CtrlK
BlogDocsLog inGet started
Tessl Logo

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.

70

Quality

86%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Passed

No known issues

SKILL.md
Quality
Evals
Security

Quality

Content

72%

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

A highly actionable body with executable code, concrete presets, and well-structured progressive disclosure, weakened only by some removable philosophical framing and the absence of explicit validation checkpoints in the otherwise clear pipeline.

Suggestions

Trim the motivational framing — cut the 'Most AI video advice stops at how to render frames' intro and the Core Thesis justifications; the Key Principles section already captures the actionable rules.

Add explicit validation checkpoints to the pipeline: after CUT, verify each hard cut lands on a beat frame via beat(n) and re-snap if it doesn't; after GENERATE, confirm 2–3 selects per preset before advancing to COMPOSE.

Add a brief recovery note for failed generations or off-beat cuts so the workflow is an explicit validate→fix→retry loop rather than a purely forward sequence.

DimensionReasoningScore

Conciseness

The bulk is lean (executable code, hex palette, beat-math formulas, prompt presets), but removable motivational framing remains — 'Most AI video advice stops at how to render frames', 'Taste is a point of view, not a menu', and the Core Thesis justifications — so it is mostly efficient but could be tightened.

2 / 3

Actionability

Fully executable guidance throughout: copy-paste FFmpeg recipes, a complete beat-synced Remotion composition skeleton, computed beat-math constants, and per-mood fal.ai prompt presets — well above the pseudocode/incomplete anchor.

3 / 3

Workflow Clarity

The 0–8 pipeline (Taste → Structure → Generate → Cut → Compose → Motion → Audio → Polish → Distribute) is clearly sequenced and mapped to skills, but explicit validation checkpoints and error-recovery feedback loops are missing for the batch 'generate 6–10, keep 2–3' and beat-cut operations.

2 / 3

Progressive Disclosure

The 70-entry genre catalog is appropriately split into the one-level-deep references/genre-taxonomy.md (verified present), clearly signaled twice as the companion file, while the actionable mood/grammar/pipeline layer is kept inline as the overview.

3 / 3

Total

10

/

12

Passed

Description

100%

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

A strong description that names concrete actions, lists natural trigger terms, explicitly covers both what and when, and carves out a distinct niche via a specific aesthetic family and named downstream skills. Voice is third person throughout, with no over-claims.

DimensionReasoningScore

Specificity

Lists multiple 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 (video-editing, fal-ai-media, remotion-video-creation, motion-*, content-engine) into one production pipeline' — naming the specific skills involved.

3 / 3

Completeness

Explicitly answers both what (distill vocabulary/mood/grammar and chain skills into a pipeline) and when via the 'Use when the work is not just making a video function but making it feel intentional, when building a music video, a fancam/edit...' clause.

3 / 3

Trigger Term Quality

Includes natural terms a user would say — 'music video', 'fancam/edit', 'moodboard-driven reel', 'AI-generated b-roll', 'feel intentional' — alongside the genre-family keywords, giving good coverage of likely phrasings.

3 / 3

Distinctiveness Conflict Risk

Occupies a clear niche — a creative-direction 'taste' layer above the named mechanical skills, scoped to the angelcore/cloud-trance/hyperpop family — making it unlikely to trigger for the wrong skill.

3 / 3

Total

12

/

12

Passed

Validation

93%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

Total

15

/

16

Passed

Repository
affaan-m/ECC
Reviewed

Table of Contents

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.