taste

A creative-direction (taste) layer for music videos and short-form edits in the angelcore / cloud-trance / hyperpop visual family. Distills a named-genre aesthetic vocabulary, a mood + color + light system, and a beat-synced editing grammar, then chains ECC's video skills (video-editing, fal-ai-media, remotion-video-creation, motion-*, content-engine) into one production pipeline. Use when the work is not just making a video function but making it feel intentional, when building a music video, a fancam/edit, a moodboard-driven reel, or when choosing a coherent visual direction for AI-generated b-roll.

Quality

86%

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

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 highly actionable with copy-paste-ready code, a clear sequenced pipeline, and well-structured progressive disclosure to a real reference file. The main weakness is minor verbosity in the thesis/principles prose and a lack of explicit validation feedback loops in the pipeline.

Suggestions

Add an explicit validation/feedback checkpoint to the pipeline (e.g., after CUT, 'review selects against the beat grid; if a cut drifts off-beat, re-cut before composing') to push workflow_clarity toward 5.

Trim the overlap between 'Core Thesis' and 'Key Principles' — several points (decide direction first, one accent per shot, cut on the beat) are stated twice — to tighten conciseness.

Consider moving the full genre-family table or the fal.ai prompt presets into references/ to keep SKILL.md a leaner overview, though current structure already scores well.

Dimension	Reasoning	Score
Conciseness	The body is efficient and assumes Claude's competence, with lean FFmpeg/Remotion/beat-math code and no padding about basic concepts, but the Core Thesis and Key Principles sections partially restate each other and some opinionated prose could be trimmed, fitting the 4 anchor.	4 / 5
Actionability	Fully executable, copy-paste-ready guidance throughout: concrete FFmpeg recipes, a working Remotion composition skeleton with beat() helper, fal.ai prompt presets, and beat-math constants covering the common cases, matching the 5 anchor.	5 / 5
Workflow Clarity	The 0–8 pipeline is clearly sequenced with a table mapping each step to an ECC skill, and quality gates ('throw away 80%', 'Generate 10, keep 2') act as implicit checkpoints, but explicit validate-then-fix feedback loops are absent, so it sits at 4 rather than 5.	4 / 5
Progressive Disclosure	SKILL.md is the actionable overview and clearly signals one-level-deep navigation to the real bundle file ('The companion file references/genre-taxonomy.md holds the full named-genre catalog'), with content appropriately split, matching the 5 anchor.	5 / 5
	Total	18 / 20 Passed

Description

87%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 well-scoped niche with explicit what-and-when guidance and good natural trigger terms. It is slightly held back from a perfect specificity score by the abstract verb 'distills' and a few missing synonyms.

Dimension	Reasoning	Score
Specificity	Lists several concrete actions ('Distills a named-genre aesthetic vocabulary, a mood + color + light system, and a beat-synced editing grammar, then chains ECC's video skills ... into one production pipeline'), but 'distills' is somewhat abstract compared to the fully-tangible verbs in the 5 anchor, leaving minor gaps.	4 / 5
Completeness	Explicitly answers both what ('A creative-direction (taste) layer ... chains ECC's video skills ... into one production pipeline') and when ('Use when the work is not just making a video function but making it feel intentional, when building a music video, a fancam/edit ...'), matching the 5 anchor with concrete trigger phrases.	5 / 5
Trigger Term Quality	Strong natural-term coverage ('music video', 'fancam/edit', 'moodboard-driven reel', 'AI-generated b-roll') plus genre names users would say ('angelcore', 'cloud-trance', 'hyperpop'), though a few common synonyms are missing, fitting the 4 anchor.	4 / 5
Distinctiveness Conflict Risk	Occupies a clear niche (angelcore/cloud-trance/hyperpop visual taste for music videos) with distinct triggers unlikely to fire for unrelated skills, matching the 5 anchor.	5 / 5
	Total	18 / 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: affaan-m/ECC
Path: skills/taste/SKILL.md
Commit: 07756ce

Reviewed: 2 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.