Exécutez n'importe quel Skill dans Manus
en un clic

Exécutez n'importe quel Skill dans Manus en un clic

juliaz-system

Foundational knowledge about the juliaz_agents multi-agent system architecture. ALWAYS trigger this skill when the conversation involves ANY component of Julia's agent ecosystem — orchestrator, bridge, cowork-mcp, OpenClaw, frontend, backend, ADHD agent, julia_medium_agent, or thesis workspace. Also trigger when Raphael asks 'where is X', 'how does X work', 'what connects to what', or any architectural/navigation question about the system. This is the map of the entire codebase and how the pieces fit together.

Exécuter dans Manus

Aperçu

Commande d'installation

npx skills add https://github.com/abzhaw/juliaz_agents --skill juliaz-system

Copiez et collez cette commande dans Claude Code pour installer le skill

Source

abzhaw/juliaz_agents

Étoiles0

Forks0

Mis à jour8 mars 2026 à 21:07

SKILL.md

readonly

name

juliaz-system

description

juliaz-system — Architecture & Navigation

You are working on juliaz_agents — Raphael's multi-agent platform for his master's thesis on autonomous AI collaboration.

Mental Model

Raphael (human) → Antigravity (IDE agent / builder) → Julia (the product being built)

Antigravity = the AI in the IDE (Claude Code / Cowork) that builds Julia
Julia = the multi-agent system being built
OpenClaw = communication gateway (Telegram, WhatsApp, etc.)

3-System Architecture

`julia/` — User-System (the product)

Component	Location	Port	Stack	Role
Frontend	`julia/frontend/`	3002	Next.js 15 + Tailwind + Framer Motion	Dashboard UI with its own AI chat (GPT-4o via Vercel AI SDK)
Bridge	`julia/bridge/`	3001	Express + MCP (streamable HTTP)	Message hub connecting agents ↔ UI. Queue stored in `data/queue.json`
Backend	`julia/backend/`	3000	Express + Prisma + PostgreSQL (Docker)	REST API for persistence: tasks, memories, letters, logs, usage, updates
Orchestrator	`julia/orchestrator/`	—	Claude Haiku (primary) + GPT-4o (fallback)	Julia's brain. Polls bridge every 5s, generates replies, manages memory
Cowork MCP	`julia/cowork-mcp/`	3003	MCP server wrapping Anthropic API	Claude delegation: 6 tools (claude_task, multimodal, code_review, summarize, brainstorm, status)
OpenClaw	`julia/openclaw/`	—	`openclaw` CLI (npm global)	Telegram gateway. Forwards messages to bridge via `julia-relay` skill

`meta/` — Meta-System (development & maintenance)

Component	Location	Schedule	Role
ADHD Agent	`meta/agents/adhd-agent/`	every 4h (LaunchAgent)	System hygiene: scans for duplicate skills, dead agents, orphaned configs
Health Checker	`meta/agents/health-checker/`	every 15min	Service monitoring, self-healing, escalation tiers
Security Agent	`meta/agents/security-agent/`	daily 07:00	Security scanning: ports, credentials, dependencies, Docker
Docs Agent	`meta/agents/docs-agent/`	every 12h	Documentation drift detection
Task Manager	`meta/agents/task-manager/`	every 6h	Task queue integrity, stale task detection
Architecture Agent	`meta/agents/architecture-agent/`	every 6h	System topology scanning, neural map generation

`thesis/` — Thesis-System (research & academic)

Directory	Purpose
`thesis/agents/thesis-agent/`	Academic writing partner (reads system, writes thesis)
`thesis/latex/`	LaTeX thesis source
`thesis/documentation/`	Project logs

Cross-system & config (root level)

Directory	Purpose
`shared-findings/`	Cross-agent communication backbone
`meta/docs/`	System documentation, agent cards, planning prompts
`.superpowers/`	Development framework (brainstorming, TDD, plans)

Message Flow (Telegram → Julia → Reply)

Telegram user sends message
  → OpenClaw gateway receives it (ws://127.0.0.1:18789)
    → OpenClaw POSTs to bridge: POST http://localhost:3001/incoming
      → Bridge stores in queue.json (state: pending)
        → Orchestrator polls via MCP: telegram_get_pending_messages (state → processing)
          → Orchestrator generates reply (Claude Haiku → GPT-4o fallback)
            → Orchestrator calls MCP: telegram_send_reply (state → replied)
              → OpenClaw polls GET /pending-reply/:chatId
                → OpenClaw delivers to Telegram

Key Patterns & Conventions

Agent Definition Files

Each agent directory follows this convention:

SOUL.md — Core identity, personality, values, boundaries
IDENTITY.md — Name, creature type, vibe, emoji
TOOLS.md — Available tools and environment config
AGENTS.md — Behavioral playbook, memory patterns, group chat rules
HEARTBEAT.md — Scheduling, health checks, reporting cadence
HEURISTICS.md — Learned rules from past incidents
MEMORY.md — Persistent context across sessions
USER.md — Info about the user (Raphael)

Tool Definition Patterns

Anthropic format (orchestrator, cowork-mcp): { name, description, input_schema } with JSON Schema
OpenAI format (frontend chat): { function: { name, description, parameters } }
MCP tools (bridge): Defined via server.tool(name, schema, handler)

Error Handling

Graceful fallback: Claude Haiku → GPT-4o (orchestrator)
Exponential backoff: Consecutive errors trigger increasing delays (capped 55s)
Rate limiting: Honors Retry-After header from Anthropic
Fire-and-forget: Memory capture and letter generation never crash main loop
Timeouts: 30s per API call with AbortController

Memory System

Short-term: In-memory conversation history (20 messages = 10 turns per chat)
Long-term: Backend PostgreSQL (memories, letters, logs, tasks)
Memory extraction: gpt-4o-mini categorizes moments as STORY, FEELING, MOMENT, WISH, REFLECTION
Letter generation: Daily physical letters via Lob.com using GPT-4o + seed file + recent memories

Configuration

Environment: .env.example (template), .env.secrets (live keys — NEVER commit)
Process manager: PM2 via ecosystem.config.js (prod) / ecosystem.dev.config.js (dev)
Docker: Only backend runs in Docker (PostgreSQL + Express API)
MCP config: .mcp.json for bridge connection

File Location Quick Reference

When Raphael asks "where is X", use this:

Looking for...	File(s)
Julia's personality/prompt	`julia/orchestrator/src/prompt.ts`
Tool definitions (orchestrator)	`julia/orchestrator/src/tools.ts`
Claude API client	`julia/orchestrator/src/claude.ts`
GPT-4o fallback client	`julia/orchestrator/src/openai.ts`
Main polling loop	`julia/orchestrator/src/index.ts`
Memory extraction logic	`julia/orchestrator/src/memory-keeper.ts`
Letter generation	`julia/orchestrator/src/letter-scheduler.ts` + `julia/orchestrator/src/lob.ts`
Bridge MCP tools	`julia/bridge/src/index.ts`
Bridge message queue	`julia/bridge/data/queue.json`
Cowork MCP tools	`julia/cowork-mcp/src/index.ts`
Frontend chat endpoint	`julia/frontend/app/api/chat/route.ts`
Dashboard page	`julia/frontend/app/page.tsx`
DevOps API route	`julia/frontend/app/api/devops/route.ts`
Backend REST API	`julia/backend/src/index.ts`
Database schema	`julia/backend/prisma/schema.prisma`
Docker setup	`julia/backend/docker-compose.yml`
PM2 configs	`ecosystem.config.js`, `ecosystem.dev.config.js`
OpenClaw relay skill	`julia/openclaw/skills/julia-relay/`
OpenClaw troubleshooting	`julia/openclaw/skills/openclaw-troubleshoot/`
System overview (non-technical)	`meta/docs/agent_system_overview.md`
Agent cards	`meta/docs/agent_cards/`
Ambient agents	`meta/agents/`
Thesis research	`thesis/research_papers/`
Thesis drafts	`thesis/drafts/`
Thesis agent	`thesis/agents/thesis-agent/`

Known Pain Points

These are real issues in the codebase — reference them when relevant:

Hardcoded Mac paths in orchestrator tools (FIXED: now uses /Users/raphael/juliaz_agents/julia/openclaw/skills/email-aberer)
Tool definition duplication between orchestrator and frontend (both define similar tools separately)
No pagination on any backend GET endpoint (returns entire table)
Bridge queue grows unbounded — no pruning of old replied messages
Memory lost on restart — in-memory conversation history clears before DB save
Cowork MCP defaults to Haiku despite being intended for complex delegation
No structured logging — sparse console.log, no log levels
No tests visible — no test files or CI/CD pipeline (except backend has Vitest configured)
No authentication on any endpoint (frontend chat, backend API, bridge)
Silent content truncation — cowork-mcp silently drops content over 25K chars

Backend Database Tables

Table	Key Fields
`task`	title, priority, dueDate, completed
`memory`	chatId, category, content, originalText
`letter`	content, status (DRAFT/SENT), lobId, sentAt
`log`	level, source, message
`usage`	model, promptTokens, completionTokens, totalTokens
`update`	title, content, type

Bridge MCP Tools

Tool	Purpose
`telegram_get_pending_messages`	Fetch & mark messages as processing
`telegram_send_reply`	Queue a reply (with optional messageId)
`telegram_bridge_status`	Status snapshot
`telegram_receive` / `telegram_send`	Compatibility aliases
`bridge_health`	Detailed peer reachability

Plus depuis ce dépôt

même dépôt

juliaz-agent-architect

abzhaw/juliaz_agents

Architecture patterns and anti-patterns for Julia's multi-agent system. Trigger when making architectural decisions — adding agents, changing message flow, redesigning tool registries, or evaluating the system's structure. Also trigger for: 'architecture', 'system design', 'how should agents work together', 'add a new agent', 'agent patterns', or any structural question about the multi-agent system.

2026-03-080

juliaz-agent-builder

abzhaw/juliaz_agents

Scaffolding and creating new agents or sub-agents within the juliaz_agents ecosystem. Trigger whenever Raphael wants to create a new agent, add a new sub-agent, define a new agent's personality/identity, set up agent heartbeats, or modify an existing agent's SOUL/IDENTITY/TOOLS/AGENTS files. Also trigger when discussing agent conventions, the SOUL.md pattern, or how agents should be structured in this project. If someone says 'new agent', 'create an agent', 'agent personality', 'SOUL.md', or 'add a bot' — this is the skill to use.

2026-03-080

juliaz-agent-improve

abzhaw/juliaz_agents

Systematic improvement of Julia's agents through performance analysis, prompt engineering, and validation. Trigger when optimizing any agent's behavior — orchestrator, frontend Julia, OpenClaw relay, or any sub-agent. Also trigger for: 'improve agent', 'agent not working well', 'optimize prompt', 'tool not being used correctly', 'Julia gives wrong answers', or any agent quality issue.

2026-03-080

juliaz-debug

abzhaw/juliaz_agents

Cross-system diagnostics and troubleshooting for the juliaz_agents multi-agent system. Trigger when Raphael reports something is broken, not working, or behaving unexpectedly — messages not arriving, Julia not responding, bridge errors, orchestrator crashes, rate limits, silent failures, queue issues, or any 'why isn't X working' question. Also trigger for: 'debug', 'broken', 'not working', 'error', 'Julia isn't responding', 'messages stuck', 'bridge down', 'check logs', 'what went wrong', or any troubleshooting request. If something in the multi-agent system is misbehaving, this is the skill to reach for.

2026-03-080

juliaz-devops

abzhaw/juliaz_agents

Service management, process supervision, and operational tasks for the juliaz_agents multi-agent system. Trigger whenever Raphael asks to start, stop, restart, or check the status of any service — PM2, Docker, bridge, orchestrator, OpenClaw, cowork-mcp, frontend, or backend. Also trigger for: environment variable management, port conflicts, log tailing, deployment, health checks, 'is Julia running', 'start everything', 'check status', 'why is X down', pm2, docker compose, or any operational/infrastructure task. If the user mentions starting services, checking health, or managing processes — use this skill.

2026-03-080

juliaz-feature

abzhaw/juliaz_agents

Adding new features to the juliaz_agents system — new tools, API endpoints, frontend components, MCP tools, or capabilities. Trigger when Raphael wants to: add a new tool to the orchestrator or bridge, create a new API endpoint in the backend, add a frontend component or page, extend cowork-mcp with new Claude tools, add a new OpenClaw skill, or implement any new capability across the system. Also trigger for 'add a tool', 'new endpoint', 'new page', 'new component', 'extend Julia', 'Julia should be able to...', or any request to add functionality to the multi-agent system.

2026-03-080

Source

abzhaw

abzhaw/juliaz_agents

Ouvrir le dépôt GitHub Voir les dépôts du créateur

Commande d'installation

Téléchargement

Exécuter dans Manus

Utile pourSOC

Développeurs de logicielsProfessions informatiques et mathématiques15-1252L4

name

juliaz-system

description

juliaz-system — Architecture & Navigation

You are working on juliaz_agents — Raphael's multi-agent platform for his master's thesis on autonomous AI collaboration.

Mental Model

Raphael (human) → Antigravity (IDE agent / builder) → Julia (the product being built)

Antigravity = the AI in the IDE (Claude Code / Cowork) that builds Julia
Julia = the multi-agent system being built
OpenClaw = communication gateway (Telegram, WhatsApp, etc.)

3-System Architecture

`julia/` — User-System (the product)

Component	Location	Port	Stack	Role
Frontend	`julia/frontend/`	3002	Next.js 15 + Tailwind + Framer Motion	Dashboard UI with its own AI chat (GPT-4o via Vercel AI SDK)
Bridge	`julia/bridge/`	3001	Express + MCP (streamable HTTP)	Message hub connecting agents ↔ UI. Queue stored in `data/queue.json`
Backend	`julia/backend/`	3000	Express + Prisma + PostgreSQL (Docker)	REST API for persistence: tasks, memories, letters, logs, usage, updates
Orchestrator	`julia/orchestrator/`	—	Claude Haiku (primary) + GPT-4o (fallback)	Julia's brain. Polls bridge every 5s, generates replies, manages memory
Cowork MCP	`julia/cowork-mcp/`	3003	MCP server wrapping Anthropic API	Claude delegation: 6 tools (claude_task, multimodal, code_review, summarize, brainstorm, status)
OpenClaw	`julia/openclaw/`	—	`openclaw` CLI (npm global)	Telegram gateway. Forwards messages to bridge via `julia-relay` skill

`meta/` — Meta-System (development & maintenance)

Component	Location	Schedule	Role
ADHD Agent	`meta/agents/adhd-agent/`	every 4h (LaunchAgent)	System hygiene: scans for duplicate skills, dead agents, orphaned configs
Health Checker	`meta/agents/health-checker/`	every 15min	Service monitoring, self-healing, escalation tiers
Security Agent	`meta/agents/security-agent/`	daily 07:00	Security scanning: ports, credentials, dependencies, Docker
Docs Agent	`meta/agents/docs-agent/`	every 12h	Documentation drift detection
Task Manager	`meta/agents/task-manager/`	every 6h	Task queue integrity, stale task detection
Architecture Agent	`meta/agents/architecture-agent/`	every 6h	System topology scanning, neural map generation

`thesis/` — Thesis-System (research & academic)

Directory	Purpose
`thesis/agents/thesis-agent/`	Academic writing partner (reads system, writes thesis)
`thesis/latex/`	LaTeX thesis source
`thesis/documentation/`	Project logs

Cross-system & config (root level)

Directory	Purpose
`shared-findings/`	Cross-agent communication backbone
`meta/docs/`	System documentation, agent cards, planning prompts
`.superpowers/`	Development framework (brainstorming, TDD, plans)

Message Flow (Telegram → Julia → Reply)

Telegram user sends message
  → OpenClaw gateway receives it (ws://127.0.0.1:18789)
    → OpenClaw POSTs to bridge: POST http://localhost:3001/incoming
      → Bridge stores in queue.json (state: pending)
        → Orchestrator polls via MCP: telegram_get_pending_messages (state → processing)
          → Orchestrator generates reply (Claude Haiku → GPT-4o fallback)
            → Orchestrator calls MCP: telegram_send_reply (state → replied)
              → OpenClaw polls GET /pending-reply/:chatId
                → OpenClaw delivers to Telegram

Key Patterns & Conventions

Agent Definition Files

Each agent directory follows this convention:

SOUL.md — Core identity, personality, values, boundaries
IDENTITY.md — Name, creature type, vibe, emoji
TOOLS.md — Available tools and environment config
AGENTS.md — Behavioral playbook, memory patterns, group chat rules
HEARTBEAT.md — Scheduling, health checks, reporting cadence
HEURISTICS.md — Learned rules from past incidents
MEMORY.md — Persistent context across sessions
USER.md — Info about the user (Raphael)

Tool Definition Patterns

Anthropic format (orchestrator, cowork-mcp): { name, description, input_schema } with JSON Schema
OpenAI format (frontend chat): { function: { name, description, parameters } }
MCP tools (bridge): Defined via server.tool(name, schema, handler)

Error Handling

Graceful fallback: Claude Haiku → GPT-4o (orchestrator)
Exponential backoff: Consecutive errors trigger increasing delays (capped 55s)
Rate limiting: Honors Retry-After header from Anthropic
Fire-and-forget: Memory capture and letter generation never crash main loop
Timeouts: 30s per API call with AbortController

Memory System

Short-term: In-memory conversation history (20 messages = 10 turns per chat)
Long-term: Backend PostgreSQL (memories, letters, logs, tasks)
Memory extraction: gpt-4o-mini categorizes moments as STORY, FEELING, MOMENT, WISH, REFLECTION
Letter generation: Daily physical letters via Lob.com using GPT-4o + seed file + recent memories

Configuration

Environment: .env.example (template), .env.secrets (live keys — NEVER commit)
Process manager: PM2 via ecosystem.config.js (prod) / ecosystem.dev.config.js (dev)
Docker: Only backend runs in Docker (PostgreSQL + Express API)
MCP config: .mcp.json for bridge connection

File Location Quick Reference

When Raphael asks "where is X", use this:

Looking for...	File(s)
Julia's personality/prompt	`julia/orchestrator/src/prompt.ts`
Tool definitions (orchestrator)	`julia/orchestrator/src/tools.ts`
Claude API client	`julia/orchestrator/src/claude.ts`
GPT-4o fallback client	`julia/orchestrator/src/openai.ts`
Main polling loop	`julia/orchestrator/src/index.ts`
Memory extraction logic	`julia/orchestrator/src/memory-keeper.ts`
Letter generation	`julia/orchestrator/src/letter-scheduler.ts` + `julia/orchestrator/src/lob.ts`
Bridge MCP tools	`julia/bridge/src/index.ts`
Bridge message queue	`julia/bridge/data/queue.json`
Cowork MCP tools	`julia/cowork-mcp/src/index.ts`
Frontend chat endpoint	`julia/frontend/app/api/chat/route.ts`
Dashboard page	`julia/frontend/app/page.tsx`
DevOps API route	`julia/frontend/app/api/devops/route.ts`
Backend REST API	`julia/backend/src/index.ts`
Database schema	`julia/backend/prisma/schema.prisma`
Docker setup	`julia/backend/docker-compose.yml`
PM2 configs	`ecosystem.config.js`, `ecosystem.dev.config.js`
OpenClaw relay skill	`julia/openclaw/skills/julia-relay/`
OpenClaw troubleshooting	`julia/openclaw/skills/openclaw-troubleshoot/`
System overview (non-technical)	`meta/docs/agent_system_overview.md`
Agent cards	`meta/docs/agent_cards/`
Ambient agents	`meta/agents/`
Thesis research	`thesis/research_papers/`
Thesis drafts	`thesis/drafts/`
Thesis agent	`thesis/agents/thesis-agent/`

Known Pain Points

These are real issues in the codebase — reference them when relevant:

Hardcoded Mac paths in orchestrator tools (FIXED: now uses /Users/raphael/juliaz_agents/julia/openclaw/skills/email-aberer)
Tool definition duplication between orchestrator and frontend (both define similar tools separately)
No pagination on any backend GET endpoint (returns entire table)
Bridge queue grows unbounded — no pruning of old replied messages
Memory lost on restart — in-memory conversation history clears before DB save
Cowork MCP defaults to Haiku despite being intended for complex delegation
No structured logging — sparse console.log, no log levels
No tests visible — no test files or CI/CD pipeline (except backend has Vitest configured)
No authentication on any endpoint (frontend chat, backend API, bridge)
Silent content truncation — cowork-mcp silently drops content over 25K chars

Backend Database Tables

Table	Key Fields
`task`	title, priority, dueDate, completed
`memory`	chatId, category, content, originalText
`letter`	content, status (DRAFT/SENT), lobId, sentAt
`log`	level, source, message
`usage`	model, promptTokens, completionTokens, totalTokens
`update`	title, content, type

Bridge MCP Tools

Tool	Purpose
`telegram_get_pending_messages`	Fetch & mark messages as processing
`telegram_send_reply`	Queue a reply (with optional messageId)
`telegram_bridge_status`	Status snapshot
`telegram_receive` / `telegram_send`	Compatibility aliases
`bridge_health`	Detailed peer reachability

juliaz-system

juliaz-system — Architecture & Navigation

Mental Model

3-System Architecture

julia/ — User-System (the product)

meta/ — Meta-System (development & maintenance)

thesis/ — Thesis-System (research & academic)

Cross-system & config (root level)

Message Flow (Telegram → Julia → Reply)

Key Patterns & Conventions

Agent Definition Files

Tool Definition Patterns

Error Handling

Memory System

Configuration

File Location Quick Reference

Known Pain Points

Backend Database Tables

Bridge MCP Tools

Plus depuis ce dépôt

juliaz-system — Architecture & Navigation

Mental Model

3-System Architecture

julia/ — User-System (the product)

meta/ — Meta-System (development & maintenance)

thesis/ — Thesis-System (research & academic)

Cross-system & config (root level)

Message Flow (Telegram → Julia → Reply)

Key Patterns & Conventions

Agent Definition Files

Tool Definition Patterns

Error Handling

Memory System

Configuration

File Location Quick Reference

Known Pain Points

Backend Database Tables

Bridge MCP Tools

Plus depuis ce dépôt

`julia/` — User-System (the product)

`meta/` — Meta-System (development & maintenance)

`thesis/` — Thesis-System (research & academic)

`julia/` — User-System (the product)

`meta/` — Meta-System (development & maintenance)

`thesis/` — Thesis-System (research & academic)