Command Claude Code
Works for you. Go outside and live. — AI orchestrator that auto-routes tasks to the cheapest model that solves them. 70% run free on local models. Self-auditing, self-improving, zero prompting skill needed. Built with vibe coding by a finance student. Your models, your data.
Command Claude Code
Works for you. Go outside and live. — AI orchestrator that auto-routes tasks to the cheapest model that solves them. 70% run free on local models. Self-auditing, self-improving, zero prompting skill needed. Built with vibe coding by a finance student. Your models, your data.
Command Claude Code
Works for you. Go outside and live. — AI orchestrator that auto-routes tasks to the cheapest model that solves them. 70% run free on local models. Self-auditing, self-improving, zero prompting skill needed. Built with vibe coding by a finance student. Your models, your data.
Command Claude Code
Declara el proyecto activo (scope global) para atribucion de coste/horas en agentactions. Sin argumento, muestra el proyecto actual.
Command Claude Code
Works for you. Go outside and live. — AI orchestrator that auto-routes tasks to the cheapest model that solves them. 70% run free on local models. Self-auditing, self-improving, zero prompting skill needed. Built with vibe coding by a finance student. Your models, your data.
Command Claude Code
Works for you. Go outside and live. — AI orchestrator that auto-routes tasks to the cheapest model that solves them. 70% run free on local models. Self-auditing, self-improving, zero prompting skill needed. Built with vibe coding by a finance student. Your models, your data.
Command Claude Code
/svsi-review {slug} # modo interactivo en sesión Claude Code /svsi-review --batch {file} # delega a predrivereview.py (tmux, no en sesión) /svsi-review --stats # métricas acumuladas desde SQLite.
Command Claude Code
Works for you. Go outside and live. — AI orchestrator that auto-routes tasks to the cheapest model that solves them. 70% run free on local models. Self-auditing, self-improving, zero prompting skill needed. Built with vibe coding by a finance student. Your models, your data.
Command Claude Code
Works for you. Go outside and live. — AI orchestrator that auto-routes tasks to the cheapest model that solves them. 70% run free on local models. Self-auditing, self-improving, zero prompting skill needed. Built with vibe coding by a finance student. Your models, your data.
Skill Claude CodeCodex
Run complete system health audit of DQIII8 — checks DB integrity, agent performance, pipeline connections, error log, and services. Produces a scored Markdown report.
Skill Claude CodeCodex
Defensive security — reads red-team findings and systematically patches every vulnerability. Hardens code, adds input validation, fixes permissions, and verifies each fix. Works from the latest red-team report.
Skill Claude CodeCodex
Skill para investigar/extraer información de una URL bajo demanda usando el Chrome autenticado del usuario a través del túnel CDP en localhost:9333 (o localhost:9222 para el Chrome local del VPS). Una investigación a la vez.
Skill Claude CodeCodex
Save and verify session state using git commits and a checkpoints log. Use before risky multi-file changes or after completing a significant implementation block.
Skill Claude CodeCodex
Skill para despachar tareas a agentes NIM/Groq/GitHub desde esta sesión CC — DORMANTE bajo Anthropic-only (directiva usuario 2026-08-18), ver archivo al inicio del cuerpo. Habilita el Hermes Work Loop — CC orquesta, agentes B/B+ ejecutan (cuando reactivado).
Skill Claude CodeCodex
Upload DOCX files from intl-reports to Google Drive Carpeta 3 using rclone. Zero reasoning — action only.
Skill Claude CodeCodex
Generate a session handover note at the end of a work session. The manual /handover path saves to sessions/ locally only, never committing or pushing — stop.py's separate automatic path does commit and push (see §Two implementations). Suggested after long sessions (50+ turns).
Skill Claude CodeCodex
Shows learned instincts from dqiii8.db, grouped by project and confidence. Internal diagnostic tool — not for user invocation.
Skill Claude CodeCodex
Genera y entrega informes de internacionalización (Diagnóstico + Plan) para pymes españolas. Batch pipeline via Orchestrator v4 (core.cli) desde tmux externo. NUNCA empresa-a-empresa con Agent Haiku manual.
Skill Claude CodeCodex
Multi-agent coordination protocol for tasks spanning 3+ distinct domains. Decomposes goal into sub-tasks, spawns specialized agents in isolated worktrees, aggregates results.
Skill Claude CodeCodex
Activa un modo de trabajo para DQIII8. Opciones: analyst | coder | creative. El modo persiste hasta fin de sesion o reinicio del VPS.
Skill Claude CodeCodex
Adversarial review of a plan file — a single Opus pass — before implementation of a ≥3-module or ambiguous-scope change.
Skill Claude CodeCodex
Analyze and optimize a prompt for the DQIII8 ecosystem. Classifies prompt type (LLM routing, image gen, TTS, agent instruction, Telegram), scores 5 dimensions, produces optimized version.
Skill Claude CodeCodex
Run the DQIII8 quality pipeline — format (Black), imports (isort), lint (ruff), tests (pytest), security scan. Used internally by checkpoint and pre-commit flows.
Skill Claude CodeCodex
Adversarial security testing — attempts to break the codebase using real hacker techniques. Tests OWASP Top 10, prompt injection, MCP poisoning, dependency attacks, auth bypass, and vibe-coding-specific patterns. Generates exploit report. NEVER auto-invoked — user must explicitly request.