jarvis-toolbelt

Core Jarvis - vault management, semantic memory, auto-extract (REQUIRED for extensions)

9 skills · 1 MCP server · hooks

Obsidian vault PKM workflows - JARVIS protocol, git audit trail, journal, exploration (requires: jarvis)

3 skills · 3 agents · 1 MCP server

Strategic analysis & briefings - orient, catchup, summarize, patterns (requires: jarvis)

4 skills

Todoist integration - task management analyst with smart routing (requires: jarvis + Todoist MCP)

2 skills · 1 agent · 1 MCP server

32 engineering skills: architecture, frontend, backend, fullstack, QA, DevOps, security, AI/ML, data engineering, Playwright (9 sub-skills), self-improving agent, Stripe integration, TDD guide, tech stack evaluator, Google Workspace CLI, a11y audit (WCAG 2.2), Azure cloud architect, GCP cloud architect, security pen testing, Snowflake development, adversarial-reviewer, ai-security, cloud-security, incident-response, red-team, threat-detection. v2.8.1 audits senior-fullstack / senior-frontend / senior-backend against karpathy-coder + Matt Pocock — each ships a 7-question forcing-question library, 4 customization profiles (JSON), deterministic decision engine, composition map into POWERFUL specialists, plus cs-fullstack-engineer / cs-frontend-engineer / cs-backend-engineer orchestrator agents (context: fork) + /cs-fullstack-review, /cs-frontend-review, /cs-backend-review, /cs-engineer-grill slash commands.

35 skills · hooks

Standalone model routing and one-off handoffs with Claudex Route, plus the full Claudex Loop planning, build and review workflow.

6 skills

Security-first workflows for coding agents that threat-model, security-review and verify code changes before they ship, across Codex, Claude Code, Cursor and Copilot.

62 skills

Pre-submission AI review and editing for CS-conference papers: direct-edit LaTeX or Markdown (Word via one-time extraction), run an adversarial multi-agent courtroom review with consensus-gated revisions, or run it unattended toward a goal.

1 skill

Full SDD loop (grill → spec → research → review → build) over one SPEC.md, caveman encoding, bug-to-spec backprop

9 skills · 7 commands

Production-grade development environment for Claude Code with 16 specialized agents, 35 slash commands, 33 skills, 22 hooks + 9 opt-in examples (21 events), 14 rules, and 4 MCP servers (playwright, context7, jina-reader, chrome-devtools pinned at 0.23.0). Includes TDD workflow, security review, code review, architecture analysis, build error resolution, Chrome DevTools Lighthouse / Core Web Vitals audits, and an adversarial verification loop (maker≠checker) with unattended API-error auto-resume, session relay, and Korean prose quality guardrails.

33 skills · 35 commands · 16 agents · 4 MCP servers