GitHub
maintaining-consistent-abstractions
Class interfaces present one cohesive abstraction - don't mix domain logic with serialization, persistence, or unrelated concerns
☆ 38Voir le skill
Skills IA Tests et sécurité
Découvrez les skills Tests et sécurité, comparez leurs dépôts et consultez leurs instructions.
Catégories: Tests et sécurité
Tests et sécurité Effacer les filtres
Explorer
GitHub
exploring-alternatives
Try 2-3 different approaches before implementing - don't settle for first design you think of
☆ 38Voir le skill
GitHub
encapsulating-complexity
Hide implementation details behind interfaces - work at domain level (what), not implementation level (how)
☆ 38Voir le skill
GitHub
writing-plans
Create detailed implementation plans with bite-sized tasks for engineers with zero codebase context
☆ 38Voir le skill
GitHub
testing-skills-with-subagents
RED-GREEN-REFACTOR for process documentation - baseline without skill, write addressing failures, iterate closing loopholes
☆ 38Voir le skill
GitHub
single-purpose-variables
Use each variable for exactly one purpose - no hybrid coupling or hidden meanings
☆ 38Voir le skill
GitHub
commenting-intent
Comment WHY code exists and non-obvious decisions, not WHAT code does (mechanics)
☆ 38Voir le skill
GitHub
reducing-complexity
Managing complexity is software's primary technical imperative - all other goals are secondary
☆ 38Voir le skill
GitHub
designing-before-coding
Design in pseudocode first, iterate approaches, then translate to code
☆ 38Voir le skill
GitHub
your-skill-name
Brief description of what this Skill does and when to use it. Include specific trigger phrases. Use when user asks "trigger phrase 1", "trigger phrase 2", or wants to [outcome]. Max 1024 characters.
☆ 38Voir le skill
GitHub
your-skill-name
Brief description of what this Skill does and when to use it. Include specific trigger phrases users would say. Use when user asks "trigger phrase 1", "trigger phrase 2", or wants to [outcome]. Max 1024 charact...
☆ 38Voir le skill
GitHub
remembering-conversations
Search previous Claude Code conversations for facts, patterns, decisions, and context using semantic or text search
☆ 38Voir le skill
GitHub
flow-planner
Plan phases, tasks, and iterations. Use when structuring new work, adding features, or organizing development plans.
☆ 38Voir le skill
GitHub
naming-variables
Choose names that fully and accurately describe what the variable represents
☆ 38Voir le skill
GitHub
brainstorming-ideas-into-designs
Interactive idea refinement using Socratic method to develop fully-formed designs
☆ 38Voir le skill
GitHub
flow-builder
Execute implementation work with gate checks and verification. Use when user wants to code, build features, implement iterations, or execute action items. Enforces gates, guides workflow, tracks progress.
☆ 38Voir le skill
GitHub
flow-completer
Mark tasks and phases complete after verification. Use when finishing tasks, closing phases, or marking work done. Ensures all work verified before completion.
☆ 38Voir le skill
GitHub
subagent-driven-development
Execute implementation plan by dispatching fresh subagent for each task, with code review between tasks
☆ 38Voir le skill
GitHub
requesting-code-review
Dispatch code-reviewer subagent to review implementation against plan or requirements before proceeding
☆ 38Voir le skill
GitHub
executing-plans
Execute detailed plans in batches with review checkpoints
☆ 38Voir le skill
GitHub
using-git-worktrees
Create isolated git worktrees with smart directory selection and safety verification
☆ 38Voir le skill
GitHub
finishing-a-development-branch
Complete feature development with structured options for merge, PR, or cleanup
☆ 38Voir le skill
GitHub
refactoring-safely
Refactor with tests first, one change at a time, never mix refactoring with bug fixes or new features
☆ 38Voir le skill
GitHub
creating-skills
TDD for process documentation - test with subagents before writing, iterate until bulletproof
☆ 38Voir le skill
Le classement utilise les étoiles du dépôt GitHub indexé. Plusieurs skills peuvent partager ce nombre : ce n’est ni un nombre d’installations ni une note de qualité.