By penkzhou
Multi-stack workflow plugin with unified 3-layer architecture. Features 6-phase Bugfix, 8-phase PR Review, 7-phase CI Job Fix, and 6-phase Execute Plan workflows. 47 agents including 4 master-coordinators and shared review-coordinator for fully closed-loop execution.
npx claudepluginhub penkzhou/swiss-army-knife-plugin --plugin swiss-army-knife执行实施计划（六阶段流程）
执行标准化 Backend Bugfix 工作流（六阶段流程）
执行标准化 E2E Bugfix 工作流（六阶段流程）
修复失败的 GitHub Action job（7 阶段流程，Phase 0-6）
执行标准化 Frontend Bugfix 工作流（六阶段流程）
处理 PR 中的 Code Review 评论（8 阶段流程，Phase 0-7）
合并依赖更新 PR（Renovate + Dependabot），减少 CI 成本
自动分析改动、运行质量检查、提交 commit 并创建 PR
自动化发版流程：更新 CHANGELOG、plugin.json、创建 git tag 并推送
Analyzes backend test failures (Python/pytest, Node.js/Jest). Parses, classifies, and matches historical fixes.
Initializes backend bugfix workflow. Loads config, captures test output, collects project context.
Verifies quality gates after fix implementation. Checks coverage, lint, typecheck, regressions.
Performs root cause analysis for backend test failures with confidence scoring.
Generates structured bugfix documentation from root cause analysis and solution design. Used in Phase 3 of bugfix workflows.
Executes TDD implementation with RED-GREEN-REFACTOR flow and incremental verification. Used in Phase 4 of bugfix workflows.
Extracts learnings from completed bugfixes and updates documentation. Used in Phase 5 after quality gates pass.
协调完整的 Bugfix 工作流（Phase 0-5）。管理 Phase 间状态传递、置信度决策、用户交互和 Review 审查流程。支持 frontend、backend、e2e 三个技术栈。
Designs comprehensive fix solutions with TDD strategy, impact analysis, and security review. Used in Phase 2 of bugfix workflows.
Classifies CI failures. Identifies type, stack, and auto-fix possibility.
Coordinates CI failure fixes with confidence-driven decisions.
Initializes Failed Job workflow. Parses URL, collects metadata, validates gh CLI.
Fetches and parses GitHub Actions job logs. Extracts error-related excerpts.
Deep root cause analysis for CI failures with historical matching.
Generates final reports for CI fix. Optionally commits and retries job.
协调完整的 CI Job 修复工作流（Phase 0-6）。管理 Phase 间状态传递、置信度决策、用户交互和 Review 审查流程。
Analyzes E2E test failures (Playwright/Cypress). Parses, classifies, and matches historical fixes.
Initializes E2E bugfix workflow. Loads config, captures test output, collects project context.
Verifies quality gates after fix implementation. Checks test pass rate, lint, regressions.
Performs root cause analysis for E2E test failures with confidence scoring.
Use this agent to coordinate batch execution of plan tasks. Manages TDD workflow (RED-GREEN-REFACTOR), handles confidence-driven decisions, and tracks execution progress with user confirmation checkpoints.
Use this agent to initialize execute-plan workflow. Parses plan files (Markdown/YAML), loads config, and collects project context including Git status and tech stack detection.
协调完整的 execute-plan 工作流（Phase 0-5）。管理 Phase 间状态传递、置信度决策、用户交互和 Review 审查流程。
Use this agent to generate execution report after plan completion. Summarizes task results, code changes, review findings, and provides knowledge extraction suggestions.
Use this agent to validate plan executability. Analyzes task dependencies, detects cyclic dependencies, and generates topologically sorted execution order with confidence scoring.
Analyzes frontend test failures (React/TypeScript/vitest). Parses, classifies, and matches historical fixes.
Initializes frontend bugfix workflow. Loads config, captures test output, collects project context.
Verifies quality gates after fix implementation. Checks coverage, lint, typecheck, regressions.
Performs root cause analysis for frontend test failures with confidence scoring.
Evaluates PR comment actionability with confidence scores and priority classification.
Fetches review and issue comments from GitHub PR using gh CLI.
Filters PR comments. Removes resolved, CI auto-generated, and empty comments.
Coordinates PR comment fixes with confidence-driven decisions. Dispatches to tech-stack workflows.
Initializes PR Review workflow. Collects PR metadata and validates gh CLI.
将高价值 PR Review 修复沉淀到知识模式库，支持智能合并。
协调完整的 PR Review 工作流（Phase 0-7）。管理 Phase 间状态传递、置信度决策、用户交互和 Review 审查流程。
Generates GitHub reply content from fix results with appropriate tone.
Posts responses to GitHub PR via gh CLI with rate limiting support.
Generates final reports for PR review with statistics and knowledge extraction.
通用代码审查 agent，检查代码质量、项目规范合规性和潜在 bug。在 Phase 5 中与其他 review agents 并行执行。
代码简化 agent，在保持功能完整的前提下提升代码清晰度、一致性和可维护性。在 Phase 5 中与其他 review agents 并行执行。
注释准确性分析 agent，检查代码注释的准确性、完整性和长期可维护性。在 Phase 5 中与其他 review agents 并行执行。
协调 Review 审查工作流，管理 6+1 个 review agents（6 个审查 agent 并行执行 + 1 个 fixer agent 串行修复）和 Review-Fix 循环。所有工作流（bugfix、PR review、CI job、execute-plan）共享此 agent 进行代码审查。
Review 问题自动修复 agent，根据 review agents 发现的 ≥80 置信度问题自动修复代码。在 Phase 5 的 review-fix 循环中被调用。
静默失败检测 agent，识别代码中的静默失败、不当错误处理和不合适的降级行为。在 Phase 5 中与其他 review agents 并行执行。
测试覆盖分析 agent，审查测试覆盖质量和完整性，识别关键测试缺口。在 Phase 5 中与其他 review agents 并行执行。
类型设计分析 agent，评估类型的封装性、不变量表达和设计质量。在 Phase 5 中与其他 review agents 并行执行。适用于 TypeScript、Python（类型提示）等强类型语言。
This skill should be used when the user asks to "debug backend tests", "fix pytest failures", "analyze Python errors", "fix FastAPI bugs", or mentions keywords like "pytest", "IntegrityError", "ValidationError", "SQLAlchemy", "FastAPI". It provides the complete bugfix workflow knowledge including error classification, confidence scoring, and TDD best practices for Python/FastAPI backends.
通用 Bugfix 工作流知识库，包含 TDD 流程、输出格式规范、置信度评分标准和通用最佳实践。适用于所有技术栈（backend/frontend/e2e）。
CI Job 失败分析知识库，包含失败类型分类、置信度评估、技术栈识别和常见错误模式
master-coordinator 和 review-coordinator 共享的通用模式，包括 Phase 验证、错误处理、TodoWrite 管理和状态说明。所有 coordinator agents 应引用此 skill 以保持一致性。
This skill should be used when the user asks to "debug E2E tests", "fix Playwright failures", "fix Cypress tests", "analyze timeout errors", or mentions keywords like "Playwright", "Cypress", "Timeout exceeded", "locator", "selector", "flaky test". It provides the complete bugfix workflow knowledge including error classification, confidence scoring, and E2E-specific debugging techniques.
Strunk 写作规则，用于提升文档质量。适用于所有面向人类读者的文本：文档、报告、注释、提交信息等。
计划执行工作流知识库，包含计划格式规范、任务解析、依赖分析和执行策略
Use this skill when debugging frontend test failures (React/TypeScript, Vitest, etc.), fixing bugs in React/TypeScript code, or following TDD methodology for frontend bug fixes. This skill provides the complete bugfix workflow knowledge including error classification, confidence scoring, and TDD best practices.
PR Review 修复模式库。在处理 PR Review 评论时自动查阅，寻找已知问题模式和解决方案。
PR Code Review 评论分析知识库，包含置信度评估、优先级分类、技术栈识别和常见评论模式
工作流过程日志格式规范和写入模式。定义 JSONL 和文本两种格式的日志结构、事件类型、级别定义和写入方法。
This repository is a Claude Code plugin marketplace containing specialized plugins for development workflows.
| Plugin | Description |
|---|---|
| swiss-army-knife | Standardized frontend bugfix workflow with 6-phase process |
# Add this marketplace
/plugin marketplace add https://github.com/penkzhou/swiss-army-knife-plugin
# Install plugin
/plugin install swiss-army-knife@swiss-army-knife-plugin
swiss-army-knife-plugin/ # Marketplace root
├── .claude-plugin/
│ └── marketplace.json # Marketplace manifest
└── swiss-army-knife/ # Plugin directory
├── .claude-plugin/
│ └── plugin.json # Plugin manifest
├── agents/ # Specialized agents
├── commands/ # Slash commands
├── hooks/ # Event handlers
└── skills/ # Agent skills
MIT
Team-oriented workflow plugin with role agents, 27 specialist agents, ECC-inspired commands, layered rules, and hooks skeleton.
Executes bash commands
Hook triggers when Bash tool is used
Uses power tools
Uses Bash, Write, or Edit tools
Core skills library for Claude Code: TDD, debugging, collaboration patterns, and proven techniques
Comprehensive skill pack with 66 specialized skills for full-stack developers: 12 language experts (Python, TypeScript, Go, Rust, C++, Swift, Kotlin, C#, PHP, Java, SQL, JavaScript), 10 backend frameworks, 6 frontend/mobile, plus infrastructure, DevOps, security, and testing. Features progressive disclosure architecture for 50% faster loading.
Tools to maintain and improve CLAUDE.md files - audit quality, capture session learnings, and keep project memory current.
Comprehensive PR review agents specializing in comments, tests, error handling, type design, code quality, and code simplification
Upstash Context7 MCP server for up-to-date documentation lookup. Pull version-specific documentation and code examples directly from source repositories into your LLM context.