third-brain-v5-skills

Command V6 multi-agent work with bounded roles, ownership, worktree isolation, IPC, integration gates, cleanup, attention budgets, and verification loops. Use when the user needs Claude Code Agent Teams, parallel agents, delegation strategy, Ender-style commander training, von Neumann-style command architecture, Palantir-style ontology command boards, FDE field discovery, EDD integration gates, dynamic workflow tradeoffs, or multi-agent orchestration grounded in Obsidian wiki operating rules.

Multi-source deep research — search, synthesize, and deliver cited reports. Use when the user wants thorough research on any topic with evidence, citations, AI-era scientific-method boundaries, AutoResearch feasibility checks, source/claim ledgers, uncertainty handling, and STOW wiki handoff.

Design V6 runtime infrastructure around AI agents — permissions, tools, MCP/Skills/Hooks, feedback loops, observability, scheduled routines, von Neumann-style runtime architecture, and governance. Use when deploying agents to production, designing multi-agent systems, building agent harnesses, or turning Obsidian wiki rules into bounded runtime controls.

Turn a repeatable task into a bounded, evidence-driven agent loop. Use when Codex needs to decide whether a task merits a Goal, Loop, Automation, or AutoResearch pattern; define a loop contract; check trigger/state/tools/codebase readiness; choose single-agent versus maker-checker versus manager-workers topology; prevent runaway iteration; or repair a loop that stalls, self-grades, exceeds review budget, or writes without verified evidence.

Design or refactor agent skills, workflows, operating loops, and V6 knowledge-OS upgrades for model-native Agentic Engineering. Use when making skills more autonomous, concise, verifiable, long-horizon capable, token-efficient, lower-friction for human-LLM collaboration, or ready to promote Obsidian wiki learning into reusable agent behavior.

Execute a V6 daily knowledge compound closed loop — 7 Key Results from input to feedback with scoring, evidence, wiki write-back, and optional scheduled Obsidian daily-loop note. Use when the user wants to do a daily review, plan their day, run a knowledge workflow, or complete the generated daily knowledge-management loop.

Manage a multi-layered V6 knowledge operating system — organize, deduplicate, retrieve, lint, queue, sync, and operate wiki files, vector DB, memory, daily loops, Agent/Wiki flywheel reports, and external stores. Use when the user wants to save, organize, search, scale, audit, or turn Obsidian wiki knowledge into supervised skill/SOP/schema improvement candidates.

Ingest articles, PDFs, videos, transcripts, and notes into a persistent interlinked knowledge wiki and V6 knowledge operating system. Use when the user wants source notes, entity pages, concept pages, navigation updates, STOW processing, Obsidian provenance, clipping lifecycle handling, or supervised promotion of source-derived insights into skills, SOPs, schemas, daily loops, or governance queues.

Health-check the V6 knowledge wiki — find orphans, broken links, missing frontmatter, contradictions, stale content, statistical drift, source/provenance debt, daily-loop health, and rule-promotion readiness. Use when the user says "lint the wiki", "health check", "check Obsidian system", "verify the knowledge loop", or periodically for maintenance.

Design an AI Six Sigma Black Belt operating model for property service, maintenance dispatch, environmental testing, quote generation, CRM follow-up, and workflow quality dashboards. Use when the user needs a Property Agent OS, AI + Ontology + DMAIC management system, CTQ metrics, agent-team roles, work-order states, or MVP roadmap for operations quality.

Improve a personal or team operating system with self-evolving loops, CASH allocation, 3B creativity, predictive coding, and diagnostics. Use when the user wants to redesign a work method, learning loop, or cognitive operating system.

Manage the LLM's context window — token budgeting, prompt assembly, truncation strategies. Use when approaching context limits or optimizing prompt costs.

Evaluate startup health using entrepreneurship, VC, and execution frameworks. Use when assessing a startup idea, company, pitch, due diligence target, fundraising readiness, or business model health.

Iron rule — no completion claims without fresh verification evidence. Use whenever about to claim work is done, fixed, working, or passing. Run verification commands and show output before making any success statement.

Design a behavior change system — decompose a goal into minimum habits, define triggers, build SOPs, and set up review cycles. Use when the user wants to build a habit, change behavior, or achieve a personal goal.

Deep learning compile framework — transforms raw information into actionable judgment. Use when the user wants to deeply understand a topic, not just capture it.

Generate, validate, and output new ideas based on existing knowledge. Combines combinatorial creativity, cross-domain analogy, and minimum experiments. Use when the user wants fresh ideas, new product concepts, or creative solutions.

Operate execution flow — triage tasks, manage priorities, keep progress structured. Use when the user needs backlog control, task planning, or workflow coordination across projects.

Extract reusable knowledge from a work session and save concepts, entities, corrections, patterns, ideas, decisions, and gaps to the wiki. Use when ending a session or when the user says to extract knowledge.