langgraph-supervisor
LangGraph supervisor-worker pattern. Use when building central coordinator agents that route to specialized workers, implementing round-robin or priority-based agent dispatch.
Découvrez les skills Blockchain, comparez leurs dépôts et consultez leurs instructions.
LangGraph supervisor-worker pattern. Use when building central coordinator agents that route to specialized workers, implementing round-robin or priority-based agent dispatch.
Use when creating or improving golden datasets for AI evaluation. Defines quality criteria, curation workflows, and multi-agent analysis patterns for test data.
CLIP, SigLIP 2, Voyage multimodal-3 patterns for image+text retrieval, cross-modal search, and multimodal document chunking. Use when building RAG with images, implementing visual search, or hybrid retrieval.
Full-power feature implementation with parallel subagents, skills, and MCPs. Use when implementing features, building features, creating features, or developing features.
LangGraph checkpointing and persistence. Use when implementing fault-tolerant workflows, resuming interrupted executions, debugging with state history, or avoiding re-running expensive operations.
Provider-native prompt caching for Claude and OpenAI. Use when optimizing LLM costs with cache breakpoints, caching system prompts, or reducing token costs for repeated prefixes.
Multi-agent frameworks beyond LangGraph. CrewAI crews, Microsoft Agent Framework, OpenAI Agents SDK. Use when building multi-agent systems, choosing frameworks.
Use when creating or developing anything, before writing code or implementation plans. Brainstorming skill refines ideas through structured questioning and alternatives.
4-phase systematic debugging for flow-fix. NO FIXES WITHOUT ROOT CAUSE INVESTIGATION FIRST.
Decide how to complete a development branch: merge, PR, squash, or cleanup.
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 as...
目录级 CLAUDE.md 生成。触发:mkdir、create directory、目录结构变更。
文件头三行契约注释。触发:create file、新建文件、编写代码。
注意力刷新协议。在关键时刻强制读取核心文档,防止目标遗忘。被 flow-dev, flow-ralph 等命令引用。
Use when ready to publish a new version of cc-devflow npm package to npm registry
Quick reference guide to CC-DevFlow Constitution v2.0.0 with links to full text. Covers all 10 Articles and Phase -1 Gates.
File naming conventions, directory structure, and YAML frontmatter standards for CC-DevFlow. Consolidates shared conventions from all agents.
Real-time Constitution compliance checker for devflow documents. Blocks partial implementations and hardcoded secrets during file editing.
CC-DevFlow workflow router and agent recommender. Use when starting requirements, running flow commands, or asking about devflow processes.
Enforces TDD order in TASKS.md - Tests MUST be marked complete before Implementation tasks. Blocks violations in real-time.
Handle code review feedback with technical rigor. Don't blindly agree - verify before implementing.
在 /flow-init 阶段强制触发,用于捕捉需求的原始意图、探索方案、记录决策。确保后续流程有明确的北极星可追溯。
Enforces TDD Iron Law in flow-dev. NO PRODUCTION CODE WITHOUT A FAILING TEST FIRST.
Use this skill when update kata to latest version with changelog display. Triggers include "update".
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.