Name: muapi-social-media-video
Rating: 65.60000000000001 (1 reviews)
Author: SamurAIGPT

muapi-social-media-video

Brand-aware social media video creator. Reads brand-identity.md, ICP.md, and messaging.md to write a post/storyboard, craft an optimized Seedance 2.0 Director prompt, generate reference frames with the best available image model, and produce platform-ready video.

Quality

78%

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 ./library/social/social-media-video/SKILL.md

The canonical home for this skill is muapi-social-media-video in SamurAIGPT/Generative-Media-Skills

Quality

Content

82%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 highly actionable with executable commands, templates, and tables, and the workflow is clearly sequenced with a quality checklist, but it keeps everything inline rather than offloading reference material to separate files and lacks explicit output-validation checkpoints.

Suggestions

Add an explicit validation/feedback step before video generation, e.g. verify the reference image file exists and rendered before passing it via --file.

Move the Camera Language Reference and Platform Specs tables into reference files (e.g. references/camera-language.md, references/platform-specs.md) and link to them from the body to improve progressive disclosure.

Trim the worked example and the playful/premium tone illustration to tighten token efficiency.

Dimension	Reasoning	Score
Conciseness	The body is dense and mostly tabular (platform specs, camera intents, model tables, templates) and assumes Claude's competence without explaining concepts, but has minor trimmable padding such as the playful/premium tone example and the long worked example.	4 / 5
Actionability	Provides fully executable, copy-paste-ready commands (generate-image.sh and run-social-video.sh, the latter verified present in scripts/), a Director Brief template, mode/model selection tables, and a complete worked example covering the common cases.	5 / 5
Workflow Clarity	A clear 5-step Agent Execution Protocol is sequenced with a Prompt Quality Checklist as a checkpoint, but there is no explicit validate-output or feedback loop (e.g., confirming the reference image rendered before invoking video generation).	4 / 5
Progressive Disclosure	Well-organized with clear section headers and a single clearly-referenced bundle script (scripts/run-social-video.sh); however all ~278 lines are inline with no references/ or assets/ files, and the camera-language/platform tables could be split out for a skill of this size.	4 / 5
	Total	17 / 20 Passed

Description

75%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 is specific and distinctive, clearly stating what the skill does through a chain of concrete actions, but it lacks an explicit 'Use when...' trigger clause, which caps its completeness and leaves the most natural platform-specific trigger terms unstated.

Suggestions

Add a 'Use when...' clause naming concrete triggers, e.g. 'Use when creating social media videos, Reels, TikToks, or YouTube Shorts for a brand.'

Include the platform names users naturally say (Instagram Reels, TikTok, YouTube Shorts) to improve trigger-term coverage.

Keep the existing action chain but ensure the trigger guidance is appended so the description answers both 'what' and 'when'.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions ('Reads brand-identity.md, ICP.md, and messaging.md to write a post/storyboard, craft an optimized Seedance 2.0 Director prompt, generate reference frames... and produce platform-ready video') with comprehensive coverage, matching the score-5 anchor.	5 / 5
Completeness	The 'what' is explicit and detailed, but there is no 'Use when...' clause or equivalent trigger guidance; per the rubric guideline a missing 'when' caps completeness at 3.	3 / 5
Trigger Term Quality	Captures natural terms like 'social media video', 'brand', 'post/storyboard', and 'video', but omits the platform-specific phrases users actually say (Reel, TikTok, YouTube Short), so a few natural terms are missing rather than fully covered.	4 / 5
Distinctiveness Conflict Risk	The 'Brand-aware social media video creator' niche anchored to 'Seedance 2.0 Director prompt' and a specific brand-file workflow is a clear, distinct trigger set with minimal conflict risk.	5 / 5
	Total	17 / 20 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: SamurAIGPT/Generative-Media-Skills
Path: library/social/social-media-video/SKILL.md
Commit: 5519622

Reviewed: 5 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.