The standing creative feedback loop for every pipeline (format-* skills, cartoon-h3, ugc-omni, vo-broll, dawn-statics, Dawn natives): PLAN the next concepts as combos from what is winning (stakes x emotion x payoff x root cause x mechanism x authority/POV x angle x device), TAG each pack/job at creation with combo_* keys, LAUNCH under that ad-name prefix, READ Meta weekly (read-only), RECODE only new concepts against the fixed codebook, UPDATE the map, recipes and the diff (incl. song vs static frequency/decay).

Lane: strategy (feeds every format-* pack) · not built yet: 0 (see below) · source: /Users/ayden/.openclaw/workspace/skills/workflow-combo-loop

workflow-combo-loop — sources and receipts

Source	What we kept
Fish 10-05 / 10-06	"map stakes / emotions / payoffs / root cause / mechanism and authority/pov and angles with each other for combos … plan like that in the pipelines, not just UGC but all of our creative pipelines, and also have feedback loops"
`output/dawn-combo-map-2026-10-05/MAP.md`	recipes A (song: accused mom → vindicated) and B (static: her exhaustion → his independence); the low-frequency theory; build order
10-05 scripts (`pull.py`, `songs.py`, `weekly.py`, `group.py`, `aggregate.py`)	promoted into `scripts/combo_loop/` (copied, parameterised by brand, throttled to ≤1 GET/s, token redacted in errors); originals untouched
`output/dawn-combo-map-2026-10-05/codebook.md`	copied verbatim to `scripts/combo_loop/codebook_dawn.md`; the coder gets it verbatim
Hub atlas (`project_angle_atlas.md`)	precedent: label at planning time by ad-name prefix so the read never guesses; sure/unsure discipline
`output/creative-strategy-cooper-2026-10-05/dawn-stakes.md`	stake bank (real line + raised) that plan.py swaps in

Receipts: first refresh 2026-10-06 → output/combo-loop/dawn/2026-10-06/MAP.md (DIFF vs the rebuilt 10-05 baseline output/combo-loop/dawn/2026-10-05/).