stream-chain
Stream-JSON chaining for multi-agent pipelines, data transformation, and sequential workflows
Find an Agent Skill for your task. Read the guide and copy the install command.
Updated 11-05 00:16
25,648 results
Stream-JSON chaining for multi-agent pipelines, data transformation, and sequential workflows
Advanced swarm orchestration patterns for research, development, testing, and complex distributed workflows
Orchestrate multi-agent swarms with agentic-flow for parallel task execution, dynamic topology, and intelligent coordination. Use when scaling beyond single…
CLI modernization and hooks system enhancement for claude-flow v3. Implements interactive prompts, command decomposition, enhanced hooks integration, and…
Deep agentic-flow@alpha integration implementing ADR-001. Eliminates 10,000+ duplicate lines by building claude-flow as specialized extension rather than…
This skill should be used when the user asks "what is Sablier", "explain Sablier protocol", "how does Sablier work", "Sablier vesting", "Sablier airdrops",…
Transition from a hands-on "bricklayer" to a high-level "architect" by managing a fleet of autonomous AI agents. Use this when you need to scale engineering…
Generate a self-contained HTML viewer for any Claude Code session, including agent team sessions with full inter-agent DM timelines. Use whenever the user asks…
Create new agent skills with proper structure, progressive disclosure, and bundled resources. Use when user wants to create, write, or build a new skill.
This skill should be used when working with Restate durable execution framework, building workflows, virtual objects, or services that need automatic retries,…
Create new skills. Only trigger on `/create-skill`.
Create new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, edit, or optimize an…
Ask which skill or process to use. A router over the skills in this repo's main flow. Triggered when the user says "which one should I use", "ask-wx", "where do I start", "what skill fits this situation", or when facing multiple similar skills and unsure which to pick.
Search historical sessions across agent CLIs and provide a resume command. When the user says "find that earlier conversation about X", "I forgot which agent I chatted about X in", "where is yesterday's session", "help me resume that last session", "find session", "search sessions", or wants to find/resume some agent…
Rules for when an agent should recall from long-term memory before acting and when it should save decisions, corrections and failures afterwards. Works with…
Delegate bounded work to other AI agents while preserving context, ownership, and progress checks.
Rewrite allowed prompts to reduce false-positive safety triggers without bypassing policy or changing intent.
Interview the user relentlessly about a plan or design. Use when the user wants to stress-test a plan before building, or uses any 'grill' trigger phrases.
Build LLM applications, RAG systems, and prompt pipelines. Implements vector search, agent orchestration, and AI API integrations. Use when working with LLM…
Build Telegram bots with grammY, Telegraf, or python-telegram-bot. Covers Bot API v10.3 webhooks vs polling, inline keyboards, commands, middleware patterns,…
Detect price gaps between TASE and US listings of the same dual-listed company (NICE, Teva, Elbit, Tower, Palo Alto Networks, and about 30 registered pairs),…
Call the Coze agent API for conversations, workflow execution, and other operations. Use when the user needs to integrate the Coze agent, call the Coze API, or develop Coze-related applications. Supports streaming and non-streaming conversations, workflow invocation, and other features.
Build on-device AI features in React Native and Expo apps with React Native ExecuTorch. Use when adding AI to a mobile app without cloud dependencies —…
Create a delegated SohoPay agent session. Use when the operator asks for create_agent_session — not human-direct and not an HTTP 402 pay.