Découvrez les skills Développement, comparez leurs dépôts et consultez leurs instructions.
Use when Claude Code needs a second opinion, verification, or deeper research on technical matters. This includes researching how a library or API works, confirming implementation approaches, verifying technica...
Applies general rules for Convex development, emphasizing schema design, validator usage, index-first query patterns, function registration, and correct handling of system fields.
Promotes modular design with distinct files for models, services, controllers, and utilities.
Use when a plan, finding, or design needs adversarial review before committing to it
This rule enforces the Don't Repeat Yourself principle to avoid code duplication and improve maintainability.
Unified skill that guides spec creation through structured, interactive process.
A complex but safe skill for project scaffolding
Provides OOP programming standards including method overriding, equals/hashCode, wrapper types, serialization, and access control. Invoke when user asks about OOP best practices or class design patterns.
Guides architects on when and how to use goal-seeking agents as a design pattern. This skill helps evaluate whether autonomous agents are appropriate for a given problem, how to structure their objectives, inte...
Multi-repository orchestration for coordinating atomic changes across dependent repositories. Tracks dependency graphs, coordinates cross-repo PRs, and detects breaking changes.
Writing clear, discoverable software documentation following the Eight Rules and Diataxis framework. Use when creating README files, API docs, tutorials, how-to guides, or any project documentation. Automatical...
Analyzes events through sociological lens using social structures, institutions, stratification, culture, norms, collective behavior, and multiple theoretical perspectives (functionalist, conflict, symbolic int...
Generates agentic outside-in tests using gadugi-agentic-test framework for CLI, TUI, Web, and Electron apps. Use when you need behavior-driven tests that verify external interfaces without internal implementati...
Proactive context window management via token monitoring, intelligent extraction, and selective rehydration. Features predictive budget monitoring, context health indicators, and priority-based retention. Use w...
Analyzes events through narrative lens using story structure, character arc analysis, dramatic tension, thematic development, and narrative theory (three-act structure, hero's journey, conflict-resolution). Pro...
Creates personalized learning paths for technologies, frameworks, or concepts. Use for user-interactive session only for onboarding new technologies, hackathon skill-building, or personal development planning....
Cross-session learning system that extracts insights from session transcripts and injects relevant past learnings at session start. Uses simple keyword matching for relevance. Complements DISCOVERIES.md/PATTERN...
Automated reproduction of comprehensive model evaluation benchmarks following the Benchmark Suite V3. Auto-activates for model benchmarking, comparison evaluation, or performance testing between AI models.
Auto-generates code flow diagrams from Python module analysis. Detects when architecture diagrams become stale (code changed, diagram didn't). Use when: creating new modules, reviewing PRs for architecture impa...
Generates and improves tests following TDD principles. Activates when new features are implemented, test coverage is low, or user requests tests. Ensures comprehensive test coverage with unit, integration, and...
Auto-invokes ultrathink workflow for any work request (default orchestrator)
Philosophy compliance guardian - ensures code aligns with amplihack's ruthless simplicity, brick philosophy, and Zen-like minimalism through systematic review
Structured multi-perspective debate for important architectural decisions and complex trade-offs
Expert backlog manager that prioritizes work using multi-criteria scoring, analyzes dependencies, and recommends optimal next tasks. Activates when managing backlogs, prioritizing work, adding items, or analyzi...
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.