claudecodex

claude-everything-workflow

Reusable engineering workflows for Claude Code and Codex.

13 on GitHubby xu91102v0.2.5MITupdated 18 days agoProductivity
/

Plugin claude-everything-workflow from marketplace cew in xu91102/claude-everything-Workflow. Commands read from the repo's manifest — 17 days ago.

What it installs

Skills (20)

  • code-review

    Review a fixed diff and confirmed scope; use self-review for verifiable low-risk work and independent review as risk grows.

  • codebase-design

    Design deep modules and seams when interfaces leak complexity or tests cross internals.

  • continuous-learning-v2

    管理学习系统的观察 Hook、instinct 评估、迁移和演化;用于明确配置或管理该学习系统的请求。

  • domain-modeling

    Model changes to business concepts, entities, states, relationships, invariants, or ownership; exclude ordinary refactors.

  • e2e-testing

    Use for explicit Playwright or E2E work; keep tests repeatable and load detailed patterns on demand.

  • feature-acceptance

    建立或维护项目验收工具与功能地图;按用户或项目验收合同执行真实流程,产出可复核证据。

  • grilling

    Resolve a consequential user-owned decision one question at a time; do not ask discoverable facts.

  • handoff

    Create a redacted handoff for an explicitly requested fresh session or context boundary.

  • implement

    Deliver one authorized scope through implementation, review, and verification.

  • improve-codebase-architecture

    Run an explicit read-only architecture-health audit and route selected findings to design or grilling.

  • prototype

    Build a throwaway runnable probe for one explicit design question; do not silently ship it.

  • resolving-merge-conflicts

    Resolve an active merge or rebase conflict hunk by hunk with verification.

  • spec-gate

    Create and self-review a formal Spec for explicit or costly-to-reverse work; wait for approval.

  • subagent-driven-development

    Dispatch approved independent frontier tickets in isolated worktrees; use only when router selects SDD.

  • systematic-debugging

    Diagnose bugs, recurring or flaky failures, slowness, and performance regressions; exclude expected TDD RED.

  • test-driven-development

    Use for behavior changes with a test path: RED, minimal GREEN, REFACTOR, then verify.

  • to-tickets

    Split an approved scope into demonstrable vertical tickets with real blocking edges; wait for approval.

  • triage

    Use only for explicit issue or pull-request triage; classify evidence and produce an agent-ready brief.

  • using-superpowers

    Route engineering delivery and explicitly requested engineering workflows; resume their process outcomes.

  • visual-companion

    Use only with consent when a local visual companion materially improves a design decision.

Slash commands (5)

  • /claude-everything-workflow:code-review

    基于固定基点和已确认范围,按风险选择自审、独立或双轴审查

  • /claude-everything-workflow:learn

    统一管理学习模式的评估、状态、项目、推广、清理与演化

  • /claude-everything-workflow:pr

    提交、推送和创建 Pull Request 的标准工作流

  • /claude-everything-workflow:to-spec

    从已确认需求生成、自审并请求批准正式工程 Spec

  • /claude-everything-workflow:verify

    运行全面验证检查

Subagents (5)

  • database-reviewer

    PostgreSQL 数据库专家,专注于查询优化、模式设计、安全性和性能。在编写 SQL、创建迁移、设计模式或排查数据库性能问题时主动使用。融合了 Supabase 最佳实践。

  • e2e-runner

    端到端测试专家,负责发现项目现有测试入口,优先使用 Playwright 创建、维护和运行可重复的 E2E 自动化测试;Agent Browser 或 MCP 仅作为可选探索和调试辅助。输出执行命令、测试结果、失败原因和产物路径。

  • harness-optimizer

    当需要审计或改进 Claude/Codex Harness 配置时使用。只修改规则、commands、agents、skills、hooks、README 等 Harness 文件;按主循环、工具、上下文、状态、权限、验证六层找最小可逆改动,并返回证据、风险和验证结果。

  • refactor-cleaner

    当需要删除死代码、清理未使用依赖、合并重复实现或做低风险重构时使用。先做只读影响面分析和风险分级;只有用户明确要求执行时才编辑或删除文件。

  • security-reviewer

    安全漏洞检测和修复专家。在编写处理用户输入、认证、API 端点或敏感数据的代码后主动使用。标记密钥泄露、SSRF、注入攻击、不安全加密和 OWASP Top 10 漏洞。

View source on GitHub

Similar plugins

caveman

claude

Talk like caveman. Cut filler. Keep technical details explicit.

22 skills · 1 command · 3 agents · hooks

JuliusBrussee/caveman 119,462

claude-mem

claudecodex

Persistent memory for Claude Code: the next session starts where the last one left off.

29 skills · 1 MCP server · hooks

thedotmack/claude-mem 116,618

Taste Skill

claudecodex

tasteskill 2.5.1: professional company websites at the figma.com and x.ai level, with one section per screen, real photographs, real product UI, effects kept for tech and gaming pages, and a real-browser checker and finish gate.

1 skill

Leonxlnx/taste-skill 114,391

career-ops

claudecodex

Open-source AI job search that runs locally in your AI coding CLI: scan job portals, evaluate listings into a structured A-H report with a 1-5 score, tailor your CV, track applications

5 skills · hooks

career-ops-hq/career-ops 82,253

mem0

claudecodex

Cross-session memory and token savings for coding agents.

6 skills · 1 agent · 1 MCP server · hooks

mem0ai/mem0 68,893

pake

claudecodex

Package any website or local web build into a lightweight desktop app with Pake CLI.

1 skill

tw93/Pake 63,463

Maintain claude-everything-workflow?

This page updates itself from your repo. Add the badge to your README, or get it Featured to pin it above the organic results with a followed link to your site.

claude & codex pluginslisted