muapi-youtube-shorts

Auto-generate viral 9:16 YouTube Shorts (or TikTok / Reels clips) from a long-form video. Thin platform-aware wrapper around the AI Clipping skill — picks sensible defaults for short-form social platforms (9:16, 30–60s sweet spot) and delegates the actual highlight extraction + crop to muapi.ai's `/ai-clipping` endpoint.

Quality

76%

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-youtube-shorts/SKILL.md

Quality

Content

86%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 body is lean, highly actionable, and clearly sequenced, but it references a script that is not part of the skill bundle, weakening progressive disclosure. Adding an explicit validation feedback loop for batch/destructive runs would strengthen workflow clarity.

Suggestions

Ship the referenced run-youtube-shorts.sh script in a scripts/ bundle directory (or remove the path reference) so the cited executable actually exists.

Add an explicit validate-then-fix feedback loop for batch/destructive operations (e.g., verify clip URLs resolve before reporting done, retry on failure) to lift workflow clarity above 4.

Move the bulk platform-defaults and server-side details into a references/ file, keeping SKILL.md as a tight overview with one-level-deep links, to improve progressive disclosure now that the skill exceeds 50 lines.

Dimension	Reasoning	Score
Conciseness	Lean and well-organized with no padding about concepts Claude already knows; every section earns its place (server-side pipeline, platform defaults table, invocation patterns).	5 / 5
Actionability	Provides copy-paste ready executable bash commands across single, preset, batch, and async invocation patterns, plus a concrete JSON output schema.	5 / 5
Workflow Clarity	Clear sequenced protocol (Collect Inputs -> Verify Prerequisites -> Run Pipeline) with Done Criteria acting as validation, but batch/destructive flows lack an explicit validate-then-fix feedback loop.	4 / 5
Progressive Disclosure	Well-sectioned structure, but the body references a script path (library/social/youtube-shorts/scripts/run-youtube-shorts.sh) that is not present in the bundle, and no references/scripts/assets directories exist to verify the split is real.	3 / 5
	Total	17 / 20 Passed

Description

66%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 trigger-rich with strong platform keywords, but it omits an explicit 'Use when...' clause, which limits its completeness score. It is largely distinct despite being a wrapper over the AI Clipping primitive.

Suggestions

Add an explicit 'Use when...' trigger clause (e.g., 'Use when the user wants YouTube Shorts, TikTok, or Reels clips from a long video') to lift completeness above 3.

Include a few more natural synonyms/file-type cues a user might say (e.g., 'vertical clips', 'reels', 'short-form highlights') to round out trigger coverage.

Sharpen the distinction from AI Clipping by stating what only this preset adds (platform defaults), so it is less likely to trigger for raw clipping requests.

Dimension	Reasoning	Score
Specificity	Names the domain and several concrete actions ('Auto-generate viral 9:16 YouTube Shorts', 'picks sensible defaults', 'delegates the actual highlight extraction + crop'), with only minor coverage gaps.	4 / 5
Completeness	Clearly states the 'what' (generate vertical short clips from a long video) but lacks an explicit 'Use when...' trigger clause, capping completeness at 3 per the rubric guideline.	3 / 5
Trigger Term Quality	Strong natural platform terms users would say ('YouTube Shorts', 'TikTok / Reels', '9:16', 'viral', 'short-form social'), though a few common synonyms/variations are absent.	4 / 5
Distinctiveness Conflict Risk	Has a clear niche (short-form social video clipping) and is mostly distinct, though being a 'wrapper around the AI Clipping skill' introduces minor overlap risk with that parent skill.	4 / 5
	Total	15 / 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
relative_links	Relative link issues: 2 suspicious	Warning

	Total	14 / 16 Passed

Repository: SamurAIGPT/Generative-Media-Skills
Path: .opencode/skills/muapi-youtube-shorts/SKILL.md
Commit: 74df8cb

Reviewed: 9 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.