ffmpeg

Guide for using FFmpeg - a comprehensive multimedia framework for video/audio encoding, conversion, streaming, and filtering. Use when processing media files, converting formats, extracting audio, creating streams, applying filters, or optimizing video/audio quality.

Quality

78%

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 ./claude/skills/ffmpeg/SKILL.md

Quality

Content

65%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.

Highly actionable command reference with clear section structure, but it over-explains codec/container basics Claude already knows, inlines 600+ lines of reference material that belongs in separate files, and lacks validation feedback loops for its batch operations.

Suggestions

Move the codec/container/parameter reference tables into separate files under references/ (e.g. CODECS.md, PARAMS.md) and link to them one level deep, keeping SKILL.md as a lean overview with the most common recipes.

Trim concept explanations Claude already knows (e.g. H.265 '25-50% better compression', MP4 'Universal compatibility') to keep only the ffmpeg-specific guidance.

Add an explicit validate→fix→retry feedback loop to the batch-processing section (e.g. verify a converted sample before running the full loop) so destructive/batch workflows clear the workflow-clarity cap.

Dimension	Reasoning	Score
Conciseness	Mostly executable commands with little fluff, but the codec/container sections restate concepts Claude already knows (H.264/H.265 compression ratios, MP4/MKV properties) and the 636-line body carries inline reference material that could be tightened; not severe enough for anchor 2's 'noticeably verbose' but above a lean 4.	3 / 5
Actionability	Dozens of copy-paste-ready ffmpeg/ffprobe commands cover format conversion, CRF/two-pass encoding, filters, streaming, hardware acceleration, and batch processing — fully executable across common cases per anchor 5.	5 / 5
Workflow Clarity	A closing checklist and 'test short clips first' best practice provide some sequence, but the batch-processing section shows loops with no validate-then-fix feedback loop; per the batch/destructive cap, workflow clarity cannot exceed 3.	3 / 5
Progressive Disclosure	Good header hierarchy gives structure, but with no bundle files (references/scripts/assets absent) the entire codec, container, and parameter reference is inlined in SKILL.md rather than split into one-level-deep referenced files — content that should be separate is inline, matching anchor 3.	3 / 5
	Total	14 / 20 Passed

Description

92%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, third-person description that explicitly pairs capabilities with concrete 'Use when' triggers and covers a broad action surface. The only gap is missing format synonyms/extensions that would push trigger term quality to the top anchor.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'encoding, conversion, streaming, and filtering' plus 'processing media files, converting formats, extracting audio, creating streams, applying filters, or optimizing video/audio quality' — giving comprehensive coverage rather than the 1-2 actions at anchor 3.	5 / 5
Completeness	Explicitly answers both what ('comprehensive multimedia framework for video/audio encoding, conversion, streaming, and filtering') and when ('Use when processing media files, converting formats, extracting audio...') with concrete trigger phrases, matching anchor 5.	5 / 5
Trigger Term Quality	Strong natural terms ('converting formats', 'extracting audio', 'creating streams', 'applying filters') that users would say, but lacks synonyms and file extensions (e.g. .mp4, .mkv) required for the comprehensive anchor 5.	4 / 5
Distinctiveness Conflict Risk	FFmpeg occupies a clear media-processing niche with distinct triggers; the multimedia framing and specific actions make overlap with other skills minimal, fitting anchor 5.	5 / 5
	Total	19 / 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
skill_md_line_count	SKILL.md is long (644 lines); consider splitting into references/ and linking	Warning
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	14 / 16 Passed

Repository: einverne/dotfiles
Path: claude/skills/ffmpeg/SKILL.md
Commit: 1446b2f

Reviewed: 12 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.