framework-architecture
Design and evolve the architecture of the Paracle multi-agent framework. Use when discussing system design, architecture decisions, component structure, or technical debt.
Explorez des skills pour le développement, le contenu, les données et la productivité. Comparez les descriptions et dépôts.
Design and evolve the architecture of the Paracle multi-agent framework. Use when discussing system design, architecture decisions, component structure, or technical debt.
Expert-level semantic versioning, package publishing, changelog generation, and release orchestration. Use for version management, PyPI/Docker releases, and deployment automation.
Write comprehensive tests (unit, integration, e2e), manage test coverage, and ensure code quality. Use when writing tests, improving coverage, or debugging test failures.
Create a template file for human reviewers to write free-form feedback before AI code review.
Structured problem-solving workflow for debugging. Use after 3 failed attempts at solving an issue, when stuck on a problem, or when encountering repeated errors.
Convert free-form reviewer notes to structured feedback format with interactive clarification.
Redmine integration skill - URL parsing, issue query and management (Rust implementation)
Use when writing UnoCSS with presetOnmax workflow - covers attribute mode patterns, fluid spacing (f- prefix), scale-to-pixel (1px base), custom variants (hocus, reka-*, data-state), nimiq-css design system (nq...
Iterative writing loop. Gemini 3 Pro writes, Claude Agent SDK reviews autonomously. Use for blog posts, docs, technical content needing quality iteration.
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 an agent's capabilities with specialized knowledge, workflows, or...
Build and refactor modern React (18+) using maintainable patterns, strong state management, performance optimization, and accessibility best practices.
Review code for correctness, maintainability, performance, and security. Produce actionable, prioritized feedback and concrete fixes aligned with repo standards.
Create or update root and nested AGENTS.md files that document scoped conventions, monorepo module maps, cross-domain workflows, and (optionally) per-module feature maps (feature -> paths, entrypoints, tests, d...
Plan and implement CRM Orbit data migrations for Automerge snapshots and Drizzle persistence, including schema additions, event payload changes, and backfills. Use when adding/removing fields, changing persiste...
Assemble and coordinate multi-agent teams: decompose tasks, select skills/agents, design workflows, and manage execution with monitoring and recovery.
Create, update, and improve clear, accurate, and actionable documentation for developers and users.
Curate CRM Orbit UI i18n strings and mappings. Use when adding or editing user-facing copy, auditing en.json, or keeping i18n/events.ts and i18n/enums.ts in sync with new keys. Scope: CRMOrbit/i18n/en.json and...
Safely refactor code to reduce complexity, improve structure, and increase maintainability while preserving behavior.
Create high-quality git commits: review/stage intended changes, split into logical commits, and write clear commit messages (including Conventional Commits). Use when the user asks to commit, craft a commit mes...
Design intuitive, accessible, and visually coherent interfaces aligned with brand and product goals.
Maintain, retrieve, and normalize shared project context (decisions, constraints, standards, task state) for multi-skill workflows. Use when Codex must be the source of truth for project context, summarize cons...
Analyze and improve database performance through safe, measurable query, index, and configuration optimizations.
Expert TypeScript development with advanced type safety, full-stack patterns, and build optimization. Use when designing or refactoring TypeScript, auditing type safety, or improving TS tooling and compile perf...
Tools for interacting with the Spatia Atomic System
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.