core

Plugin core from marketplace dxta-skills in DxTa/claude-code-skills. Commands read from the repo's manifest — 5 days ago.

Skills (25)

• agent-selection

  Select Pi agents from compact local agent index.

• anti-patterns

  Common mistakes to avoid with explanations and correct alternatives

• clean-code

  Apply Robert C. Martin Clean Code principles and the clean-code-skills rule catalog when code quality is explicit or when an agent is reviewing, simplifying, refactoring, or cleaning touched code. Use for clean code, code smells, maintainability, readability, naming, small functions, comments/docstr

• code-design-patterns

  Language-agnostic guidance for detecting code smells, selecting behavior-preserving refactorings, and choosing or rejecting classic Refactoring.Guru design patterns. Use for requests like “review this for code smells,” “how should I refactor this long method?”, or “should I use Adapter, Strategy, or

• code-review

  Routes code-review situations to the right practice, and executes a two-axis review (Standards + Spec) of a diff via parallel sub-agents. Use when reviewing a branch/PR/work-in-progress, receiving review feedback, or before any completion claim. Dispatches receiving-code-review, requesting-code-revi

• collision-zone-thinking

  Force unrelated concepts together to discover emergent properties - "What if we treated X like Y?

• defense-in-depth

  Validate at every layer data passes through to make bugs impossible

• finishing-a-development-branch

  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

• inversion-exercise

  Flip core assumptions to reveal hidden constraints and alternative approaches - "what if the opposite were true?

• meta-pattern-recognition

  Spot patterns appearing in 3+ domains to find universal principles

• planning-with-files

  Use when Tier 2+ tasks, multi-step projects, or when tracking/recovery is needed and plan files must persist across sessions.

• push-all

  Stage all changes, run quality gates (lint/typecheck), safety checks (secrets/large files), commit, and push to remote

• python-design-patterns

  Problem-first guidance for choosing, rejecting, and reviewing classic design patterns in Python. Use when selecting a Python design pattern, comparing Factory vs Builder, replacing conditionals with Strategy, evaluating a Refactoring.Guru pattern, refactoring toward or away from a GoF pattern, or de

• receiving-code-review

  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

• requesting-code-review

  Use when completing tasks, implementing major features, or before merging to verify work meets requirements

• root-cause-tracing

  Systematically trace bugs backward through call stack to find original trigger

• scale-game

  Test at extremes (1000x bigger/smaller, instant/year-long) to expose fundamental truths hidden at normal scales

• simplification-cascades

  Find one insight that eliminates multiple components - "if this is true, we don't need X, Y, or Z

• simplify

  Review changed code for reuse, clarity, efficiency, and unnecessary complexity, then apply the smallest behavior-preserving cleanup. Use when simplifying a diff, cleaning a recently changed file, or removing over-engineering without weakening required behavior.

• skill-creator

  Guide for creating effective skills. This skill should be used when users want to create a new skill (or update an existing skill) that extends Claude's capabilities with specialized knowledge, workflows, or tool integrations.

• systematic-debugging

  Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes

• test-driven-development

  Use when implementing any feature or bugfix, before writing implementation code

• verification-before-completion

  Use when about to claim work is complete, fixed, or passing, before committing or creating PRs - requires running verification commands and confirming output before making any success claims; evidence before assertions always

• when-stuck

  Dispatch to the right problem-solving technique based on how you're stuck

• yagni-engineering-principle

  Apply YAGNI to feature planning, architecture, code review, dependency selection, and refactoring by separating committed needs from speculation and choosing the smallest clean solution. Use when evaluating future-proofing, abstractions, optional configuration, infrastructure, or over-engineering.

Similar plugins