konradre/video-production-skills / skills/video-refs-continuity
video-refs-continuity
VerifiedContinuity through consistency for generated video: builds the DERIVED reference set and start image every shot needs, keeps the continuity ledger between shots, and runs the refs gate in code before any generation call. Use when a shot must match the shot before it (room, cast, seats, wardrobe, held props, door swing, a named state), when a character, product or room reference is built or cut from a keeper, when a plate or start image is generated, or when seeds keep drifting between shots. Triggers — "continuity", "refs gate", "reference set", "start image", "continuity ledger", "backfill from accepted", "the door is on the wrong wall", "not the same guy", "the same shape in all videos". Not for the cost line, the GO and the submit itself — use video-gen-cost-gate. Not for the prompt's wording — use video-prompt-dialects. Not for upscale, film look, grain or the delivery encode — use video-finish.
| File | Kind | Size |
|---|---|---|
| SKILL.md | skill md | 31.6 KB |
| references/ASSET-HYGIENE.md | markdown | 6.1 KB |
| references/CONTINUITY-AXES.md | markdown | 6.3 KB |
| references/REFERENCE-CONTRACT.md | markdown | 19.0 KB |
| references/REPAIR-LADDER.md | markdown | 6.0 KB |
| references/SCENE-PROXY.md | markdown | 24.5 KB |
| references/ZOOM-OUT-CHAIN.md | markdown | 4.1 KB |
| references/refs-required.example.json | config | 3.1 KB |
| scripts/air_pieces.pyexecutable | script | 3.9 KB |
| scripts/cast_stress.pyexecutable | script | 17.8 KB |
| scripts/comfy_preflight.py | script | 22.3 KB |
| scripts/comfy_ready.pyexecutable | script | 2.7 KB |
| scripts/comfy_up.shexecutable | script | 2.6 KB |
| scripts/knit_letters.pyexecutable | script | 7.3 KB |
| scripts/plate_pieces.pyexecutable | script | 4.9 KB |
| scripts/ref_dag.pyexecutable | script | 5.2 KB |
| scripts/refs_gate.pyexecutable | script | 41.1 KB |
| scripts/scene_blockout.py | script | 6.4 KB |
| scripts/scene_proxy.py | script | 16.6 KB |
| scripts/split_sheet.pyexecutable | script | 1.4 KB |
| scripts/sprinkle_pieces.pyexecutable | script | 2.8 KB |
references/refs-required.example.json
View on GitHub{
"_doc": "REFS GATE rules for scripts/refs_gate.py. Copy to <project>/prompts/refs-required.json. Each rule = an element (a regex over the prompt body, negated clauses removed) and the reference ROLES it needs; a role is met by any listed reference NAME that is in the call's --refs AND uploaded for the target (receipts/<NAME>-upload-id.txt for hf; refs-urls.json for kie), or inherited from the start image's own accepted gate record. Every capitalised subject in a prompt must be ruled here, declared --births (born in this gen) or --prose (a conscious prose-only decision). Add a rule the moment an element gets a locked reference. 'spots' restricts a rule to spot ids parsed from the prompt filename by spot_regex. require_ref_files and require_ref_acceptance make an unregistered or an unaccepted cited reference FAIL — a new project sets both (without them they WARN). look_plates lists the project's look plates: light or grade language in a prompt's prose then needs one of them cited (look_language overrides the default light vocabulary; --prose LOOK keeps a prose-only light on purpose). min_side is the smallest short side a reference file may have. require_text_read makes an accepted frame with no text read (refs_gate.py --accept NAME --text none | \"intended: <string>\") FAIL. cast maps each recurring member to its identity references; require_cast_lock makes a cited one FAIL until scripts/cast_stress.py has locked that member (10 of 10 stills) — a new project sets all three. Names below are examples — one SHAPE sheet and one SIZE ref per product colour, one PRODUCT sheet per SKU, one ROOM ref (the establishing frame, which embeds its cast) per set, one ref per recurring character, one LOOK plate per light context.",
"take_regex": "^S\\d\\d-[A-Z0-9]+(-v\\d+)?-s\\d+$",
"spot_regex": "(S\\d\\d)",
"require_ref_files": true,
"require_ref_acceptance": true,
"min_side": 256,
"require_text_read": true,
"require_cast_lock": true,
"cast": {
"W1": ["S01-W1-ref"],
"LEAD": ["S01-LEAD-ref"]
},
"look_plates": ["LOOK-interior-lamp", "LOOK-exterior-overcast"],
"caps_stoplist": ["BOOM", "CLANG", "WHACK", "KNOCK", "SILENCE", "POV", "OTS", "MCU", "VO", "SFX", "CTA", "SKU", "LED", "TV", "OK"],
"embeds": {
"S01-ROOM-ref": ["S01-W1-ref", "S01-W2-ref", "S01-W3-ref", "S01-LEAD-ref"]
},
"rules": [
{
"element": "product pieces",
"regex": "\\bpieces\\b|\\bburst\\b",
"roles": {
"SHAPE": ["PRODUCT-sheet-exact-colour1"],
"SIZE": ["PRODUCT-scale-ref-colour1"]
}
},
{
"element": "product (the device)",
"regex": "\\bdevice\\b|\\btube\\b",
"roles": {
"PRODUCT": ["PRODUCT-sheet-real-sku1"]
}
},
{
"element": "room (living room)",
"spots": ["S01", "S07"],
"regex": "living room|\\bcarpet\\b|\\bsofa\\b|\\bdoorway\\b",
"roles": {
"ROOM": ["S01-ROOM-ref", "S01-PLATE-A", "S01-PLATE-B"]
}
},
{
"element": "character W1",
"spots": ["S01", "S07"],
"regex": "\\bW1\\b|the woman in the red dress",
"roles": {
"W1": ["S01-W1-ref", "S01-ROOM-ref"]
}
},
{
"element": "prop (pouch)",
"regex": "\\bpouch\\b",
"roles": {
"POUCH": ["S01-POUCH-ref"]
}
}
]
}
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| reverse-engineer-anythingmorluto/reaReverse engineer native, managed, Electron/JavaScript, packaged, firmware, and browser targets with REA, and build agent environments (AgentEnv bundles) of web applications from a live instance or a capture, and of Linux desktop apps with a task from a request. Use shipped-artifact or requested runtime evidence to explain features, compare versions, decompile code, or guide a reconstruction. Skip REA for ordinary source-repository architecture analysis. | Stars: 472k | Updated | Claude CodeCodex | Unverified | Install |
| diagnosing-superpowersobra/superpowersUse when a superpowers session went wrong and your human partner wants to know why — repeated work, ignored plans, stumbles, poor results, a skill that didn't fire, "it took too long", "why is it so expensive", "what is it doing" — or wants to build a bug report for the superpowers maintainers, for the current session or a past one identified by id or path, on any harness. | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| dispatching-parallel-agentsobra/superpowersUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| executing-plansobra/superpowersUse when executing an implementation plan in the current session as the implementer yourself — your human partner chose inline execution, or no subagent tool is available | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |