Token导航 LogoToken导航TokenDH.com
开发操作浏览器github未标认证来源可访问许可证需确认审计通过

grey-haven-pr-template灰色天堂公关模板

Agent Skill

grey-haven-pr-template 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

220

周安装

9

GitHub Stars

24

下载量

71
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:grey-haven-pr-template(灰色天堂公关模板)
来源仓库:https://github.com/greyhaven-ai/claude-code-config
仓库路径:skills/grey-haven-pr-template
安装命令:
npx skills add https://github.com/greyhaven-ai/claude-code-config --skill grey-haven-pr-template
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/greyhaven-ai/claude-code-config --skill grey-haven-pr-template

简介

用于处理 GitHub 仓库、Issue 和 Pull Request 协作信息,适合在 Codex、Claude 等宿主中生成标准化 PR 描述。

  • 适用于提供更改概述、动机说明和技术实现细节的场景。
  • 通过 github 安装后,可结合来源仓库验证模板格式和占位符用法。
  • 安装前建议确认权限范围,避免对生产分支造成意外推送。
  • 需注意模板中的线性问题编号和 RLS 策略应人工替换为真实值。

SKILL.md

Grey Haven Pull Request Template

Create comprehensive, informative pull request descriptions that help reviewers understand the changes, context, and testing approach.

PR Structure (Standard Template)

Every pull request should follow this structure:

## Summary
[Concise 2-4 sentence description of changes]

## Motivation
[Why these changes are needed - business value, user impact, problem solved]

## Implementation Details
[Technical approach, key decisions, trade-offs considered]

## Testing
[Test strategy: unit/integration/e2e/benchmark, manual testing steps]

## Checklist
- [ ] Code follows Grey Haven style guidelines (90 char TS, 130 char Python)
- [ ] Type hints added (Python) or types maintained (TypeScript)
- [ ] Tests added/updated (unit, integration, e2e, benchmark)
- [ ] Database migrations tested (up and down)
- [ ] Multi-tenant isolation verified (tenant_id/RLS)
- [ ] Pre-commit hooks passing
- [ ] Documentation updated
- [ ] No breaking changes (or documented with migration guide)

Section Guidelines

Summary

Purpose: Provide a brief, clear overview of what changed.

Guidelines:

  • 2-4 sentences maximum
  • Focus on what changed from user/system perspective
  • Reference Linear issues: GREY-123
  • Mention multi-tenant or RLS changes
  • Use present tense

Example:

## Summary

This PR adds magic link authentication using better-auth with email verification.
Users can now sign in via emailed links instead of passwords. Addresses Linear
issue GREY-234 and integrates with multi-tenant RLS policies.

Motivation

Purpose: Explain why these changes are necessary.

Guidelines:

  • Describe the problem being solved
  • Explain business value or user impact
  • Reference Linear issues: GREY-123
  • Include context not obvious from code
  • Mention technical debt or performance concerns

Example:

## Motivation

Users reported frustration with password-based auth (GREY-234). Analytics show
35% abandon signup at password creation. Magic links offer passwordless auth,
better security, reduced support burden, and built-in email verification.

Aligns with Q1 goal of improving onboarding conversion by 20%.

Implementation Details

Purpose: Explain how the changes work at technical level.

Guidelines:

  • Mention Grey Haven tech stack: TanStack Start/Router/Query, FastAPI, Drizzle, SQLModel
  • Reference Grey Haven patterns: repository pattern, multi-tenant RLS, server functions
  • Note database schema changes (snake_case fields, tenant_id, indexes)
  • Explain testing markers: unit, integration, e2e, benchmark
  • Include code references with file:line format

Example:

## Implementation Details

### Authentication Flow
1. Added magic link server function in [lib/server/functions/auth.ts:45](lib/server/functions/auth.ts#L45)
2. Created email template with Resend integration
3. Implemented token verification route at `/auth/verify`

### Key Changes
- **Server Functions**: New `sendMagicLink` and `verifyMagicLink` with tenant context
- **Database Schema**: Added `magic_link_tokens` table (snake_case, tenant_id, RLS)
- **Routes**: Magic link verification page with TanStack Router navigation

### Design Decisions
- Token expiry: 15 minutes (security vs UX balance)
- Single-use tokens with unique constraint
- Tenant isolation via RLS policies
- Email via Resend (better deliverability)

Testing

Purpose: Describe testing strategy and manual testing steps.

Guidelines:

  • List testing markers used: unit, integration, e2e, benchmark
  • Include manual testing steps
  • Mention test coverage
  • Note any edge cases tested

Example:

## Testing

### Automated Tests
- **Unit tests** (18 new): Token generation, validation, expiry logic
- **Integration tests** (6 new): Email sending, database operations
- **E2e tests** (3 new): Full magic link flow with Playwright

### Manual Testing
1. Request magic link from login page
2. Verify email received within 30 seconds
3. Click link in email
4. Verify successful auth and redirect
5. Test expired token (wait 16 minutes)
6. Test single-use token (use link twice)

### Coverage
- New code: 94% coverage
- Critical paths: 100% coverage

Checklist

Use this checklist before requesting review:

  • Code follows Grey Haven style guidelines (90 char TS, 130 char Python)
  • Type hints added (Python) or types maintained (TypeScript)
  • Tests added/updated (unit, integration, e2e, benchmark)
  • Test coverage meets 80% threshold
  • Database migrations tested (up and down)
  • Multi-tenant isolation verified (tenant_id/RLS)
  • Pre-commit hooks passing (Prettier, Ruff, mypy)
  • Documentation updated (README, API docs)
  • No breaking changes (or documented with migration guide)
  • Linear issue referenced in description
  • Commit messages follow commitlint format
  • Virtual environment activated (Python projects)

Supporting Documentation

All supporting files are under 500 lines per Anthropic best practices:

- feature-pr.md - Feature PR example - bugfix-pr.md - Bug fix PR example - refactor-pr.md - Refactoring PR example - INDEX.md - Examples navigation

- feature-template.md - Feature PR template - bugfix-template.md - Bug fix PR template - database-template.md - Database PR template

- pr-checklist.md - Comprehensive PR checklist

Special Cases

Breaking Changes

Always include migration guide:

## Breaking Changes

**BREAKING:** User IDs are now UUIDs instead of sequential integers.

### Migration Guide
1. Update API clients to handle UUID format
2. Run database migration: `bun run db:migrate`
3. Update any hardcoded user IDs in tests
4. Verify multi-tenant isolation still works

### Timeline
- Migration available: 2025-01-15
- Required by: 2025-02-01

Database Migrations

Include up and down testing:

## Database Migration

### Changes
- Add `tenant_id` column to `organizations` table
- Create RLS policies for tenant isolation
- Add index on `tenant_id`

### Testing
- ✅ Migration up: Successful
- ✅ Migration down: Successful
- ✅ Data backfill: Verified for 1000+ records
- ✅ RLS policies: Tested with different tenants

When to Apply This Skill

Use this skill when:

  • Creating pull requests in Grey Haven projects
  • Reviewing pull requests for completeness
  • Onboarding new developers to PR standards
  • Creating PR templates for new repos
  • Documenting complex features or refactorings

Template Reference

These standards come from Grey Haven's actual templates:

  • cvi-template: TanStack Start + React 19
  • cvi-backend-template: FastAPI + SQLModel

Critical Reminders

  1. Summary: 2-4 sentences - concise overview
  2. Motivation: explain why - business value, user impact
  3. Implementation: explain how - technical approach with file references
  4. Testing: comprehensive - automated + manual steps
  5. Checklist: complete - all items checked before review
  6. Linear issues: reference - GREY-123 format
  7. Multi-tenant: verify - tenant_id and RLS mentioned
  8. Breaking changes: document - migration guide required
  9. Database: test migrations - up and down
  10. Code references: clickable - use file:line format

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

35.56%
按下载量换算25

Claude

32.12%
按下载量换算23

Cursor

18%
按下载量换算13

Gemini CLI

10.48%
按下载量换算7

安全审计

Gen Agent Trust Hub

通过

Socket

通过

Snyk

通过

权限和风险

操作浏览器

该 Skill 可能涉及浏览器控制能力,使用时可能读取或操作网页内容,需要在受控环境中确认权限边界。

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。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