Topic: multi-agent
1,931 skills in this topic.
-
cli-reference
Claude Code CLI commands, flags, headless mode, and automation patterns
vibeeval/vibecosystem 458
-
circuit-breaker
Agent hata toleransi ve devre kesici pattern. Ust uste hata yapan agent'i durdur, cooldown uygula, fallback'e gec. Kaskatli hatalari ve sonsuz retry dongularini onler.
vibeeval/vibecosystem 458
-
graceful-degradation
Graceful Degradation with Helpful Messages
vibeeval/vibecosystem 458
-
deep-interview
Mathematically rigorous Socratic interview system that drives ambiguity below 20% before any code is written. One question per message, weighted ambiguity scoring, brownfield-aware, outputs a complete PRD. Replaces discovery-interview with a stricter protocol.
vibeeval/vibecosystem 458
-
github-search
Search GitHub code, repositories, issues, and PRs via MCP
vibeeval/vibecosystem 458
-
design-to-code
Figma-to-code translation, design tokens, spacing/typography scales, responsive breakpoints, and design system bridge patterns.
vibeeval/vibecosystem 458
-
fix
Meta-skill workflow orchestrator for bug investigation and resolution. Routes to debug, implement, test, and commit based on scope.
vibeeval/vibecosystem 458
-
eval-harness
Formal evaluation framework for Claude Code sessions implementing eval-driven development (EDD) principles
vibeeval/vibecosystem 458
-
form-validation
React Hook Form + Zod integration, multi-step forms, optimistic validation, server-side error mapping, and file upload patterns.
vibeeval/vibecosystem 458
-
event-driven-patterns
Message queue patterns with BullMQ, Kafka, RabbitMQ - saga, outbox, dead letter queue, exactly-once semantics.
vibeeval/vibecosystem 458
-
loogle-search
Search Mathlib for lemmas by type signature pattern using Loogle.
vibeeval/vibecosystem 458
-
content-marketing
Icerik pazarlama ve SEO odakli yazi uretimi. AI slop temizleme (30+ pattern), icerik kalite skorlama (5 boyut), watermark temizleme, copywriting formulleri (AIDA, PAS, BAB), programmatic SEO ve icerik stratejisi.
vibeeval/vibecosystem 458
-
layered-recall
Progressive memory recall with 4 scope layers AND 3 depth layers. Scope: identity > project > room > deep. Depth: IDs only > summary > full. 10-50x token savings through fetch-on-confirmation pattern.
vibeeval/vibecosystem 458
-
llm-tuning-patterns
LLM Tuning Patterns
vibeeval/vibecosystem 458
-
help
Interactive workspace discovery - learn what tools, workflows, agents, and hooks are available
vibeeval/vibecosystem 458
-
art-director
AI art direction system. Claude directs image generation models (Gemini, DALL-E, Flux) via structured prompts. Generate banners, diagrams, logos, screenshots, and social media visuals without leaving the terminal.
vibeeval/vibecosystem 458
-
api-patterns
API design, versioning, testing, schema validation, and contract testing patterns for REST and GraphQL APIs.
vibeeval/vibecosystem 458
-
learn
vibeeval/vibecosystem 458
-
git-commits
Git Commit Rules
vibeeval/vibecosystem 458
-
math-help
Guide to the math cognitive stack - what tools exist and when to use each
vibeeval/vibecosystem 458
-
complete-skill
A complete skill for E2E testing
vibeeval/vibecosystem 458
-
hook-developer
Complete Claude Code hooks reference - input/output schemas, registration, testing patterns
vibeeval/vibecosystem 458
-
background-agent-pings
Background Agent Pings
vibeeval/vibecosystem 458
-
django-patterns
Django architecture patterns, REST API design with DRF, ORM best practices, caching, signals, middleware, and production-grade Django apps.
vibeeval/vibecosystem 458