beat-sync-reel

Generates Instagram Reels where product image cuts are synced to audio beats. Accepts audio as a local file, URL, or search query. Uses librosa for beat detection, FFmpeg Ken Burns for scene animation, and Pillow for text overlays. No AI video generation — fully free, fast, and scalable.

Quality

65%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./skills/design/packs/video-production/beat-sync-reel/SKILL.md

Quality

Content

71%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 highly actionable with executable code throughout and a clear 7-step pipeline, but it lacks explicit validation checkpoints for a batch media operation and inlines reference-style material rather than splitting it into separate files.

Suggestions

Add validation checkpoints between steps, e.g. ffprobe the resolved audio duration before beat detection, verify scraped image files are non-empty, and check scene durations for micro-cuts before concatenation.

Extract the zoompan filter catalog and the style-preset font table into a reference file (e.g. references/effects.md) referenced one level deep, keeping SKILL.md as a lean overview.

Replace the '.../' placeholder in the concat.txt example with an explicit note on how to generate the full file list (e.g. a shell loop), so the example is directly executable.

Dimension	Reasoning	Score
Conciseness	The body is largely lean with executable ffmpeg/python snippets and tables rather than concept explanations, and it does not over-explain libraries Claude already knows; only minor padding (e.g. the 'Typical results by tempo' table) could be trimmed.	4 / 5
Actionability	Nearly every step ships copy-paste-ready bash and python commands (yt-dlp, librosa beat_track, ffmpeg zoompan filters, concat, audio mix), with concrete parameters covering the common cases.	5 / 5
Workflow Clarity	The 7-step pipeline is clearly sequenced, but this is a batch media operation with no explicit validation checkpoints (e.g. verify ffprobe duration, confirm scraped images exist, check scene durations before concat), so workflow clarity is capped at 3 per the rubric.	3 / 5
Progressive Disclosure	The content is well-sectioned into a single SKILL.md with no bundle files present, but material that could live in separate references (full zoompan filter set, style preset table, scraping methods) is inlined with no one-level-deep references to split it out.	3 / 5
	Total	15 / 20 Passed

Description

60%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 names concrete tools and actions, but it omits any explicit 'Use when...' trigger guidance, which limits completeness. It carves out a clear, low-conflict niche among video-generation skills.

Suggestions

Add an explicit trigger clause, e.g. 'Use when the user wants an Instagram Reel where image cuts land on beats, or mentions beat-synced/music-synced product videos.'

Broaden trigger terms with synonyms users naturally say, such as 'music video', 'trending audio', or 'beat-cut reel'.

Mention the image-scraping capability in the description so the 'what' covers the full pipeline, not just the sync step.

Dimension	Reasoning	Score
Specificity	Lists several concrete actions ('detects beats', 'FFmpeg Ken Burns for scene animation', 'Pillow for text overlays') and names the libraries used, though it omits the scraping/concatenation steps covered in the body, leaving minor gaps.	4 / 5
Completeness	The 'what' is clearly stated (generates beat-synced Reels with named tools), but there is no 'Use when...' clause or equivalent explicit trigger guidance, capping completeness at 3 per the rubric.	3 / 5
Trigger Term Quality	Includes relevant terms like 'Instagram Reels', 'audio beats', and 'product image cuts', but lacks common synonyms or variations a user might naturally say (e.g. 'music video', 'beat-cut reel', 'trending audio') that would broaden triggering.	3 / 5
Distinctiveness Conflict Risk	The niche is narrow (beat-synced product Reels with no AI video generation), which clearly distinguishes it from a generic video skill; only minor overlap risk with related reel-generation skills remains.	4 / 5
	Total	14 / 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
allowed_tools_field	'allowed-tools' contains unusual tool name(s)	Warning
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	14 / 16 Passed

Repository: gooseworks-ai/goose-skills
Path: skills/design/packs/video-production/beat-sync-reel/SKILL.md
Commit: 2523432

Reviewed: 7 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.