stitch-videos-ffmpeg

stitch video segments with ffmpeg concat, xfade, overlay, audio mux, and export settings.

Quality

54%

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/ads/packs/video-ad-formats/stitch-videos-ffmpeg/SKILL.md

Quality

Content

50%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 SKILL.md is concise and well-sectioned but almost entirely generic: it describes a templated workflow without pointing to the concrete, executable ffmpeg scripts that actually live in ./scripts/. This leaves it non-actionable and without validation checkpoints for a destructive batch media operation.

Suggestions

Replace the generic 'Run the ... script described by this skill' step with the actual commands, e.g. 'bash scripts/composite_final.sh edit_plan.json vo.mp3 subtitles.ass music.wav out.mp4 [duration]' and link normalize_clip.sh for per-segment prep.

Add an inline validation checkpoint between passes (e.g. probe nosubs.mp4 duration before burning subtitles) and a feedback loop on ffmpeg/libass failure, since this is a destructive batch media operation.

Add a '## Scripts' section that one-level-deep references each bundle file (scripts/composite.py, scripts/composite_final.py, scripts/normalize_clip.sh) with a one-line purpose so the bundle is discoverable from SKILL.md.

Document the edit_plan.json shape (duration, aspect, cuts[], audio, subtitles, music) inline or via a reference, since both composite scripts depend on it.

Dimension	Reasoning	Score
Conciseness	The body is short and avoids explaining ffmpeg concepts Claude already knows; it could be marginally tighter (the generic Workflow/Output/Quality Checks boilerplate is somewhat padded) but is largely efficient.	4 / 5
Actionability	Despite real, executable bundle scripts existing in ./scripts/ (composite.py, composite_final.py, normalize_clip.sh), the body never names or invokes them — it gives only high-level hints like 'Run the provider, script, or planning workflow described by this skill' with no concrete command, path, or edit_plan schema reference.	2 / 5
Workflow Clarity	A five-step sequence is listed, but for a batch/destructive media operation the validation is only a generic post-hoc Quality Checks list; there are no inline validate-then-proceed checkpoints or feedback loops, capping clarity at 3 per the destructive/batch rule.	3 / 5
Progressive Disclosure	The body has clear section headers but never signals the existing bundle scripts (composite.py, composite_final.sh, normalize_clip.sh, voiceless/composite.py) as references, so the split between SKILL.md and the scripts folder is not surfaced for navigation.	3 / 5
	Total	12 / 20 Passed

Description

58%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 is specific and distinct, naming concrete ffmpeg operations, but it omits any 'when to use' trigger guidance and relies on technical jargon over natural user phrasing. Completeness is capped at 3 per the missing-trigger-clause rule.

Suggestions

Add a 'Use when...' clause naming natural triggers, e.g. 'Use when stitching or joining video segments, combining clips with transitions, or muxing audio onto a video.'

Include user-facing synonyms and file extensions alongside the technical terms (e.g. 'stitch clips', 'combine videos', '.mp4 segments').

Lead with the user intent ('Combine video segments into one export') before the ffmpeg mechanism list.

Dimension	Reasoning	Score
Specificity	Names several concrete ffmpeg actions ('concat, xfade, overlay, audio mux, and export settings'), giving clear coverage of what the skill does, though the actions are listed as a terse chain rather than fully elaborated.	4 / 5
Completeness	It states a clear 'what' (stitch segments with specific ffmpeg operations) but has no 'Use when...' clause or equivalent explicit trigger guidance, which the rubric caps at 3.	3 / 5
Trigger Term Quality	'ffmpeg', 'concat', 'xfade', and 'audio mux' are domain-relevant but lean technical; it lacks the natural phrases and synonyms (e.g. 'stitch clips', 'join videos', 'combine segments') a user would actually say.	3 / 5
Distinctiveness Conflict Risk	The ffmpeg concat/xfade/overlay framing carves a reasonably distinct niche that is unlikely to trigger for unrelated skills, with only minor overlap risk against general video-editing skills.	4 / 5
	Total	14 / 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: gooseworks-ai/goose-skills
Path: skills/ads/packs/video-ad-formats/stitch-videos-ffmpeg/SKILL.md
Commit: 2523432

Reviewed: 7 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.