muapi-cinema-director
v1.0.0Direct high-fidelity cinematic video with AI — translates creative intent into technical cinematographic directives for Veo3, Kling, and Luma video models vi...
⭐ 1· 244·0 current·0 all-time
byAnil Chandra Naidu Matcha@anil-matcha
MIT-0
Download zip
LicenseMIT-0 · Free to use, modify, and redistribute. No attribution required.
Security Scan
OpenClaw
Benign
high confidencePurpose & Capability
The skill's name/description (translate creative intent into technical prompts for video models) matches the actual behavior: it expands a brief into a director-style prompt and calls a platform video-generation primitive. There are only minor documentation mismatches: SKILL.md mentions three models (Veo3, Kling, Luma) but the included script documents/accepts veo3 and kling as examples (Luma is referenced in prose but not explicitly validated in the script). This is an implementation/Docs mismatch, not a security concern.
Instruction Scope
SKILL.md instructs the agent to expand user prompts with specific director rules and to run the included generate-film.sh script. The script only constructs a prompt and calls a local platform primitive (core/media/generate-video.sh). It does not read unrelated files, access environment variables, or transmit data to unknown external endpoints within the skill files provided.
Install Mechanism
No install spec — instruction-only plus a small helper script. Nothing is downloaded or written to disk beyond the provided script. Low install risk.
Credentials
The skill declares no required environment variables, config paths, or credentials. The included script likewise doesn't request secrets. Note: the script invokes a platform primitive (core/media/generate-video.sh) which may itself use platform credentials; that is expected and outside this skill's declared scope.
Persistence & Privilege
The skill is not always-enabled and is user-invocable (defaults). It does not attempt to modify other skills or global config and contains no self-install behavior. Normal privilege profile for an agent skill.
Assessment
This skill appears coherent and low-risk: it only maps creative briefs into a technical prompt and calls a platform video-generation primitive. Before installing, verify (1) that your platform provides the referenced core/media/generate-video.sh and core/platform/check-result.sh scripts and understand what credentials those primitives use, (2) whether you need to supply or restrict which video models are allowed (SKILL.md references Luma but the script examples focus on Veo3/Kling), and (3) that you are comfortable with the agent invoking the platform primitive to generate video (the skill itself does not request secrets, but the underlying primitive may). If you want extra assurance, inspect the platform core scripts (core/media/generate-video.sh and core/platform/check-result.sh) to confirm they don't call unexpected external endpoints or require exposing credentials you don't want shared.Like a lobster shell, security has layers — review code before you run it.
latestvk970mh5j8h34sm3gz51wq8wxss82v453
License
MIT-0
Free to use, modify, and redistribute. No attribution required.