muapi-cinema-director

Direct high-fidelity cinematic video with AI — translates creative intent into technical cinematographic directives for Veo3, Kling, and Luma video models via muapi.ai

Quality

53%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./.opencode/skills/muapi-cinema-director/SKILL.md

Quality

Content

53%Weight 40%Scale 1-5

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The content is well-structured and rich in genuinely specialized cinematography mappings, but its executable guidance is undermined by a broken bash example and references to non-existent script files, and the workflow lacks validation checkpoints.

Suggestions

Fix the bash example by adding line-continuation backslashes or writing it as a single line so it is copy-paste executable.

Provide the referenced scripts/generate-film.sh and core/platform/check-result.sh as bundle files, or note explicitly that they live outside the skill.

Add an explicit validation/feedback loop for the async step (e.g. 'poll check-result.sh; if status is failed, inspect the error and re-run with adjusted parameters').

Dimension	Reasoning	Score
Conciseness	Mostly efficient dense reference tables and lists, but it opens by restating the description ("A specialized skill for AI Agents to direct high-fidelity cinematic video") and defines basic camera terms (Dolly, Truck, Crane) Claude already knows, so it has some unnecessary explanation that could be trimmed.	3 / 5
Actionability	Provides a concrete command example and a prompt-expansion formula, but the bash snippet is not executable as written (multi-line command with no line-continuation backslashes) and the referenced scripts/ directory does not exist, so key execution details are missing.	3 / 5
Workflow Clarity	A clear 3-step sequence (define brief, invoke script, poll async result) is present, but there are no explicit validation checkpoints or error-recovery feedback loops for the async polling step.	3 / 5
Progressive Disclosure	The body is well-organized into clearly labeled sections (intent mapping, camera movements, protocol, constraints) with one-level-deep references to named scripts; however, those referenced script files are not present in any bundle directory, a minor organization gap.	4 / 5
	Total	13 / 20 Passed

Description

53%Weight 40%Scale 1-5

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

The description clearly conveys a distinctive niche and names concrete models, but it lacks an explicit use-when trigger clause and only describes a single primary action, leaving it solidly mid-tier rather than exemplary.

Suggestions

Add an explicit trigger clause, e.g. 'Use when the user wants to generate cinematic/AI video, direct a shot, or mentions Veo3, Kling, or Luma.'

List 2-3 concrete actions (e.g. 'compose shots, select camera movements, optimize model parameters') to raise specificity from one action to several.

Include natural synonyms users say ('AI video generation', 'text-to-video', 'generate a video clip') alongside the model names.

Dimension	Reasoning	Score
Specificity	Names the domain and one core action ("translates creative intent into technical cinematographic directives") plus specific models (Veo3, Kling, Luma), but does not list several distinct concrete actions, so it sits at the 1-2 actions anchor rather than the comprehensive-coverage anchor.	3 / 5
Completeness	The "what" is clearly stated (translating creative intent into cinematographic directives for named models), but there is no explicit "Use when..." clause or equivalent trigger guidance, which caps completeness at 3 per the guidelines.	3 / 5
Trigger Term Quality	Includes relevant keywords ("cinematic video", "Veo3, Kling, and Luma", "muapi.ai") but omits natural variations a user would say such as "generate video", "AI video", or "text-to-video", so coverage has gaps.	3 / 5
Distinctiveness Conflict Risk	The niche is specific (cinematographic directing for Veo3/Kling/Luma via muapi.ai) with distinct triggers and low overlap risk, though it could still marginally overlap with generic AI-video generation skills, keeping it just below a 5.	4 / 5
	Total	13 / 20 Passed

Validation

87%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 14 / 16 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning
referenced_paths_exist	Referenced path issues: 1 missing	Warning

	Total	14 / 16 Passed

Repository: SamurAIGPT/Generative-Media-Skills
Path: .opencode/skills/muapi-cinema-director/SKILL.md
Commit: 3b62f78

Reviewed: 6 days ago

Table of Contents

Discovery Implementation Validation

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.