AB chain-referenced-shortform-video
Use when generating AI films, short dramas, cinematic sequences, or storyboard-driven video scenes that need strong cross-shot continuity and real film-language control. Covers asset-driven preproduction, shot lists, storyboards, blocking, lensing, camera movement, five-dimension prompt control, subtractive prompting, staged keyframe gates, bridge-frame selection, shot cards, continuity ledgers, and chain-referenced video generation. Trigger for requests about AI movie generation, cinematic prompt engineering, short drama workflows, continuity pipelines, previsualization, scene packs, shot templates, bridge frames, or swapping scripts without rewriting the workflow.
As a process B 70/100 · Nearly there — weak spots: result and completion, inputs and preconditions, running it twice
How to improve
- Your own cases (evals/evals.json, 4–6 real requests with expected answers): the full check would then run those instead of a model-drafted suite.
- A spec.yaml with trigger phrases and assertions — a behaviour contract for CI; `skilltest init` writes a template.
Guard findings · 1
✓ No critical or high findings
Medium and low: 1
-
low Risky intent
intent-offensive-securityreferences/film-language.md:89Offensive-security / dual-use content (legitimate for authorised testing; review intended use)- `16:9`: favors geography, ensemble spacing, lateral movement
Files scanned: 5. 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 70/100
- 0Result and completion. Does not say what the result is
- 0Inputs and preconditions. Does not say what the process needs to start
- 0Progress reporting. Says nothing while it works
- 30Running it twice. 3 mutating operations with no state check
- 100Tools and files. No external tools needed
- 100Steps. 191 steps
- 100When it triggers. States when to use and when not to
- 100Failures and branches. 9 branches, has a failure section
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 2311 tokens
- low 16 top-level sections: this looks like several domains in one skill
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
- +4Description does not say when NOT to use the skill (false activations)
- +3Output format is not stated: the model decides each time
- +4No input/output examples
- -4Absolute local paths (C:\Users, /home/…): not portable
- +1No license
- +2Single-language instructions
- +3Description length 674: enough signal without eating the budget
- +4Structure: 22 headings
- +3Step-by-step instructions: 191 items
- +4Reference files are cited in the instructions (3 of 3)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 80.