AC luma
The Luma Dream Machine craft skill — generate cinematic AI video shots (Ray3: text-to-video, image-to-video, keyframes, character reference, Modify V2V, HDR) with draft-first economics and the right rights. Use when someone wants to generate video with Luma/Dream Machine/Ray3, animate a still into video, keep a character consistent across shots, restyle real footage, control credit burn, pick a Luma model or plan, or build a multi-shot AI brand film. Uses the DREAM framework. Reads ai-video + brand-profile + short-form-video-script first. The agent writes shot briefs and can drive the API where connected; the HUMAN judges every clip; WoopSocial publishes. Generations are shots not films (no native audio); Draft Mode first, HDR only for finals; verify tiers in-app. Never use unpermitted likeness, generate fake-event footage, or state credit rates as fact. Distinct from ai-video, veo-3/kling/runway, flux (the stills this animates), heygen/synthesia, and capcut.
The Luma Dream Machine craft skill — generate cinematic AI video shots (Ray3: text-to-video, image-to-video, keyframes, character reference, Modify V2V, HDR)…
As a process C 58/100 · Has gaps — weak spots: result and completion, inputs and preconditions, running it twice
How to improve
- A spec.yaml with trigger phrases and assertions — a behaviour contract for CI; `skilltest init` writes a template.
Guard findings · 0
✓ No critical or high findings
Files scanned: 0. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
✓ No remarks against the Agent Skills spec
Process rating: all ten parameters 58/100
- 0Inputs and preconditions. Does not say what the process needs to start
- 0Progress reporting. Says nothing while it works
- 30Running it twice. 11 mutating operations with no state check
- 40Result and completion. Does not say what the result is
- 50When it triggers. No condition that starts the skill
- 50Failures and branches. 0 branches, has a failure section
- 60Tools and files. Uses tools (python) that frontmatter does not declare
- 100Steps. 9 steps
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 1842 tokens
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
- low No test case covers injection arriving through data
Everything here is measured from the skill text rather than judged by a model, so the numbers are checkable. A parameter weighs more when it is a more common reason for the process to stall.
Quality signals
- +5Description has no quoted example phrases that should trigger the skill
- +3Description length 973: 120–800 characters recommended
- +3Output format is not stated: the model decides each time
- +4No input/output examples
- +1No license
- +2Single-language instructions
- +4Description says when NOT to use the skill
- +4Structure: 9 headings
- +3Step-by-step instructions: 9 items
- +4Reference files are cited in the instructions (4 of 4)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 85.