Mark393295827

Manages the LLM's context window, covering token budgeting, prompt assembly, and truncation strategies. Use when nearing context limits or optimizing prompt costs.

Ender's Game approach to commanding Claude Code Agent Teams. Strategic multi-agent orchestration with Karpathy Agentic Engineering principles — plan, act, observe, iterate. L1-L5 commander progression.

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.

Execute a daily knowledge compound closed loop — 7 Key Results from input to feedback with scoring. Use when the user wants to do a daily review, plan their day, or run a knowledge workflow.

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

Multi-source deep research — search, synthesize, and deliver cited reports. Use when the user wants thorough research on any topic with evidence and citations.

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

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.

Ingest sources (articles, PDFs, videos, notes) into a persistent interlinked knowledge wiki. Creates source notes, entity pages, concept pages, and updates navigation. Based on the STOW (Source → Think → Organize → Write) pattern.

Health-check the knowledge wiki — find orphans, broken links, missing frontmatter, contradictions, stale content, and statistical drift. Use when the user says "lint the wiki", "health check", or periodically for maintenance.

Design runtime infrastructure around AI agents — permissions, tools, feedback loops, observability. Use when deploying agents to production or designing multi-agent systems.

Cognitive Symbiont is a livewired self-evolving system utilizing CASH and 3B creativity algorithms (Bending, Breaking, Blending). It incorporates predictive coding, collective intelligence, and time-arrow diagnostics.

Design or refactor agent skills, workflows, and operating loops for model-native Agentic Engineering. Use when making skills more autonomous, concise, verifiable, long-horizon capable, token-efficient, and lower-friction for human-LLM collaboration.

Generates, validates, and outputs new ideas based on existing knowledge, combining combinatorial creativity, cross-domain analogy, and minimum experiments. Use when the user wants fresh ideas, new product concepts, or creative solutions.

Manage a multi-layered knowledge system to ingest, organize, deduplicate, vectorize, sync, and retrieve information across various stores. Use this skill to save, organize, sync, search, or scale your knowledge base.

Extracts reusable knowledge from sessions, scanning for new concepts, entities, corrections, patterns, ideas, decisions, and gaps, then saving them to a wiki. Use at session end or by saying extract knowledge.

Evaluate startups using the 24-step disciplined entrepreneurship framework. Use when assessing a startup idea, conducting due diligence, or analyzing a business model.