254 tagged knowledge graph, measured the same way as everything else here.
Browse within: agent-memory 48citations 40gemini 25knowledge-base 24local-first 17fastapi 15arelle 14aws 14embeddings 14markdown 14obsidian 14postgresql 14xbrl 14agent-orchestration 13
Command Claude Code
Use Potpie context before feature work. Load potpie-project-preferences first, and load potpie-infra-architecture when the change touches services, deployment, adapters, or runtime behavior.
Command Claude Code
Record durable Potpie learnings after useful work.
Command
Manage Hyper-Extract configuration for LLM and embedder settings.
Command
Extract knowledge from documents and save to a knowledge abstract.
Command
Chat with your knowledge abstract using natural language.
Command Claude Code
Build the LLM Wiki knowledge graph.
Command Claude Code
Ingest a source document into the LLM Wiki.
Command Claude Code
Health-check the LLM Wiki for issues.
Command
List entity briefs and workspace playbooks, or view a specific brief.
Command
List agent skills, view a skill, compile, or sync to local folder.
Command Claude Code
Use when designing, auditing, polishing, improving, or codifying frontend UI — websites, dashboards, landing pages, components, design systems.
Command Claude Code
User-invoked learning toolkit — guided reading, investigation, pattern extraction, or second opinions. Manual /maestro-learn only; NEVER auto-invoke for code exploration or analysis — route those intents to the analyze step via /maestro-next.
Command Claude Code
Unified entry for all development intents — classify intent, assess complexity, route to the correct execution channel: /maestro-companion (lightweight), standard single run, or /maestro and /maestro-ralph (multi-step manual/orchestrated). Pure router, never runs execution loops itself.
Command
RUN { git ls-files; git ls-files --others --exclude-standard; } 2>/dev/null | sort -u | xargs wc -l 2>/dev/null | sort -rn | head -150 READ README.md.
Command
You are saving what you learned this session into the megamemory knowledge graph. This is YOUR memory — record anything valuable for future sessions: what you understood about the project, what you built, decisions that were made, patterns you noticed, or intent the user shared.
Command
Shortcut to the canonical Memtrace impact analysis skill.
Command
Shortcut to the canonical Memtrace codebase exploration skill.
Command
Shortcut to the canonical Memtrace preflight skill.
Command
Run a task as a bounded, gate-verified loop backed by SuperLocalMemory — iterate until an independent gate passes, never on the agent's own claim.
Command
Check if LeanKG MCP server is connected and initialized.
Command Claude Code
Advance the current Writ workflow phase with an explicit tool-confirmed advance. NOT a replacement for pattern-match approval detection; this command spends the token that detection mints (see Authorization below).
Command Claude Code
Review AKB production-governance docs and hooks.
Command
Setup wizard for lockedin. Walks the user through: (1) wiring the HUD into Claude Code's statusLine, (2) default Q&A interview language, (3) vault path. Every choice is reversible. Safe to re-run; idempotent. Use when the user says any of: "/lockedin:setup", "setup lockedin", "lockedin 설정", "lockedin 설정해줘", "configure…
Command
Lite ingest — fetch a paper and write a short 4-section triage summary (Key Takeaways, Background, Main Idea & Summary, Critique). No figures, fast.