By southlab-ai
KG educativo privado e independiente: resuelve OA y recupera currículum, materiales y marcos de evaluación mediante un MCP remoto autenticado.
Buscar evidencia curricular y materiales docentes con el KG Educación v3. Usa query_curriculum para OA, programas e indicadores; usa query_teaching_materials para libros, guías, BDA, actividades y componentes por package_id, OA o estructura interna del material.
Crear evaluaciones originales alineadas a OA usando currículum, materiales y marcos recuperados desde KG Educación V3.
Qué es KG Educación y cómo usar sus cinco tools V3 para recuperar currículum, OA, materiales y marcos de evaluación.
Planificar año, semestre, unidad o clase usando evidencia curricular y materiales recuperados desde KG Educación V3.
Asistente de configuración de kg-educacion v3, un KG educativo privado e independiente con sourcing MINEDUC. Conecta el MCP en Claude Code o Codex, registra la cuenta y configura una API key para ambos clientes. Úsala la primera vez o ante un 401.
External network access
Connects to servers outside your machine
Based on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
Claude Code plugin marketplace by Southlab AI.
| Plugin | Description | Version | Category |
|---|---|---|---|
| agent-bridge | Connect independent Codex or Claude chats with blocking request/reply calls while preserving the native desktop app. | 0.1.0 | Productivity |
| upwork-scraper | Scrape Upwork jobs, analyze market demand, write proposals, optimize rates, and build portfolios. 5 slash commands + 5 AI agents. | 0.2.0 | Freelance |
| the-council | Catch blind spots in architecture decisions with multi-perspective analysis. 4 auto-routed modes, configurable roles, /council:build pipeline, /council:value analysis, memory attribution, progressive hints. | 3.2.0 | Productivity |
| computer-vision | Desktop computer vision and input control for Windows. 28 tools: screenshots, click, type, scroll, OCR, element finder, text extraction, UI trees, app-specific adapters, action verification, and 9 sandbox tools for parallel automation (Claude works in isolated Windows Sandbox while you keep working). | 2.0.0 | Utilities |
codex plugin marketplace add southlab-ai/Claude-Plugin-Marketplace
codex plugin add agent-bridge@southlab-marketplace
Restart Codex Desktop after installation, then invoke the agent-bridge skill from two chats.
Inside Claude Code:
/plugin marketplace add southlab-ai/Claude-Plugin-Marketplace
/plugin install upwork-scraper@southlab-marketplace
/plugin install the-council@southlab-marketplace
/plugin install computer-vision@southlab-marketplace
/plugin install agent-bridge@southlab-marketplace
Close and reopen Claude Code for the MCP server to connect.
Each plugin has a setup command:
/upwork-scraper:setup
/council:setup
/cv-setup
Use the agent-bridge skill in two independent chats. The receiver registers and calls
listen; the sender calls ask and remains blocked until the receiver calls reply.
The default wait is one hour. The bundled MCP client timeout is 7,300 seconds, allowing explicit waits of up to two hours.
| Command | Description |
|---|---|
/upwork-scraper:setup | Install dependencies |
/upwork-scraper:best-matches | Fetch personalized Best Matches |
/upwork-scraper:search <query> | Search jobs with filters |
/upwork-scraper:analyze <skill> | Analyze market demand |
/upwork-scraper:portfolio <skills> | Get portfolio project ideas |
| Command | Description |
|---|---|
/council:setup | Install dependencies (auto-offers init) |
/council:init | Initialize .council/ in your project |
/council:consult <goal> | Multi-perspective consultation (auto-routed: default, debate, plan, reflect) |
/council:value <goal> | Value-realization analysis: scores 4 dimensions (clarity, timeline, perception, discovery) |
/council:build <goal> | Full build pipeline: PRD + tech deck + backlog + feature gate + implementation |
/council:status | View decisions, memory health, staleness warnings, compaction recommendations |
/council:maintain | Compact memory using the curator agent |
/council:update | Migrate council data after a plugin update |
/council:reset | Clear session data (add --all to also clear memory) |
npx claudepluginhub southlab-ai/claude-plugin-marketplace --plugin kg-educacionOrchestrate a fleet of OpenAI Codex agents (GPT-5.6 sol/terra/luna) from Claude Code — ultracode-style multi-agent audits, reviews, migrations, and design panels. Includes a codex-agent skill for spawning single background Codex workers.
Blocking request/reply communication between independent Codex or Claude chats without replacing the desktop app.
Scrape Upwork jobs, analyze market demand, write proposals, evaluate postings, optimize rates, review profiles, and design portfolio projects. Includes 5 slash commands and 5 specialized AI agents.
Desktop computer vision and input control for Claude Code on Windows. 24 tools: screenshots, scene analysis, human-like mouse movement, action recording, UIA-based element invocation (cv_click_ui — works on WinUI 3 apps where SendInput fails), deep UI tree search, click, type, OCR, element finder, text extraction. Background mode via PostMessage.
Session supervisor for Claude Code's Telegram channel — guided VPS setup, persistent sessions, crash recovery, long-term memory
Upstash Context7 MCP server for up-to-date documentation lookup. Pull version-specific documentation and code examples directly from source repositories into your LLM context.
Persistent coding companion for Claude Code, Pi, and Oh My Pi. MCP-based terminal pet with ASCII art, stats, reactions, and personality.
Comprehensive skill pack with 66 specialized skills for full-stack developers: 12 language experts (Python, TypeScript, Go, Rust, C++, Swift, Kotlin, C#, PHP, Java, SQL, JavaScript), 10 backend frameworks, 6 frontend/mobile, plus infrastructure, DevOps, security, and testing. Features progressive disclosure architecture for 50% faster loading.
Consult multiple AI coding agents (Gemini, OpenAI, Grok, Perplexity, plus codex, antigravity, and grok CLIs when installed) to get diverse perspectives on coding problems
Comprehensive startup business analysis with market sizing (TAM/SAM/SOM), financial modeling, team planning, and strategic research
v9.54.1 — Reliability wave: tangle contextual review correction loop with hard round ceiling, progress-supervised review rounds (per-agent stall watch, descendant-tree kills), council diversity and agy pin fixes, marketplace generator source-of-truth fix, provider troubleshooting runbook and cost-expectations docs. Run /octo:setup.