senda-labs
OrganizationWorks 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.
Categories
Indexed Skills (17)
blue-team
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.
handover
Generate a session handover note at the end of a work session. Saves to sessions/, updates project status, commits and pushes. Auto-invoked after long sessions (50+ turns).
instinct-status
Shows learned instincts from dqiii8.db, grouped by project and confidence. Internal diagnostic tool — not for user invocation.
intl-reports
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.
prompt-optimize
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.
red-team
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.
security-cycle
Run iterative red-team/blue-team cycles until the codebase is hardened. Each cycle runs /red-team, then /blue-team, then /red-team again to verify fixes hold. Stops when red-team finds 0 CRITICAL and 0 HIGH findings.
speckit
Spec-Driven Development (SDD) con github/spec-kit. Úsalo para arrancar cualquier feature no trivial en un proyecto nuevo o existente. Cubre instalación, ciclo completo SDD y restricciones críticas del entorno dqiii8.
svsi
Pre-revisión semántica de informes de internacionalización antes de subir al Drive compartido. Detecta inconsistencias entre cuestionario, diagnóstico y plan. Propone correcciones focales (surgical_edit) en sesión o genera handoff para tmux (regen_section). Trigger: "revisa el informe de X", "pre-review X", "checkea X antes de Drive", "/svsi-review X".
transcript-learn
Extract knowledge from video transcripts (YouTube, courses, seminars, podcasts) and convert to DQ knowledge chunks, skills, or agent definitions. Accepts YouTube URLs or .txt transcript files. ONLY invoked explicitly by user — never auto-invoked.
audit
Run complete system health audit of DQIII8 — checks DB integrity, agent performance, pipeline connections, error log, and services. Produces a scored Markdown report.
checkpoint
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.
gemini-review
Launch an efficiency audit on modified Python files using Aider + Gemini 2.0 Flash. Analyzes bugs, efficiency, readability, and security. Saves report to database/audit_reports/.
mobilize
Multi-agent coordination protocol for tasks spanning 3+ distinct domains. Decomposes goal into sub-tasks, spawns specialized agents in isolated worktrees, aggregates results.
skill-create
Analyzes DQIII8 git history to extract patterns and generate SKILL.md files in skills-registry/custom/
test-team
Agent team coordination test — research-analyst gathers Kelly Criterion info, python-specialist implements it. Validates sequential agent coordination via tasks/results/ handoff.
weekly-review
Generate weekly dashboard update — reads sessions from last 7 days, queries metrics from dqiii8.db, regenerates 00_DASHBOARD.md, commits and pushes.
Bio shown is the top-scored skill's repo description as a fallback — real GitHub bios land in a future update.