Use when validating a cross-machine HUD flow where Butler deploys/runs the full Windows app over SSH+SCP (tailnet default host), then publishes configurable test messages to HUD zones via MCP `publish_to_zone`.
Langue du texte source : anglais
Menu
SkillsMP a collecté 12 skills depuis Tzeusy/tze-hud. Ouvrez un skill pour examiner sa source et ses détails.
Affichage de 12 skills collectés sur 12.
Use when validating a cross-machine HUD flow where Butler deploys/runs the full Windows app over SSH+SCP (tailnet default host), then publishes configurable test messages to HUD zones via MCP `publish_to_zone`.
Langue du texte source : anglais
Use when an already-running LLM session should project itself onto the HUD, attach to a text-stream portal, publish live output, consume HUD input, or detach. Trigger phrases include project this session to the HUD, attach this agent to HUD, and check HUD…
Langue du texte source : anglais
CRITICAL — This skill provides the foundational doctrine for tze_hud, an agent-native presence engine. Every agent working in this repository MUST consult relevant soul doctrine before making architectural decisions, writing code, designing APIs, creating…
Langue du texte source : anglais
Use when publishing content to a user's HUD display, showing notifications or status on screen, sending text/color/alerts to tze_hud display zones, or giving an LLM visual presence on a user's GUI via MCP zone publishing.
Langue du texte source : anglais
Use when running deep performance and throughput investigations for HUD publishing paths (widgets/zones/tiles), including MCP HTTP benchmarks and gRPC bidi stream benchmarks. The canonical gRPC widget publish-load benchmark is…
Langue du texte source : anglais
Use when you need to deploy a freshly-built tze_hud.exe to the Windows host and launch the TRANSPARENT overlay HUD in one deterministic command — kill the stale instance, scp + checksum-verify the exe, launch it as a scheduled task (exe-direct, so overlay…
Langue du texte source : anglais
Use when an already-running Codex, Claude, opencode, or other LLM session should project itself onto the HUD, show its output or status on screen, attach to a text-stream portal, publish live transcript, poll HUD-originated operator input, acknowledge input,…
Langue du texte source : anglais
Load the project's engineering quality bar before writing, reviewing, or merging code. The about/craft-and-care/ directory defines testing standards, performance budgets, code quality conventions, review expectations, observability requirements, and…
Langue du texte source : anglais
Archive a completed change in the experimental workflow. Use when the user wants to finalize and archive a change after implementation is complete.
Langue du texte source : anglais
Load the project's topology maps to understand where components live, how they connect, and what boundaries exist. The about/lay-and-land/ directory contains component inventories, data flow diagrams, dependency maps, deployment topology, and operational…
Langue du texte source : anglais
Load tze_hud RFC design contracts to contextualize implementation work. The about/legends-and-lore/ directory contains 13 RFCs that define the wire-level contracts, data models, state machines, protobuf schemas, and quantitative budgets for the tze_hud…
Langue du texte source : anglais
Ground all tze_hud implementation work in the v1 MVP capability specifications (openspec/). The 13 capability specs are the single source of truth for feature planning and development. Use this skill: (1) before implementing any feature — to identify and load…
Langue du texte source : anglais