By weiping
Core skills library for Claude Code: TDD, debugging, collaboration patterns, and proven techniques
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation. 在任何创意工作前必须使用 - 创建功能、构建组件、添加功能或修改行为之前。 适用于:需求分析、功能设计、方案制定、头脑风暴、想做新功能、从哪里开始开发。
Use when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies. 面临 2 个以上可并行处理的独立任务时使用。 适用于:并行处理、多任务并发、独立任务分发、同时修复多个不相关问题。
Use when you have a written implementation plan to execute in a separate session with review checkpoints. 有书面实现计划需要批次执行并设置检查点时使用。 适用于:执行已有计划、按计划实现、批次执行任务、分批推进开发。
Use when implementation is complete, all tests pass, and you need to decide how to integrate the work - guides completion of development work by presenting structured options for merge, PR, or cleanup 实现完成、所有测试通过,需要决定如何集成工作时使用。 适用于:完成分支、合并分支、结束开发、提 PR、合并代码、完成功能开发。
Use when receiving code review feedback, before implementing suggestions, especially if feedback seems unclear or technically questionable - requires technical rigor and verification, not performative agreement or blind implementation 收到代码审查反馈时使用,在实施建议之前,尤其当反馈不清晰或存在技术疑问时。 适用于:处理审查意见、回应代码评审、技术性反驳、验证审查建议。
Own this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimOwn this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimBased on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
A Pi platform port of the Superpowers workflow skill library, with Chinese trigger support
pi-superpowers ports 14 professional workflow skills from obra/superpowers to the Pi programming assistant platform, adding:
Skill, TodoWrite, Task) to Pi equivalentsdispatch_agent tool: Simulates Claude Code's Task sub-agent with context isolation via pi --no-session --print subprocess/brainstorm, etc.)After installation, 14 skills are available. Skill descriptions include both Chinese and English keywords — Pi automatically loads the matching skill when a relevant request is received.
You can also force-load any skill with the /skill:<name> command.
| Skill | Trigger Scenario | Chinese Keyword Examples |
|---|---|---|
brainstorming | Requirements analysis and design before implementing a new feature/component | 头脑风暴、做一个新功能、从哪里开始、需求分析 |
writing-plans | Breaking down requirements into fine-grained implementation steps | 写计划、制定开发计划、拆分任务、做规划 |
subagent-driven-development | Executing multiple independent tasks according to an implementation plan | 执行计划、开始实现、逐任务执行 |
executing-plans | Batch-executing an existing written plan | 按计划实现、批次执行任务 |
test-driven-development | Before implementing any feature or fixing a bug | TDD、测试驱动开发、先写测试、测试优先 |
using-git-worktrees | When isolation from the current workspace is needed | git worktree、隔离开发、新分支开发 |
dispatching-parallel-agents | Facing 2+ independent tasks that can run in parallel | 并行处理、多任务并发、同时修复多个问题 |
verification-before-completion | Just before declaring a task complete | 验证完成、声明完成前、提交前验证 |
| Skill | Trigger Scenario | Chinese Keyword Examples |
|---|---|---|
systematic-debugging | Encountering a bug, test failure, or unexpected behavior | 调试、找 bug、修复问题、测试失败、根本原因分析 |
requesting-code-review | Code review before completing a task or merging | 代码审查、code review、审查代码、提交前审查 |
receiving-code-review | Handling review feedback after receiving it | 处理审查意见、回应评审、技术反驳 |
finishing-a-development-branch | Implementation complete, tests passing, ready to integrate | 完成分支、提 PR、合并代码、结束开发 |
| Skill | Trigger Scenario | Chinese Keyword Examples |
|---|---|---|
using-superpowers | At the start of every conversation (auto-injected by the Bootstrap extension) | Auto-triggered, no manual action needed |
writing-skills | Creating or modifying skill files | 写 skill、创建新技能、设计工作流技能 |
You: Help me build a user permissions management module
└→ AI auto-loads brainstorming skill, begins requirements analysis
↓ Explores requirements, proposes multiple approaches, awaits confirmation
You: OK, let's go with that approach
└→ AI auto-loads writing-plans skill, breaks down implementation steps
↓ Generates a plan with 2–5 minute granularity per step
You: Start implementing
└→ AI auto-loads subagent-driven-development / executing-plans skill
↓ Implements task by task in TDD cycles (tests first, then implement, review, then continue)
You: Everything is done
└→ AI auto-loads verification-before-completion skill, runs verification commands
↓ After confirmation, loads finishing-a-development-branch to decide merge strategy
You: Tests are failing — TypeError: Cannot read property 'id' of undefined
└→ AI auto-loads systematic-debugging skill
↓ Systematic root-cause analysis: confirm symptoms → isolate scope → find minimal repro → fix
↓ Must write a failing test that reproduces the bug before applying the fix (TDD)
When auto-triggering is unreliable, use /skill: commands to force-load a skill:
npx claudepluginhub weiping/pi-superpowersAI-powered 8-stage interaction design workflow: from product context to interactive prototype and delivery documentation. Supports iOS, Android, Web, and PC client platforms.
Core skills library for Claude Code: TDD, debugging, collaboration patterns, and proven techniques
Superpowers Plus core skills library for Claude Code: planning, execution routing, TDD, debugging, and collaboration workflows
Evidence-gated AI coding workflow: scan → analyze → plan → TDD → execute → fix → verify → review, powered by Codebase Memory MCP >= 0.9.0 with optional Serena LSP intelligence. Includes blast-radius planning, test/cycle gates, independent review, and Windows Git Bash hook auto-resolution.
Matt Pocock's agent skills for real engineering — grilling, spec/ticket flows, TDD, code review, domain modelling and more. Plug-and-play, not vibe coding.
v9.52.0 - Reliability wave: tangle contextual review correction loop with hard round ceiling, progress-supervised review rounds (per-agent stall watch, descendant-tree kills), council diversity and agy pin fixes, marketplace generator source-of-truth fix, provider troubleshooting runbook and cost-expectations docs. Run /octo:setup.
Claude harness - A harness for solo developers (Vibecoders) to handle full-cycle contract development.