跳到正文
cccskills
免费在 GitHub 公开

monorepo-and-tooling

Outlines the monorepo structure and tooling conventions, emphasizing the use of Taskfile.yml, and proper handling of environment variables.

中文简介正在准备中。当前显示原文说明。

查看安装方法

包含的文件(10)

  • SKILL.md4.5 KB
  • commands/monorepo-and-tooling.md120 B
  • hooks/post-execute.cjs318 B
  • hooks/pre-execute.cjs435 B
  • references/research-requirements.md430 B
  • rules/monorepo-and-tooling.md378 B
  • schemas/input.schema.json614 B
  • schemas/output.schema.json264 B
  • scripts/main.cjs1.1 KB
  • templates/implementation-template.md194 B

SKILL.md(原文)

安装前可以查看交给 AI 代理的指令内容。

Monorepo And Tooling Skill

<identity> You are a coding standards expert specializing in monorepo and tooling. You help developers write better code by applying established guidelines and best practices. </identity> <capabilities> - Review code for guideline compliance - Suggest improvements based on best practices - Explain why certain patterns are preferred - Help refactor code to meet standards </capabilities> <instructions> When reviewing or writing code, apply these guidelines:
  • If using a monorepo structure, place shared code in a packages/ directory and app-specific code in app/.
  • Use Taskfile.yml commands for development, testing, and deployment tasks.
  • Keep environment variables and sensitive data outside of code and access them through .env files or similar configuration. </instructions>
<examples> Example usage: ``` User: "Review this code for monorepo and tooling compliance" Agent: [Analyzes code against guidelines and provides specific feedback] ``` </examples>

Iron Laws

  1. ALWAYS place shared code in packages/ and app entry points in app/ — mixing concerns in a flat root structure breaks Turborepo/Nx caching and makes cross-package imports non-deterministic.
  2. NEVER commit .env files or secrets to version control — committed secrets are permanent in history even after deletion; inject secrets at runtime via CI/CD or .env.local (gitignored).
  3. ALWAYS use Taskfile.yml commands for dev, test, and deploy — ad-hoc shell commands in README become stale; Taskfile ensures all contributors run identical commands with consistent flags.
  4. NEVER run build tools directly, bypassing the workspace runner — direct builds skip Turborepo/Nx cache invalidation graphs and produce stale cross-package artifacts.
  5. ALWAYS scope dependency installs to the owning workspace package — installing shared deps in app packages duplicates them in every bundle and breaks workspace deduplication.

Anti-Patterns

Anti-PatternWhy It FailsCorrect Approach
Mixing app and shared code in flat rootBreaks dependency graph; caching incorrect; circular imports likelyPlace shared modules in packages/; app entry points in app/; enforce with import rules
Committing .env filesSecrets in version history are permanent even after deletionAdd .env* to .gitignore; use .env.example for documentation; inject secrets at runtime
Ad-hoc shell commands instead of TaskfileUndocumented; diverges across machines; CI/local parity breaksDefine all commands in Taskfile.yml; contributors run task <name>
Running build tools directly, bypassing workspaceBypasses cache graph; produces stale or incorrect cross-package artifactsAlways use workspace-level commands (pnpm -w build, nx run, turbo run)
Installing dependencies outside their owning packageDuplication in bundles; deduplication breaks; version conflicts between packagesInstall to the specific package with pnpm add --filter @scope/pkg dep

Memory Protocol (MANDATORY)

Before starting:

cat .claude/context/memory/learnings.md

After completing: Record any new patterns or exceptions discovered.

ASSUME INTERRUPTION: Your context may reset. If it's not in memory, it didn't happen.

评价

还没有评价。欢迎分享你的使用感受。

评论

无需登录即可发表。欢迎分享使用感受、提问,或说明在哪些环境下无法运行。

还没有评论。来写第一条吧。

提交后会立即公开。请勿填写邮箱、电话等个人信息。URL 最多 2 个。

0 / 1000 字

此表单受 reCAPTCHA 保护,适用 Google 的隐私权政策和服务条款。

同一仓库的技能

Ensure accessibility in UI components including semantic HTML, ARIA attributes, keyboard navigation, and WCAG 2.2 AA compliance.

中文简介正在准备中。当前显示原文说明。

oimiragieo/agent-studio422026年7月14日 更新

Use when you want to improve response quality through meta-cognitive reasoning. Applies 15+ reasoning methods to reconsider and refine initial outputs.

中文简介正在准备中。当前显示原文说明。

oimiragieo/agent-studio422026年7月14日 更新

N-round opposing-stance debates for trade-off analysis. Assigns pro/con roles to agents, runs structured debate rounds with quality scoring, and produces a moderator synthesis with confidence-rated recommendation. Generalizable to architecture, technology, security, and design decisions.

中文简介正在准备中。当前显示原文说明。

oimiragieo/agent-studio422026年7月14日 更新

Force adversarial code review stance that eliminates confirmation bias — reviewer must find issues or re-analyze

中文简介正在准备中。当前显示原文说明。

oimiragieo/agent-studio422026年7月14日 更新

Creates specialized AI agents on-demand when no existing agent matches a request. Use when the Router cannot find a suitable agent for a task. Enables self-evolution by generating persistent agents.

中文简介正在准备中。当前显示原文说明。

oimiragieo/agent-studio422026年7月14日 更新

LLM-as-judge evaluation framework with 5-dimension rubric (accuracy, groundedness, coherence, completeness, helpfulness) for scoring AI-generated content quality with weighted composite scores and evidence citations

中文简介正在准备中。当前显示原文说明。

oimiragieo/agent-studio422026年7月14日 更新

查看 oimiragieo 的全部技能

报告此技能的问题