zk-context-vault

Use when creating, editing, or debugging Factorio mods — writing prototypes in data.lua, handling events in control.lua, defining mod settings, structuring info.json, writing locale files, or diagnosing desync and prototype errors.

Use when creating, editing, or debugging Factorio mods — writing prototypes in data.lua, handling events in control.lua, defining mod settings, structuring info.json, writing locale files, or diagnosing desync and prototype errors.

Comprehensive Nix package and configuration management following Determinate Systems best practices.

Manage Nix packages, flakes, and configurations using Determinate Nix installer patterns. Use when installing/updating packages, creating flakes, troubleshooting Nix issues, or optimizing Nix workflows. Keywords: nix, flake, package, nixpkgs, nix profile, flake.nix, flake.lock, determinate, nix-installer

Use when working with Obsidian vaults — creating or editing .md notes, wikilinks, callouts, frontmatter, embeds, tags, or Obsidian-specific syntax; or when interacting with a vault via the obsidian CLI to read, create, search, manage notes/tasks/properties, or develop and debug plugins and themes.

Use when working with Obsidian Canvas files as cognitive modeling tools — compiling spatial/visual structure into deterministic JSON, designing canvas layouts with semantic color and edge conventions, exporting structured data from canvas, or importing JSON into canvas form.

Use when working with Obsidian vaults — creating or editing .md notes, wikilinks, callouts, frontmatter, embeds, tags, or Obsidian-specific syntax; or when interacting with a vault via the obsidian CLI to read, create, search, manage notes/tasks/properties, or develop and debug plugins and themes.

Use when working with Obsidian Canvas files as cognitive modeling tools — compiling spatial/visual structure into deterministic JSON, designing canvas layouts with semantic color and edge conventions, exporting structured data from canvas, or importing JSON into canvas form.

Apply Catppuccin color palettes to configs, stylesheets, and terminal themes. This skill should be used when creating or modifying CSS themes, terminal color schemes, shell prompts (Starship, etc.), or any configuration that requires consistent Catppuccin colors. Covers all four official flavors (Latte, Frappe, Macchiato, Mocha) plus ZK's custom variants (rose, sage, grape, honey, blueberry).

Use when running inference probes on the mesh, routing tasks to pi or hermes harnesses, or configuring model loading across LM Studio (adeck:1234), vLLM (zrrh:8000), or llama-server (zrrh direct). Covers gateway config, ctx ceiling procedure, tool-call probing, KV quant config, dense vs MoE tradeoffs, and harness architecture.

Guide for creating high-quality MCP (Model Context Protocol) servers that enable LLMs to interact with external services through well-designed tools. Use when building MCP servers to integrate external APIs or services, whether in Python (FastMCP) or Node/TypeScript (MCP SDK).

This skill should be used when the user asks to "implement agent memory", "persist state across sessions", "build knowledge graph", "track entities", or mentions memory architecture, temporal knowledge graphs, vector stores, entity memory, or cross-session persistence.

Advanced OpenRGB integration for ambient computing — SDK server automation, remote display surfaces, presence indicators, notification channels, and event-driven effects using openrgb-python. Use when building RGB as an ambient interface layer, presence/notification systems, multi-host lighting coordination, or system-event-driven effects.

Use when the user asks for astrology readings, celestial timing, planetary hours, tattwa cycles, moon sign, biorhythms, or symbolic timing weather. Requires sideriod installed locally — if not present, run the setup guide.

Use when the user asks for astrology readings, celestial timing, planetary hours, tattwa cycles, moon sign, biorhythms, or symbolic timing weather. Requires sideriod installed locally — if not present, run the setup guide.

Use when running inference probes on the mesh, routing tasks to pi or hermes harnesses, or configuring model loading across LM Studio (adeck:1234), vLLM (zrrh:8000), or llama-server (zrrh direct). Covers gateway config, ctx ceiling procedure, tool-call probing, KV quant config, dense vs MoE tradeoffs, and harness architecture.

Advanced OpenRGB integration for ambient computing — SDK server automation, remote display surfaces, presence indicators, notification channels, and event-driven effects using openrgb-python. Use when building RGB as an ambient interface layer, presence/notification systems, multi-host lighting coordination, or system-event-driven effects.

Universal agent configuration patterns for any AI coding environment. Use when configuring steering, specs, or context assembly for Kiro, Claude Code, Codex, Charm, or other agents.

Master LLM-as-a-Judge evaluation techniques including direct scoring, pairwise comparison, rubric generation, and bias mitigation. Use when building evaluation systems, comparing model outputs, or establishing quality standards for AI-generated content.

Design and evaluate context compression strategies for long-running agent sessions. Use when agents exhaust memory, need to summarize conversation history, or when optimizing tokens-per-task rather than tokens-per-request.

Understand the components, mechanics, and constraints of context in agent systems. Use when designing agent architectures, debugging context-related failures, or optimizing context usage.

Apply optimization techniques to extend effective context capacity. Use when context limits constrain agent performance, when optimizing for cost or latency, or when implementing long-running agent systems.

Build evaluation frameworks for agent systems. Use when testing agent performance, validating context engineering choices, or measuring improvements over time.

Design and implement memory architectures for agent systems. Use when building agents that need to persist state across sessions, maintain entity consistency, or reason over structured knowledge.

Design multi-agent architectures for complex tasks. Use when single-agent context limits are exceeded, when tasks decompose naturally into subtasks, or when specializing agents improves quality.

Design and build LLM-powered projects from ideation through deployment. Use when starting new agent projects, choosing between LLM and traditional approaches, or structuring batch processing pipelines.

Design tools that agents can use effectively, including when to reduce tool complexity. Use when creating, optimizing, or reducing agent tool sets.

Apply Catppuccin color palettes to configs, stylesheets, and terminal themes. This skill should be used when creating or modifying CSS themes, terminal color schemes, shell prompts (Starship, etc.), or any configuration that requires consistent Catppuccin colors. Covers all four official flavors (Latte, Frappe, Macchiato, Mocha) plus ZK's custom variants (rose, sage, grape, honey, blueberry).

Recognize, diagnose, and mitigate patterns of context degradation in agent systems. Use when context grows large, agent performance degrades unexpectedly, or debugging agent failures.

Apply covenant principles as design constraints across all core systems. Use when building agents, prompts, recipes, artifacts, or multi-agent architectures.

Transform content through eight cognitive lenses for different kinds of understanding. Use when the same concept needs exploration through story, debate, simulation, uncertainty, fiction, embodiment, ritual, or reflection.

Guide for creating high-quality MCP (Model Context Protocol) servers that enable LLMs to interact with external services through well-designed tools. Use when building MCP servers to integrate external APIs or services, whether in Python (FastMCP) or Node/TypeScript (MCP SDK).

This skill should be used when the user asks to "implement agent memory", "persist state across sessions", "build knowledge graph", "track entities", or mentions memory architecture, temporal knowledge graphs, vector stores, entity memory, or cross-session persistence.

Patterns for coordinating multiple AI agents. Use when single-agent context limits are exceeded, tasks decompose naturally, or specialized agents improve quality.

Recipe-based context assembly and deployment using slice architecture. Use when building compilation pipelines, extracting documentation slices, or deploying context to multiple targets.