All authors
Claude Skills by senda-labs
github.com/senda-labs26 skills1 installs38 views
- AuditRun complete system health audit of DQIII8 — checks DB integrity, agent performance, pipeline connections, error log, and services. Produces a scored Markdown report.Votes: 0GitHub stars: 11
- Blue TeamDefensive 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.Votes: 0GitHub stars: 11
- CheckpointSave and verify session state using git commits and a checkpoints log. Use before risky multi-file changes or after completing a significant implementation block.Votes: 0GitHub stars: 11
- HandoverGenerate 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).Votes: 0GitHub stars: 11
- Instinct StatusShows learned instincts from dqiii8.db, grouped by project and confidence. Internal diagnostic tool — not for user invocation.Votes: 0GitHub stars: 11
- Intl ReportsGenera 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.Votes: 0GitHub stars: 11
- MobilizeMulti-agent coordination protocol for tasks spanning 3+ distinct domains. Decomposes goal into sub-tasks, spawns specialized agents in isolated worktrees, aggregates results.Votes: 0GitHub stars: 11
- ModeActiva un modo de trabajo para DQIII8. Opciones: analyst | coder | creative. El modo persiste hasta fin de sesion o reinicio del VPS.Votes: 0GitHub stars: 11
- Prompt OptimizeAnalyze 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.Votes: 0GitHub stars: 11
- Quality GateRun the DQIII8 quality pipeline — format (Black), imports (isort), lint (ruff), tests (pytest), security scan. Used internally by checkpoint and pre-commit flows.Votes: 0GitHub stars: 11
- Red TeamAdversarial 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.Votes: 0GitHub stars: 11
- Security CycleRun 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.Votes: 0GitHub stars: 11
- Skill CreateAnalyzes DQIII8 git history to extract patterns and generate SKILL.md files in skills-registry/custom/Votes: 0GitHub stars: 11
- SpeckitSpec-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.Votes: 0GitHub stars: 11
- SvsiPre-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".Votes: 0GitHub stars: 11
- Test TeamAgent team coordination test — research-analyst gathers Kelly Criterion info, python-specialist implements it. Validates sequential agent coordination via tasks/results/ handoff.Votes: 0GitHub stars: 11
- Transcript LearnExtract 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.Votes: 0GitHub stars: 11
- Weekly ReviewGenerate weekly dashboard update — reads sessions from last 7 days, queries metrics from dqiii8.db, regenerates 00_DASHBOARD.md, commits and pushes.Votes: 0GitHub stars: 11
- Cdp InvestigateSkill 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.Votes: 0GitHub stars: 11
- Dispatch AgentSkill 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).Votes: 0GitHub stars: 11
- Drive UploadUpload DOCX files from intl-reports to Google Drive Carpeta 3 using rclone. Zero reasoning — action only.Votes: 0GitHub stars: 11
- Panel ReviewAdversarial review of a plan file — a single Opus pass — before implementation of a ≥3-module or ambiguous-scope change.Votes: 0GitHub stars: 11
- Code ReviewReview the changes since a fixed point (commit, branch, tag, or merge-base) along two axes: Standards (does the code follow this repo's documented coding standards?) and Spec (does the code match what the originating issue/spec asked for?). Runs both reviews in parallel sub-agents and reports them side by side. Use when the user wants to review a branch, a PR, work-in-progress changes, or asks to \"review since X\".Votes: 0GitHub stars: 11
- Infra Blue TeamDefensive infrastructure audit + reversible remediation on the 2 owned Netcup VPS — diffs live state against infra_baseline.yaml, files findings in infra_findings, applies only safe non-disruptive fixes (ufw deny, cscli ban) over SSH. Never edits local files — every fix is a remote command, audited as such. NEVER auto-invoked.Votes: 0GitHub stars: 11
- Infra Red TeamAdversarial testing against the 2 owned Netcup VPS (dqiii8 + Lier infra) — port/service scan, Syncthing exposure review, CrowdSec/UFW bypass checks, optional isolated Kali container for wifi audit. Never invents targets — hard-gated by infrastructure/redteam_target_allowlist.yaml. NEVER auto-invoked.Votes: 0GitHub stars: 11
- New Plglobal ProjectCrea un proyecto nuevo en my-projects/ con documentación y estructura de carpetas en notación Obsidian, pensado para operadores sin experiencia técnica (Isabel, Mario). Úsalo cuando pidan "crear un proyecto nuevo", "empezar un caso nuevo de cliente" o similar.Votes: 0GitHub stars: 11