Fork, clone to ~/.clank, run installer, edit CLAUDE.md
原文语言:英语
菜单
已展示 37 / 37 个已收集 Skill。
Fork, clone to ~/.clank, run installer, edit CLAUDE.md
原文语言:英语
RED-GREEN-REFACTOR for process documentation - baseline without skill, write addressing failures, iterate closing loopholes
原文语言:英语
Skills wiki intro - mandatory workflows, search tool, brainstorming triggers
原文语言:英语
Interactive idea refinement using Socratic method to develop fully-formed designs
原文语言:英语
Execute detailed plans in batches with review checkpoints
原文语言:英语
Execute implementation plan by dispatching fresh subagent for each task, with code review between tasks
原文语言:英语
Complete feature development with structured options for merge, PR, or cleanup
原文语言:英语
Create isolated git worktrees with smart directory selection and safety verification
原文语言:英语
Receive and act on code review feedback with technical rigor, not performative agreement or blind implementation
原文语言:英语
Search previous Claude Code conversations for facts, patterns, decisions, and context using semantic or text search
原文语言:英语
Create detailed implementation plans with bite-sized tasks for engineers with zero codebase context
原文语言:英语
Four-phase debugging framework that ensures root cause investigation before attempting fixes. Never jump to solutions.
原文语言:英语
Run verification commands and confirm output before claiming success
原文语言:英语
TDD for process documentation - test with subagents before writing, iterate until bulletproof
原文语言:英语
Write the test first, watch it fail, write minimal code to pass
原文语言:英语
Never test mock behavior. Never add test-only methods to production classes. Understand dependencies before mocking.
原文语言:英语
Dispatch code-reviewer subagent to review implementation against plan or requirements before proceeding
原文语言:英语
Hide implementation details behind interfaces - work at domain level (what), not implementation level (how)
原文语言:英语
Class interfaces present one cohesive abstraction - don't mix domain logic with serialization, persistence, or unrelated concerns
原文语言:英语
Comment WHY code exists and non-obvious decisions, not WHAT code does (mechanics)
原文语言:英语
Try 2-3 different approaches before implementing - don't settle for first design you think of
原文语言:英语
Each routine does one thing and does it well - extract when routines have multiple responsibilities
原文语言:英语
Declare variables in smallest possible scope, initialize close to first use, minimize span and live time
原文语言:英语
Name code by what it does in the domain, not how it's implemented or its history
原文语言:英语
Choose names that fully and accurately describe what the variable represents
原文语言:英语
Refactor with tests first, one change at a time, never mix refactoring with bug fixes or new features
原文语言:英语
Flatten nested conditionals with early returns or table-driven methods - keep nesting depth under 3 levels
原文语言:英语
Use each variable for exactly one purpose - no hybrid coupling or hidden meanings
原文语言:英语
Check all external inputs for validity - garbage in, nothing out, never garbage out
原文语言:英语
Write comments explaining WHAT and WHY, never temporal context or history
原文语言:英语
Maintain skills wiki health - check links, naming, cross-references, and coverage
原文语言:英语
Managing complexity is software's primary technical imperative - all other goals are secondary
原文语言:英语
Design in pseudocode first, iterate approaches, then translate to code
原文语言:英语
Use multiple Claude agents to investigate and fix independent problems concurrently
原文语言:英语
Validate at every layer data passes through to make bugs impossible
原文语言:英语
Systematically trace bugs backward through call stack to find original trigger
原文语言:英语
Replace arbitrary timeouts with condition polling for reliable async tests
原文语言:英语