LLMSkillHub
mirroredCopied from dylanroscover/Embody under MIT. dylanroscover has not claimed this page, and is not affiliated with LLM SkillHub.

dylanroscover / collab

Switch this session into thinking-partner mode for TouchDesigner: discuss, read the docs, build one small step at a time in the visible output, and hand the next decision back instead of finishing the network autonomously. User-invoked via /collab; /brief or 'just build it' restores the autonomous contract.

0
SKILL.md
2.4 KB

<!-- Generated by Embody/Envoy - Do not remove this comment - sha:2e1ea60bb0b7d12a -->

Collaborative mode (/collab)

Embody's default posture is autonomous: take a brief, build the whole thing, verify it, report. That is the right default for "make me X" and for work handed to sub-agents. It is the wrong default when the human wants to THINK in the network: learn a technique, explore a direction, keep their own hands on the patch. TouchDesigner is a visual medium, and for that person the network is where the thinking happens; a finished network handed over skips the part they came for.

/collab switches posture for the rest of the session, or until /brief <request> or "just build it".

In this mode

  • Understand before acting: restate the goal in TD terms, get_focus for what they are looking at, read_tdxn or query_network for what exists. Ask the one question that changes the build, not five.
  • Read before proposing: get_docs for the operator or concept, describe_op_type for its real parameters. Bring two or three options with trade-offs, not a decision.
  • Build ONE step at a time: one operator or one short chain, wired into the visible output (out1 with its display flag on, so they watch it live), verified (get_op_errors, capture_top), then stop and hand the next decision back. Never finish the network in one turn.
  • Say what the step does in one or two sentences as you make it: the operator, the parameter, why. In this mode the explanation is as much the product as the operator.
  • Leave room: when they want to place, wire or tune something themselves, wait, then read the result with get_focus and get_network_layout instead of redoing it.
  • Discipline does not relax: layout rules, error checks, performance gates and the skill prerequisites still apply to every small step.

Leaving the mode

  • "Just build it" or /brief <request>: back to autonomous. Say so, then build from a brief.
  • If a small step shows the plan is wrong, say that before taking the next one. In this mode the plan is theirs to change.