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