composition
Read references/skill-composition.md before deciding whether to invoke or
extend any adjacent capability. The record distinguishes optional upstream and
downstream handoffs from embedded Kit modules. Do not silently depend on a
sibling Skill that is not shipped with this source.
Workflow (MANDATORY)
You MUST follow these steps in order.
Step 0: Resolve skill root, dependencies, and runtime context
- Use
SKILL_DIRif the environment provides it. - Otherwise infer the installed skill directory from the current skill context.
- Verify every required local module, reference, script, and asset before work.
- If a required resource is missing, name its expected relative path and stop before producing a partial result.
When running scripts manually:
export SKILL_DIR="/path/to/lov-api-creator"
Resolve context.profile on every invocation. The precedence is current request,
project context, Skill-specific profile records, shared preferences, shared
brand/user profile, then safe defaults. A direct user statement about a durable
preference or brand fact should be saved with scripts/profile_store.py record
using --confirm, followed by a concise saved-path report.
Step 1: Understand the requested outcome
- Separate internal context from user-visible output.
- Confirm the input, intended audience, expected deliverable, and evidence gaps.
- 确认三项输入:app 名称、需要网关化的上游能力(LLM 聚合 / 代理 / 业务 API)、
前端项目路径(DCloud uni-app,含
pages.json与manifest.json)。 - Record one real user case before calling the Skill complete. The case must show the input, the prompt or minimum brief, and the output; do not invent results.
Step 1.5: Analyze nearby Skills before implementation
- Inspect related local and installed Skills by routing contract and concrete input/output, not by filename alone.
- Record upstream, core, downstream, overlap, and not-composed decisions in
references/skill-composition.md. - Keep sibling Skills optional and artifact-based. When stages require hard coupling for one outcome, create a self-contained Kit instead.
Step 2: Execute the workflow
按 kit.yaml 的流水线执行。默认跑 full(backend → frontend);用户只要求一端时只跑对应模块。
- backend(
$SKILL_DIR/skills/backend/SKILL.md):在 uni-api 后端为该 app 创建网关能力 —— 业务packages/<domain>/+router/<capability>.py+ 注册进router/__init__.py- 把 tag 分组加入
config/app_groups.py+ 必要 env。产物是网关端点清单。
- 把 tag 分组加入
- frontend(
$SKILL_DIR/skills/frontend/SKILL.md):在 uni-app 前端封装网关调用层 —— 统一request封装(baseURL / token / 错误处理)+ 按端点清单生成的模块化 API 文件。 产物是可用的api/模块与用法示例。
两模块通过「网关 baseURL + 端点清单」契约交接:backend 的端点表是 frontend 的输入。
Step 3: Validate the deliverable
- 后端:
python -c "import main"通过(先按 uni-api 的 AGENTS.md 备好.env与socksio),/openapi出现新 tag,/docs新 Tab 生效。 - 前端:request 封装可被页面
import后正常调用,错误提示可复制并携带上下文。 - Report concrete files or results, plus any remaining evidence gaps.
- Validate
skill-card.yaml,cases/cases.json, andpricing-card.yamlas the standard trust bundle for this Skill.
Dependencies
- 后端:可访问的 uni-api(FastAPI)仓库;
python3与项目 poetry 环境;.env与socksio等 运行前提见 uni-api 仓库根目录AGENTS.md。 - 前端:DCloud uni-app 项目(HBuilderX 或 CLI 工程均可)。
- 无第三方外部服务依赖。
Files in this skill
42lov-api-creator skill questions
How do I install the lov-api-creator skill in Claude Code?
Run npx degit lovstudio/skills/skills/api-creator ~/.claude/skills/lov-api-creator. Claude Code loads skills from ~/.claude/skills (all projects) or .claude/skills (one project) and uses a skill when its description matches the task.
Which clients can use the lov-api-creator skill?
Any client that reads the Agent Skills format: Claude Code, Codex, Gemini CLI and claude.ai (upload as a ZIP). Scripts in the skill run only where the client allows code execution.
What does this skill do for the backend?
It creates gateway capabilities in the uni-api backend by adding business packages, routers, and registering them in the app groups configuration.
What is the output for the frontend?
The skill provides a unified request encapsulation including baseURL, tokens, and error handling, along with modular API files generated from the endpoint list.
What are the requirements to use this skill?
You need access to a uni-api (FastAPI) backend repository and a DCloud uni-app frontend project.