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

81%

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

76%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 highly actionable, well-structured skill body with strong executable examples across the pipeline. The main weakness is missing validation checkpoints for batch/destructive cut operations, plus some editorializing prose.

Suggestions

Add validation/verification steps after batch cuts and concatenation (e.g., check output duration, probe with ffprobe, confirm segment count matches the edit decision list) to enable error-recovery feedback loops.

Trim the 'Core Thesis' and 'Key Principles' sections to the essential, non-obvious guidance to improve token efficiency.

For the fal.ai generated-visuals block, replace the pseudocode generate() call with a concrete executable command or explicitly justify the pseudocode form.

Dimension	Reasoning	Score
Conciseness	Mostly efficient with abundant actionable code, tables, and lists, but 'Core Thesis' and 'Key Principles' sections editorialize concepts Claude already grasps and could be trimmed; not quite the lean 5.	4 / 5
Actionability	Provides fully executable, copy-paste-ready FFmpeg, Remotion TSX, and Python examples that cover the common editing cases (cut, concat, normalize, reframe, voiceover).	5 / 5
Workflow Clarity	The 6-layer pipeline is clearly sequenced, but batch cuts and destructive trim operations lack validation/verification checkpoints, which the rubric caps at 3 for batch/destructive workflows.	3 / 5
Progressive Disclosure	Single file is well-sectioned with clear navigation and one-level pointers to external docs and related skills; no bundle files exist, and content is reasonably organized with only minor gaps.	4 / 5
	Total	16 / 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.

A strong description that clearly communicates purpose, scope, and activation triggers with concrete tool names and natural user phrases. Minor improvements possible by adding file-extension triggers and a few more concrete action verbs.

Suggestions

Add file-extension triggers (e.g., '.mp4', 'video files') to broaden natural-term coverage.

Expand the action list beyond 'cutting, structuring, augmenting' with a few more concrete verbs (e.g., 'concatenate', 'reframe', 'subtitle') to reach comprehensive specificity.

Dimension	Reasoning	Score
Specificity	Names the domain and several concrete actions ('cutting, structuring, and augmenting real footage') plus a specific tool pipeline (FFmpeg, Remotion, ElevenLabs, fal.ai, Descript/CapCut), with only minor coverage gaps; not quite the comprehensive multi-action list of a 5.	4 / 5
Completeness	Explicitly states both what it does (cut/structure/augment real footage through a named pipeline) and when to use it ('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	Includes natural phrases users say ('edit video', 'cut footage', 'create vlogs', 'build video content') with good coverage, but misses common synonyms and file extensions like .mp4 that would push it to 5.	4 / 5
Distinctiveness Conflict Risk	Carves a clear niche (AI-assisted editing of real footage, explicitly not generation) with distinct triggers and named tools, minimizing overlap with related generation skills.	5 / 5
	Total	18 / 20 Passed

Validation

100%

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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: affaan-m/ECC
Path: .agents/skills/video-editing/SKILL.md
Commit: d8409a4

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.