Everyday actions are where the LLM compresses hardest. Both prompts get a worked not-X-but-Y catalog (unbuttoning a shirt, changing a diaper, turning on a lamp, opening a door, buckling a strap, handing over an object) under the rule that an action named without its steps is a report, not a render; self-checks and SKILL.md carry the same catalog. |
||
|---|---|---|
| .. | ||
| h3_agent_workflow_examples | ||
| build_plan.py | ||
| count_prompt_tokens.py | ||
| h3_plan_assembler_system_prompt.md | ||
| h3_plan_json_system_prompt.md | ||
| h3_scene_agent_system_prompt.md | ||
| SKILL.md | ||
| verify_plan_rules.py | ||