video-clipper

Repurposes long-form video (podcasts, interviews, talks) into short-form vertical clips for Instagram Reels, TikTok, and YouTube Shorts. Handles transcription, moment selection, clip extraction, speaker-tracked reframing (16:9 to 9:16), and animated captions.

Quality

74%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./skills/design/packs/video-production/video-clipper/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.

A strongly actionable, well-sequenced pipeline document with real commands, API payloads, and cost transparency. Its main gaps are the absence of error-recovery loops for batch processing against paid APIs (capping workflow clarity) and a monolithic single-file layout where reference material is inlined rather than split out.

Suggestions

Add feedback loops for API failures: specify what to do when a Klap task or Captions.ai video returns FAILED or polling exceeds a timeout (retry, skip the clip, or surface the error to the user), and verify each final clip with ffprobe against the output specs before declaring it ready to post.

Move the caption template table, platform caption formats, and detailed Klap/Captions.ai API walkthroughs into a references/ file (e.g. references/apis.md), keeping SKILL.md as a lean overview with clearly signaled links.

Trim duplication: the Workflow Summary repeats the Pipeline section and the default template ID and install instructions each appear multiple times — consolidate to one authoritative location.

Dimension	Reasoning	Score
Conciseness	The body is dense with actionable material (commands, API calls, cost tables) and assumes Claude's competence throughout, with only minor redundancy — the Workflow Summary restates the Pipeline, the default template ID appears three times, and install instructions are repeated between Requirements and Known Limitations.	4 / 5
Actionability	Nearly every step ships concrete, executable code or commands (ffprobe/yt-dlp/ffmpeg commands, full Klap and Captions.ai request payloads with endpoints and auth headers). The polling snippets are illustrative fragments rather than copy-paste-ready loops, keeping it just below fully executable.	4 / 5
Workflow Clarity	The 8-step sequence is clear with an explicit user-approval gate ('Do NOT proceed to Step 4 until user approves') and dependency verification, but this is a batch operation over paid APIs with no error-recovery feedback loops — FAILED statuses, polling timeouts, and invalid outputs are mentioned or implied without any fix-and-retry guidance, capping workflow clarity at 3 per the rubric.	3 / 5
Progressive Disclosure	No bundle files exist (no references/, scripts/, or assets/), so everything is inlined in a ~370-line SKILL.md. Section structure is good, but content that belongs in separate reference files — the 8-row caption template table, platform caption formats, and full Klap/Captions.ai API walkthroughs — is all inline.	3 / 5
	Total	14 / 20 Passed

Description

75%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 highly specific, well-scoped description that names concrete actions and platform targets. Its one material weakness is the absence of an explicit 'when to use' clause, which both caps completeness and leaves trigger conditions implicit.

Suggestions

Add a 'Use when...' clause, e.g. 'Use when the user wants to turn a podcast, interview, or long video into clips for Reels, TikTok, or Shorts.'

Include a few more natural user phrasings as triggers, such as 'make clips from a video' or 'cut a YouTube video into shorts'.

Dimension	Reasoning	Score
Specificity	The description enumerates five concrete pipeline actions — 'transcription, moment selection, clip extraction, speaker-tracked reframing (16:9 to 9:16), and animated captions' — comprehensively covering the skill's capabilities with no generic filler.	5 / 5
Completeness	The 'what' is explicit and detailed, but there is no 'Use when...' clause or equivalent trigger guidance, which caps completeness at 3 per the rubric guidelines.	3 / 5
Trigger Term Quality	Natural trigger terms are strong — 'podcasts, interviews, talks', 'Instagram Reels, TikTok, YouTube Shorts', 'short-form vertical clips' — but a few common user phrasings like 'YouTube video', 'viral clips', or 'make clips from a video' are absent.	4 / 5
Distinctiveness Conflict Risk	It occupies a clear niche (long-form video → platform-specific vertical clips) with distinct trigger vocabulary; minimal risk of firing for unrelated video or editing skills.	5 / 5
	Total	17 / 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
allowed_tools_field	'allowed-tools' contains unusual tool name(s)	Warning
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	14 / 16 Passed

Repository: gooseworks-ai/goose-skills
Path: skills/design/packs/video-production/video-clipper/SKILL.md
Commit: cc3e518

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.