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

61%

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

65%

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

The content is concise and reasonably actionable with useful mapping tables and a prompt formula, but it leans on non-existent script references and lacks validation/retry guidance for its async workflow.

Suggestions

Either bundle the referenced scripts (generate-film.sh, core/platform/check-result.sh) or replace the dead references with self-contained, executable instructions.

Add an explicit poll-until-complete loop with error handling and a retry/failure path for the async video generation workflow.

Show the actual check-result.sh invocation rather than only naming it, so the polling step is copy-paste ready.

Dimension	Reasoning	Score
Conciseness	The body is lean and table/bullet-driven, assumes Claude's competence, and avoids explaining concepts Claude already knows; only minor intro repetition keeps it from feeling padded.	3 / 3
Actionability	It provides a concrete bash example, a prompt-expansion formula, and mapping tables, but the example references a non-bundled script and the polling command is named without being shown.	2 / 3
Workflow Clarity	Three sequenced steps are present, but the async polling workflow lacks validation checkpoints or an error-recovery feedback loop, which caps this dimension at 2.	2 / 3
Progressive Disclosure	Sections are well-organized inline, but referenced script paths (generate-film.sh, check-result.sh) point to no actual bundle files and nothing is split into separate reference files.	2 / 3
	Total	9 / 12 Passed

Description

57%

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 is specific and distinctive about its cinematic-video niche, but it omits explicit trigger guidance and lacks the breadth of concrete actions and natural user keywords that would raise it to the top level.

Suggestions

Add an explicit 'Use when...' clause naming natural user triggers (e.g., generating AI video, cinematic prompts, or directing shots with Veo3/Kling/Luma).

Expand the action list beyond 'Direct' and 'translates' to concrete capabilities like composing shots, choosing camera movements, and tuning model parameters.

Include common user phrasings such as 'AI video generation' or 'make a video' alongside the model names.

Dimension	Reasoning	Score
Specificity	It names the domain and concrete actions ('Direct high-fidelity cinematic video', 'translates creative intent into technical cinematographic directives') plus specific models, but offers only two actions rather than a comprehensive multi-action list.	2 / 3
Completeness	It clearly states what the skill does but lacks any 'Use when...' trigger clause, which caps completeness at 2 per the rubric guidelines.	2 / 3
Trigger Term Quality	Relevant terms like 'cinematic video', 'video models', and the model names appear, but common user phrasings such as 'AI video generation' or 'make a video' are missing.	2 / 3
Distinctiveness Conflict Risk	The AI cinematic-video-directing niche tied to specific models via muapi.ai is distinct and unlikely to trigger for the wrong skill.	3 / 3
	Total	9 / 12 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: 71242e2

Reviewed: about 21 hours 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.