Token导航 LogoToken导航TokenDH.com
开发external-servicegithub未标认证来源可访问许可证需确认审计异常

project-setup项目设置

Agent Skill

project-setup 用于处理 GitHub 仓库、Issue、Pull Request 和代码协作信息,适合在 Codex、Claude、Cursor、Gemini CLI 中需要围绕仓库状态、代码变更或协作事项进行整理时使用。可结合来源仓库、安装命令和原始 README 继续核验具体用法。安装前建议确认权限范围、维护状态,以及是否会触发联网、命令执行或文件读写。

总安装

823

周安装

35

GitHub Stars

公开资料未说明

下载量

288
CodexClaudeCursorGemini CLI

安装说明

本站只整理中文说明和来源信息,不托管安装包,也不代用户安装。

GitHub

来源数

2

许可证

unknown

最后核验

2026-05-01

来源状态

来源可访问

安装方式

通过对话安装

复制提示词发给支持本地命令或 Skills 的 AI 助手,先确认命令和权限,再让它执行。

请帮我安装这个 Agent Skill:project-setup(项目设置)
来源仓库:https://github.com/loxosceles/ai-dev
仓库路径:skills/project-setup
安装命令:
npx skills add https://github.com/loxosceles/ai-dev --skill project-setup
安装前请先检查当前环境是否支持对应 CLI,并向我确认将要执行的命令、安装目录、联网范围和文件读写权限;确认后再执行。

命令行安装

复制命令到本机终端执行。该命令会通过 npx skills 从第三方来源获取 Skill;本站只展示命令,不托管安装包,也不自动执行。

skills.shnpx skills
npx skills add https://github.com/loxosceles/ai-dev --skill project-setup

简介

project-setup 用于处理 GitHub 仓库、Issue、Pull Request 和代码协作信息,适合在 Codex、Claude、Cursor、Gemini CLI 中整理协作事项。

  • 适用于项目初始化、环境配置和开发流程管理等开发场景。
  • 围绕仓库状态和代码变更进行信息整合,需结合原始 README 确认具体用法。
  • 安装命令为 npx skills add https://github.com/loxosceles/ai-dev --skill project-setup。
  • 使用前建议确认权限范围、维护状态及是否触发联网或文件读写操作。

SKILL.md

Project Setup

This is a strict guideline. Follow these rules exactly.

New projects are created from blueprints stored at loxosceles/project-blueprints on GitHub.


Workflow

  1. Pre-flight: Verify devcontainer-state: Before anything else, check that ~/.devcontainer-state/.git exists. If it doesn't, stop immediately and instruct: ⛔ ~/.devcontainer-state is not a git repo. Docker will auto-create mount targets as empty root-owned directories, breaking the devcontainer. Fix: git clone git@github.com:loxosceles/devcontainer-state.git ~/.devcontainer-state If ~/.devcontainer-state already exists (empty/root-owned), remove it first: sudo rm -rf ~/.devcontainer-state Do not proceed until this is resolved.
  2. Identify the blueprint: Ask which stack the user wants (e.g., "nextjs-sst", "sst-python"). Read the corresponding blueprint from blueprints/{stack}.md in the repo.
  3. Read the full blueprint before starting. Understand all sections.
  4. Collect variables: Ask for project_name, git_name, git_email, and any other values the blueprint requires.
  5. Execute sections in order: Follow the blueprint step by step.
  6. Copy fragments verbatim: Fragment files from fragments/ are exact configs. Copy them, then replace {{template_variables}} with actual values.
  7. Assemble stack-specific files: Common fragments (fragments/common/) contain {{INJECTION_MARKERS}}. Read the matching injection snippets from fragments/injections/{stack}/ and insert them at the marked points. Pick the Dockerfile from fragments/dockerfiles/{stack}/. The result is one clean file per output — no runtime includes or sourcing. For devcontainer.json, merge the injection's extensions and settings into the common base.
  8. Pause on version mismatches: If a tool (create-next-app, SST, etc.) has a new major version compared to what the blueprint specifies, stop and ask: "Should I evaluate the upgrade or use the pinned version?"
  9. Never silently modify fragments: If a fragment doesn't work with current tool versions, report the conflict and ask.
  10. Run verification: Execute all verification commands at the end. All must pass.
  11. Install skills and configure agents:

- Run npx skills add loxosceles/ai-dev --agent claude-code github-copilot codex kiro-cli -y and ask about additional third-party skills. - Pre-create all host mount targets (Docker creates missing sources as root-owned, breaking permissions): PROJECT=<project-name> mkdir -p ~/.devcontainer-state/cache/${PROJECT}/claude mkdir -p ~/.devcontainer-state/cache/${PROJECT}/kiro/agents mkdir -p ~/.devcontainer-state/cache/${PROJECT}/kiro/settings - Kiro agents are seeded from ~/.devcontainer-state/ai/agents/kiro/ into ~/.kiro/agents/ by post_create.sh on first run. They persist in the per-project kiro cache mount. - Codex agents are symlinked from ~/.devcontainer-state/ai/agents/codex/ into .github/agents/ by post_create.sh on every container start. .github/agents/ is gitignored. - Both agent mounts are overridable via KIRO_AGENTS and CODEX_AGENTS env vars in .devcontainer/.env. - Never copy agent configs into the project's .kiro/agents/ — that causes conflicts with the host's global ~/.kiro/agents/.

  1. Verify MCP server config: Check that ~/.devcontainer-state/ai/mcp/servers.json exists. If not, warn the user to copy from servers.json.template. MCP servers are distributed to all agents (Kiro, Claude, Amazon Q) by post_start.sh on every container start.
  2. Verify devcontainer scripts: The setup uses two scripts:

- post_create.sh — runs once after container creation (validation, symlinks, git identity, agent seeding, skills restore) - post_start.sh — runs on every container start (Claude CLI install/update, Claude settings copy, MCP server distribution)

Rules

  • Execute in the current directory (must be empty or an empty git repo)
  • Git remotes must use SSH, never HTTPS: git@github.com:user/repo.git
  • Never skip verification steps
  • If a step fails, present the error with options — don't silently retry
  • Template variables use {{double_braces}} syntax
  • Fragment files are the source of truth for configs — don't improvise alternatives
  • Consistency with project-migration: This skill and project-migration must produce identical results for shared concerns (devcontainer, skills, kiro, linting, CI/CD). If you detect a discrepancy between what this skill instructs and what project-migration does, stop and warn the developer before proceeding.

Progressive Improvement

If the developer corrects a behavior that this skill should have prevented, suggest a specific amendment to this skill to prevent the same correction in the future.

适合场景

01

用户想查找某类 Agent Skill 时

02

需要根据任务场景推荐可安装能力包时

03

需要对比不同来源的安装命令和来源信息时

能力概览

能力 1

按任务关键词查找相关 Skills

能力 2

展示可复制的安装命令

能力 3

保留来源站点、仓库和原始说明,方便继续核验

能力 4

展示第三方安全扫描或审计结果

安装后应在对应宿主中按原始 README 的触发条件使用;具体调用方式请以来源页面和 README 为准。

平台分布

Codex

33.94%
按下载量换算98

Claude

30.49%
按下载量换算88

Cursor

18.02%
按下载量换算52

Gemini CLI

8.43%
按下载量换算24

安全审计

Gen Agent Trust Hub

通过

Socket

可疑

Snyk

未通过

权限和风险

external-service

该 Skill 可能调用第三方服务、云服务或外部模型 API,使用前需要确认账号、额度、数据发送范围和服务条款。

安装前确认

本站仅展示第三方公开信息,不托管安装包,不提供自动安装或运行环境。安装前应自行审查源码、依赖和命令行为。来源安全扫描存在 warning/failed 结果,不能写成本站确认安全。当前只有一个来源,正式发布前建议补源仓库或其他目录站核验。

来源信息

继续浏览同类 Skills