mmprompt/h3-plan-gate
Z User f5575fa678 Scene composition is the gate, not word counts
The skill exists so the LLM writes/rewrites each scene one at a time
with full attention on making it a complete scene composition — not so
it can hit a word target.

Prompts: the word-budget craft bullets are replaced by an 8-element
composition checklist (subject anchor, style anchor, continuity anchor,
blocking, camera, performance, physical texture, exit state) in both the
scene-writer PROMPT B (new SCENE COMPOSITION section) and the single-pass
prompt. Chase the elements, never a number; padding is as much a failure
as a thin one-liner.

Validator: hard word bands (<10s: 150-200, >=10s: 200-300) removed from
plan and fragment checks. Replaced by a thin-scene floor (100/120 words)
that only trips lazy output, plus a new continuity-anchor check — chained
fragments must open inside the previous end_state. No target band, no
upper limit; output lines say so.

SKILL.md/README: goal, Step 2, craft rules, table rows, and example
outputs updated to match. Suite, --check, chained fragment checks all
green.
2026-10-29 19:13:27 +00:00
..
h3_agent_workflow_examples Realign: one plan JSON, written one scene at a time 2026-10-29 19:00:11 +00:00
build_plan.py Realign: one plan JSON, written one scene at a time 2026-10-29 19:00:11 +00:00
count_prompt_tokens.py Realign: one plan JSON, written one scene at a time 2026-10-29 19:00:11 +00:00
h3_plan_assembler_system_prompt.md Realign: one plan JSON, written one scene at a time 2026-10-29 19:00:11 +00:00
h3_plan_json_system_prompt.md Scene composition is the gate, not word counts 2026-10-29 19:13:27 +00:00
h3_scene_agent_system_prompt.md Scene composition is the gate, not word counts 2026-10-29 19:13:27 +00:00
SKILL.md Scene composition is the gate, not word counts 2026-10-29 19:13:27 +00:00
verify_plan_rules.py Scene composition is the gate, not word counts 2026-10-29 19:13:27 +00:00