video-editing

AI-assisted video editing workflows for cutting, structuring, and augmenting real footage. Covers the full pipeline from raw capture through FFmpeg, Remotion, ElevenLabs, fal.ai, and final polish in Descript or CapCut. Use when the user wants to edit video, cut footage, create vlogs, or build video content.

Quality

75%

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 ./skills/video-editing/SKILL.md

Quality

Content

61%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.

A well-structured, largely executable pipeline skill with strong FFmpeg/Remotion coverage and verified one-level bundle references. Its weaknesses are off-topic pipeline paragraphs that pad token usage and missing validation/verification steps around batch FFmpeg operations.

Suggestions

Add validation after the batch cut loop (e.g. verify each output segment exists, is non-empty, and matches the expected count/duration before concatenation) and after silence-detection cuts, satisfying the batch-operation feedback loop the rubric requires.

Remove or relocate the DAW/MIDI/bridge-capability paragraphs in The Pipeline section; they address audio-workstation concerns not exercised anywhere else in this video-editing skill.

Move the Native Fusion Presets detail and the tool-strength comparison table into the assets/fusion READMEs or a reference file to shorten SKILL.md and deepen the progressive-disclosure structure.

Dimension	Reasoning	Score
Conciseness	The FFmpeg/Remotion sections are tight and command-first, but the Pipeline section carries off-topic DAW/MIDI/bridge-audition paragraphs whose relevance to video editing is unclear — trimming candidates that go beyond minor over-explanation.	3 / 5
Actionability	Most blocks are copy-paste ready (ffmpeg timestamp cuts, concat, loudnorm, full Remotion component), but the fal.ai generate() call and VideoDB snippets are illustrative pseudocode without imports or setup, leaving minor gaps.	4 / 5
Workflow Clarity	The six-layer pipeline is clearly sequenced with per-layer jobs, but the central batch operations (the cuts.txt while-loop and silence-detection auto-cut) have no output validation steps, which the rubric caps at 3.	3 / 5
Progressive Disclosure	Bundle references (assets/fusion/ito-production-v1/README.md, assets/fusion/ito-v28/README.md) are real files, one level deep, and clearly signaled with scope caveats; minor organization gaps remain where Fusion-preset detail and the tool-comparison table sit inline in an already long body.	4 / 5
	Total	14 / 20 Passed

Description

88%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.

A strong description: concrete capability verbs, an explicit tool pipeline, and a clear third-person 'Use when...' trigger clause. The only weakness is trigger-term breadth — a few natural synonyms and file extensions are absent.

Dimension	Reasoning	Score
Specificity	"cutting, structuring, and augmenting real footage" plus a named pipeline (FFmpeg, Remotion, ElevenLabs, fal.ai, Descript/CapCut) lists multiple concrete actions covering the full workflow comprehensively, matching the anchor-5 example.	5 / 5
Completeness	It explicitly answers what ("AI-assisted video editing workflows for cutting, structuring, and augmenting real footage...") and when ("Use when the user wants to edit video, cut footage, create vlogs, or build video content") with concrete trigger phrases.	5 / 5
Trigger Term Quality	"edit video", "cut footage", "create vlogs", and "build video content" are natural user phrases, but common variations and synonyms (e.g. trim, subtitles, short-form, .mp4) are missing.	4 / 5
Distinctiveness Conflict Risk	The editing-not-generation framing carves a clear niche, but naming ElevenLabs and fal.ai creates minor overlap risk with a media-generation skill covering those tools.	4 / 5
	Total	18 / 20 Passed

Validation

81%

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 — 13 / 16 Passed

Validation for skill structure

Criteria	Description	Result
metadata_version	'metadata.version' is missing	Warning
relative_links	Relative link issues: 2 deeper-than-1-level	Warning
referenced_paths_exist	Referenced path issues: 2 deeper-than-1-level	Warning

	Total	13 / 16 Passed

Repository: affaan-m/ECC
Path: skills/video-editing/SKILL.md
Commit: c70874f

Reviewed: 1 day 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.