Token导航 LogoToken导航

Agent Skill · 研究检索

linear-implement(Linear 实现)

用于处理 Linear 项目、Issue、团队、周期和产品开发任务流。它适合让 Agent 辅助查询任务状态、整理需求队列、创建缺陷或汇总迭代进展。使用时需要确认 workspace、team、label、assignee 和状态流转规则;涉及批量创建或修改任务时,应先核对字段和目标团队,避免把草稿需求直接写入正式项目。

linear-implement 是研究检索类 Agent Skill,可用宿主为 Codex、Claude、Cursor、Gemini CLI,通过GitHub 仓库获取,权限为调用外部服务;许可证为 MIT,第三方扫描有提醒项,按安装量在研究检索类的 73,675 个 Skill 里排第 48,205。

总安装 699周安装 28GitHub Stars 50下载 226核验 2026-05-01

安装说明

本站只整理中文说明,不托管安装包,也不代用户安装。
GitHub
许可证
MIT

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:linear-implement(Linear 实现)
来源仓库:https://github.com/dgalarza/claude-code-workflows
仓库路径:skills/linear-implement
安装命令:
npx skills add https://github.com/dgalarza/claude-code-workflows --skill linear-implement
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。不同来源提供的安装方式可能略有差异;本站展示可直接复制的安装命令,安装前请核对来源页面。

skills.shnpx skills
npx skills add https://github.com/dgalarza/claude-code-workflows --skill linear-implement

这个 Skill 是做什么的

研究检索类 Skill 主要解决「找资料、核对事实、把来源整理清楚」的问题,通常会让助手先检索再总结。

用于处理 Linear 项目、Issue、团队、周期和产品开发任务流。适合辅助查询任务状态、整理需求队列、创建缺陷或汇总迭代进展。使用时需确认 workspace、team、label、assignee 和状态流转规则。涉及批量操作时应先核对字段和目标团队,避免误写入正式项目。

安装方式:通过 npx skills add 命令从 GitHub 仓库安装。

来源仓库内路径:skills/linear-implement

上手步骤

4 步
  1. 1

    确认自己的宿主工具

    公开资料标注支持 Codex、Claude、Cursor、Gemini CLI;先确认自己用的是其中之一,再按对应工具的 Skills 目录放置。

  2. 2

    拿到安装命令

    可以直接复制的命令是 npx skills add https://github.com/dgalarza/claude-code-workflows --skill linear-…;命令里的占位符换成自己的路径或密钥再执行。

  3. 3

    安装后重启宿主

    命令执行完要完全退出宿主工具再打开,让新装的 Skill 被重新扫描到,否则列表里可能看不到。

  4. 4

    按最小权限试用

    它需要调用外部服务,先在测试目录或测试账号里跑,确认没问题再放到正式项目。

常见问题

6 条

linear-implement 怎么安装?

在终端执行 npx skills add https://github.com/dgalarza/claude-code-workflows --skill linear-implement。装完完全退出宿主工具再打开,让它重新扫描本地 Skill。

linear-implement 支持哪些 AI 工具?

公开资料标注支持 Codex、Claude、Cursor、Gemini CLI。其他工具只要能读取本地 Skill 目录,一般也能手动放进去,但要自己确认触发方式是否一致。

linear-implement 需要什么权限?

权限级别是调用外部服务。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。

linear-implement 是免费的吗?

来源标注的许可证是 MIT。本站不代收任何费用,也不托管安装包;能否商用、要不要署名,以许可证原文为准。

linear-implement 用的人多吗?

公开数据是累计安装 699 次,近一周安装 28 次,下载 226 次,GitHub 50 星。这些数字来自第三方目录统计,只能当作热度参考,不代表质量或安全性。

linear-implement 安全吗?

第三方扫描有提醒项,说明存在需要人工确认的行为。安装前请打开源码看清它读了什么、联网到哪里。

值得选的地方和要先想清楚的地方

值得选的地方

  • 同时适配 4 种工具,换客户端不用重新找替代品。
  • 3 个目录同时收录,说明这个 Skill 流传比较广。
  • 许可证明确为 MIT,商用和分发边界好判断。

先想清楚的地方

  • 第三方扫描存在提醒项或未通过项,需要人工逐条确认。
  • 第三方目录整理,版本更新和行为细节以来源仓库为准。

适不适合你

更适合

  • 已经在用 Codex,想直接扩展它能力的人。
  • 需要处理研究检索类任务、又不想每次都手写提示词的人。

不太适合

  • 需要厂商级技术支持和 SLA 的生产系统。

研究检索类 Skill 对比

6 个同类
Skill总安装GitHub 星权限许可证扫描
find-skills

寻找技能 · Codex、Claude

31,199,81316,486操作浏览器MIT有提醒
self-improving-agent

自我改进 Agent · OpenClaw

16,464,0023,396接触敏感数据MIT-0通过
soultrace

灵魂追踪 · Codex、Claude

7,588,94412需要联网未明确有提醒
self-improving

自我完善 · OpenClaw

6,829,2841,046需要联网MIT-0通过
microsoft-foundry

微软代工厂 · Codex、Claude

6,614,144764调用外部服务未明确有提醒
linear-implement

Linear 实现 · 本页

69950调用外部服务MIT有提醒

按安装量取同分类前几名;数字来自第三方目录统计,只作热度参考,不代表质量结论。

SKILL.md 原文

Linear Issue Implementation

Overview

This skill provides a comprehensive workflow for implementing Linear issues with professional software engineering practices. It automates the entire development lifecycle from issue analysis through PR creation, ensuring quality through test-driven development, parallel code reviews, and systematic validation.

When to Use This Skill

Use this skill when:

  • User provides a Linear issue ID (format: TRA-9, DEV-123, etc.)
  • User requests implementation of a Linear issue
  • User wants a structured TDD approach with code review
  • User needs automated workflow from issue to PR

Examples:

  • "Implement TRA-142"
  • "Help me build the feature in DEV-89"
  • "Work on Linear issue ABC-456"

Core Workflow

The skill follows a 14-step process:

  1. Fetch Linear Issue - Retrieve complete issue details via Linear MCP
  2. Gather Additional Context - Search Obsidian, Sentry, and GitHub for related information
  3. Move to In Progress - Update issue status to indicate active work
  4. Create Feature Branch - Use Linear's suggested git branch naming
  5. Analyze & Plan - Break down requirements and create implementation plan
  6. Save to Memory - Store plan in memory graph for tracking
  7. Review Plan - Present plan for user confirmation
  8. TDD Implementation - Invoke tdd-workflow skill for test-driven development
  9. Parallel Code Reviews - Invoke parallel-code-review skill for comprehensive analysis
  10. Address Feedback - Invoke code-review-implementer skill to systematically fix issues
  11. Validation - Ensure all tests and linters pass
  12. Logical Commits - Create meaningful commit history
  13. Create PR - Generate comprehensive pull request with Linear linking
  14. Final Verification - Confirm CI/CD pipeline and Linear integration

Workflow Implementation Details

Step 1: Fetch Linear Issue Details

Retrieve the complete issue using Linear MCP tools:

mcp__linear__get_issue(id: <issue-id>)

Extract key information:

  • Title and description
  • Current status and priority
  • Suggested git branch name (branchName field)
  • Team and project context
  • Attachments or related work
  • Labels and assigned team members

Step 2: Gather Additional Context

Before planning, gather related context from multiple sources to inform the implementation approach.

Search Obsidian Vault

Search for any existing notes that might be related to this issue:

# Search by issue ID
Search Obsidian vault for: "TRA-142"

# Search by issue summary/keywords
Search Obsidian vault for: "<keywords from issue title/description>"

Look for:

  • Previous meeting notes discussing this feature
  • Architecture decisions or technical notes
  • Related implementation notes from similar work
  • User research or requirements documentation
Fetch Sentry Context (if referenced)

If the Linear issue references any Sentry issues or error tracking:

mcp__sentry__get_issue(issue_id: <sentry-issue-id>)

Extract from Sentry:

  • Error stack traces and frequency
  • Affected users and environments
  • Related events and breadcrumbs
  • Any existing comments or assignments

This context helps understand:

  • The root cause of bugs
  • Which code paths are affected
  • How frequently the issue occurs
  • Environmental factors to consider
Fetch GitHub Context (if referenced)

If the Linear issue references GitHub pull requests, issues, or discussions:

# View PR details and discussion
gh pr view <pr-number>

# View PR comments and review threads
gh pr view <pr-number> --comments

# View issue details
gh issue view <issue-number>

# View issue comments
gh issue view <issue-number> --comments

Extract from GitHub:

  • Previous implementation attempts
  • Review feedback and concerns raised
  • Design discussions and decisions
  • Related code changes or context

Context Summary:

After gathering context, summarize:

  • Relevant information found in Obsidian
  • Sentry error details (if applicable)
  • GitHub discussion insights (if applicable)
  • How this context affects the implementation approach

Step 3: Move Issue to In Progress

Update the issue status to reflect active development:

  1. Identify the team ID from the issue
  2. Retrieve "In Progress" state using mcp__linear__list_issue_statuses(team: <team-id>)
  3. Update issue using mcp__linear__update_issue(id: <issue-id>, state: <in-progress-state-id>)

This provides visibility to team members that work has begun.

Step 4: Create Feature Branch

Use Linear's suggested branch name for consistency:

# Ensure on main and up-to-date
git checkout main
git pull origin main

# Get branch name from Linear's branchName field
BRANCH_NAME="<from Linear branchName field>"

# Create branch if new, or checkout if exists (idempotent)
git checkout -b "$BRANCH_NAME" 2>/dev/null || git checkout "$BRANCH_NAME"

# Verify correct branch
git branch --show-current

This pattern ensures:

  • Reuse of existing branches
  • Consistent Linear-suggested naming
  • Idempotent operations (safe to re-run)
  • Always working from latest main

Step 5: Analyze and Plan Solution

Break down the issue into an actionable implementation plan:

Analysis Process:

  1. Extract specific requirements from issue description
  2. Identify affected components and systems
  3. Determine testing strategy (unit → integration → system)
  4. Plan implementation approach following project patterns
  5. Identify potential risks and dependencies

Planning Output:

  • Goal: Clear statement of implementation objective
  • Requirements: Specific functional and technical requirements
  • Architecture: How solution fits existing codebase (models, services, controllers)
  • Test Strategy: Comprehensive testing including system specs
  • Implementation Steps: Ordered list of development tasks
  • Acceptance Criteria: Definition of done

Step 6: Save Plan to Memory

Store the implementation plan using memory MCP tools:

mcp__memory__create_entities(entities: [
  {
    name: "Linear Issue <issue-id>",
    entityType: "implementation-plan",
    observations: [
      "Requirements: <requirements>",
      "Architecture: <architecture-decisions>",
      "Test Strategy: <test-approach>",
      "Status: planning-complete"
    ]
  }
])

This creates permanent tracking of:

  • Issue context and requirements
  • Implementation approach and reasoning
  • Progress throughout development
  • Lessons learned for future work

Step 7: Review Plan with User

Present the complete plan for confirmation:

Plan Presentation:

  • Summary of what will be implemented
  • Key technical decisions and rationale
  • Testing strategy and expected coverage
  • Estimated complexity and identified risks
  • Explicit confirmation request

User Options:

  • Approve to proceed with implementation
  • Request modifications to approach
  • Add requirements or constraints
  • Ask clarifying questions

Step 8: Test-Driven Development Implementation

Upon approval, invoke the TDD workflow skill:

Invoke the Skill tool with: tdd-workflow

The TDD workflow skill enforces:

  • Red-Green-Refactor cycles
  • Test pyramid strategy (unit → integration → system)
  • Writing tests before implementation
  • Comprehensive test coverage including system specs

Expected Outcomes:

  • Complete test coverage for new functionality
  • Implementation following project POODR principles
  • Result pattern for operations that can fail
  • Clean, maintainable code structure

Step 9: Parallel Subagent Code Reviews

After implementation, invoke the parallel code review skill:

Invoke the Skill tool with: parallel-code-review

This launches specialized review subagents in parallel:

Security Review:

  • OWASP Top 10 vulnerabilities
  • Multi-tenant security (ActsAsTenant verification)
  • XSS, CSRF, SQL injection prevention
  • Authentication and authorization checks
  • Sensitive data handling

Rails Best Practices Review:

  • POODR principles (SRP, dependency management, Tell Don't Ask)
  • Rails 7+ conventions
  • N+1 query prevention
  • ActiveRecord optimization
  • Service object patterns
  • Result pattern usage

Frontend Review (if applicable):

  • ViewComponent best practices
  • Tailwind CSS conventions
  • StimulusJS patterns
  • Accessibility (ARIA attributes)

Output:

  • Consolidated review report
  • Decision tracking to prevent redundancy
  • Prioritized feedback by severity and impact

Step 10: Address Review Feedback

Invoke the code review implementer skill:

Invoke the Skill tool with: code-review-implementer

This skill systematically addresses feedback:

Process:

  1. Parse and prioritize feedback by impact and effort
  2. Identify common refactoring patterns
  3. Implement fixes incrementally with test validation
  4. Ensure backward compatibility
  5. Update documentation as needed

Architectural Feedback is MANDATORY:

  • Extract service objects if controllers/models have too many responsibilities
  • Apply Result pattern for operations that can fail
  • Refactor to improve testability and maintainability
  • Add comprehensive specs for new service objects

Note: Do NOT create PR until all architectural feedback is implemented.

Step 11: Validation and Quality Assurance

Before creating commits, ensure everything passes:

Validation Steps:

# Run full test suite
bundle exec rspec

# Run linting (Standard, ERB, Brakeman)
bin/lint

# Fix any failures or warnings
# Verify system specs pass in clean environment

Quality Checks:

  • Code follows project POODR principles
  • Result pattern used appropriately
  • No security vulnerabilities
  • Performance impact considered (no N+1 queries)
  • All subagent feedback addressed
  • Test coverage sufficient

Linting Notes:

  • Yarn failures can be ignored if only working on Rails code
  • Warnings about MigratedSchemaVersion and ContextCreatingMethods are harmless
  • Actual offenses must be addressed (look for file paths and line numbers)

Step 12: Create Logical Commits

Create meaningful commits that tell the implementation story:

Commit Strategy:

  1. Test commits: Add failing tests for new functionality
  2. Implementation commits: Add code to make tests pass
  3. Refactor commits: Improve code structure
  4. Security fixes: Address security review feedback
  5. Pattern improvements: Implement OOP/Rails pattern suggestions
  6. Documentation commits: Update docs if needed

Commit Message Format:

Present-tense summary under 50 characters

- Detailed explanation if needed (under 72 chars per line)
- Reference which review feedback was addressed
- Note any breaking changes or migration requirements

Linear issue: <Linear issue URL>
Implemented with Claude Code

Use heredoc for proper formatting:

git commit -m "$(cat <<'EOF'
Add user notification service

- Extract notification logic from controller
- Apply Result pattern for error handling
- Add comprehensive RSpec tests with edge cases

Linear issue: https://linear.app/company/issue/TRA-142
Implemented with Claude Code
EOF
)"

Step 13: Create Pull Request

Generate comprehensive PR with Linear integration:

PR Creation Command:

gh pr create --title "<concise-title>" --body "$(cat <<'EOF'
## Summary
- Concise bullet points of what was implemented
- Key technical decisions made

## Implementation Details
- Architecture approach and patterns used
- Services/models/controllers added or modified
- Database changes (if applicable)

## Testing Strategy
- Test coverage added (unit, integration, system)
- Edge cases covered
- Manual testing performed

## Code Review Process
- Security review findings and resolutions
- Rails best practices review findings and resolutions
- Performance considerations addressed

## Breaking Changes
[None or list any breaking changes]

## Linear Issue
Closes <Linear issue URL>

---
Implemented with Claude Code following TDD methodology with parallel code reviews.
EOF
)"

PR Description Includes:

  • Summary of implementation
  • Technical approach and key decisions
  • Testing strategy and coverage
  • Code review findings and resolutions
  • Security considerations addressed
  • Breaking changes or migration notes
  • Screenshots/demos if applicable

Linear Integration:

  • Include Closes <Linear-issue-URL> in PR body
  • Linear automatically links and updates issue status when PR merges

Step 14: Final Verification

Verify PR setup and completion:

Final Checks:

  • ✅ CI/CD pipeline triggered successfully
  • ✅ Linear issue linked and updated
  • ✅ All tests passing in CI environment
  • ✅ Code review assignees notified
  • ✅ Branch protection rules satisfied
  • ✅ Security and pattern reviews documented

Completion Summary: Present checklist to user:

  • ✅ Linear issue analyzed and planned
  • ✅ Solution implemented with TDD
  • ✅ Comprehensive system specs added
  • ✅ Security review completed
  • ✅ Rails/OOP patterns review completed
  • ✅ All review feedback addressed
  • ✅ All tests and linting pass
  • ✅ Logical commit history created
  • ✅ PR created with Linear integration

Integration with Other Skills

This skill orchestrates multiple specialized skills:

tdd-workflow:

  • Enforces Red-Green-Refactor cycles
  • Ensures test-first development
  • Guides test pyramid strategy

parallel-code-review:

  • Runs security and Rails reviews concurrently
  • Consolidates findings to avoid redundancy
  • Provides prioritized feedback

code-review-implementer:

  • Systematically addresses all feedback
  • Applies common refactoring patterns
  • Validates fixes with tests

Project-Specific Conventions

This skill adheres to project guidelines from CLAUDE.md:

Rails Patterns:

  • Service objects for business logic
  • Result pattern for operations that can fail
  • POODR principles (SRP, Tell Don't Ask, Law of Demeter)

Multi-Tenant Security:

  • ActsAsTenant automatic scoping
  • Tenant isolation verification
  • No need for explicit tenant scoping in queries

Testing:

  • RSpec with shoulda-matchers
  • System specs for user workflows
  • Avoid stubbing the system under test
  • Use backdoor middleware for auth in request specs

Code Style:

  • i18n for all user-facing text
  • Timestamp columns instead of booleans
  • Postgres enums for static values
  • ENV.fetch for required environment variables

Requirements

Linear MCP Integration:

  • Linear MCP server must be configured and available
  • Required tools: mcp__linear__get_issue, mcp__linear__update_issue, etc.

Git Repository:

  • Current directory must be a git repository
  • main branch exists and is up-to-date
  • Git configured with user credentials

Testing and Linting:

  • bundle exec rspec available for testing
  • bin/lint script available for linting
  • Ruby/Rails development environment configured

GitHub CLI:

  • gh CLI tool installed and authenticated
  • Repository configured for PR creation

Skills:

  • tdd-workflow skill available
  • parallel-code-review skill available
  • code-review-implementer skill available

Error Handling

Common Issues and Solutions:

Linear Issue Not Found:

  • Verify issue ID format (e.g., TRA-9, not tra-9)
  • Confirm Linear MCP integration is working
  • Check user has access to the team/issue

Branch Already Exists:

  • Expected behavior - workflow checks out existing branch
  • Ensures work can be resumed safely
  • Verifies branch is synced with remote

Tests or Linting Fail:

  • Review failures and fix before creating PR
  • Common linting issues: StandardRB, ERB Lint, Brakeman
  • Never use standardrb --fix blindly - review changes

Code Review Identifies Issues:

  • MUST address architectural feedback before PR
  • Extract service objects as recommended
  • Apply Result pattern where suggested
  • Only create PR after all feedback implemented

Example Workflow

User Request:

Implement TRA-142

Skill Response:

  1. Fetches TRA-142 from Linear
  2. Gathers additional context:

- Searches Obsidian vault for "TRA-142" and related keywords - Fetches Sentry issue details (if referenced in Linear issue) - Retrieves GitHub PR discussions (if referenced in Linear issue)

  1. Updates issue to "In Progress"
  2. Creates branch dg/tra-142-user-notification-service
  3. Analyzes requirements and creates plan (informed by gathered context)
  4. Saves plan to memory graph
  5. Presents plan: "This will create a new service object for user notifications using the Result pattern..."
  6. Waits for user approval
  7. Upon approval, invokes tdd-workflow skill
  8. After implementation, invokes parallel-code-review skill
  9. Reviews identify: "Extract notification logic to service object, apply Result pattern"
  10. Invokes code-review-implementer skill to address feedback
  11. Runs validation: bundle exec rspec ✅, bin/lint ✅
  12. Creates logical commits with proper messages
  13. Creates PR with comprehensive description and Linear linking
  14. Presents completion checklist

Final Output:

  • Working feature branch with complete implementation
  • All tests passing
  • All linting passing
  • Comprehensive PR with Linear integration
  • Issue automatically updated when PR merges

Best Practices

Planning Phase:

  • Take time to understand requirements fully
  • Identify edge cases and error conditions
  • Consider multi-tenant implications
  • Plan for comprehensive system specs

Implementation Phase:

  • Follow TDD strictly - tests before code
  • Keep commits small and logical
  • Write self-documenting code
  • Use i18n for all user-facing text

Review Phase:

  • Address ALL architectural feedback
  • Don't skip recommended refactoring
  • Validate fixes with tests
  • Consider performance implications

PR Creation:

  • Write comprehensive descriptions
  • Document review findings and resolutions
  • Include manual testing notes
  • Ensure Linear linking is correct

Quality Gates:

  • Never create PR with failing tests
  • Never create PR with linting errors
  • Never create PR without addressing architectural feedback
  • Never skip validation steps

平台分布

Claude Code

29.86%
按下载量换算67

OpenCode

24.23%
按下载量换算55

Cursor

17.21%
按下载量换算39

Codex

13.98%
按下载量换算32

Antigravity

9.06%
按下载量换算20

windsurf

3.43%
按下载量换算8

安全审计

Gen Agent Trust Hub

通过

Socket

通过

Snyk

可疑

权限和风险

调用外部服务

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。来源安全扫描存在提醒或未通过项,安装前请自行复核。

继续浏览同类 Skills