Tessl • The package manager for agent skills

SkillPublic

fal-video-edit

Edit existing videos using AI — remix style, upscale, remove background, and add audio via fal.ai's hosted video models.

Quality

66%

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/fal-video-edit/SKILL.md

Quality

Content

47%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 body is a lean, well-sectioned catalogue stub that clearly defers to the upstream repo, but it provides almost no executable guidance — no real install command, no model-usage instructions, and no validation steps. It functions as an advertisement rather than an actionable skill body.

Suggestions

Replace the `open <url>` pseudo-step with a real, executable installation step (e.g. a git clone or copy command with concrete destination paths for the skills directory).

Include minimal actionable guidance for the core operations (e.g. how to invoke a fal.ai video model for upscale or background removal), or bundle the upstream references/scripts locally so the skill is self-contained.

Add a verification checkpoint after installation (e.g. confirming the skill appears in the agent's skill list) to give the sequence a concrete success condition.

Dimension	Reasoning	Score
Conciseness	The body is short and free of concept over-explanation, but it wastes tokens repeating the frontmatter verbatim: the description is duplicated in "What it does" and the Source section restates the category and upstream URL already in frontmatter — minor trimming opportunities, fitting the efficient-with-minor-gaps anchor.	4 / 5
Actionability	The only command is `open https://github.com/fal-ai-community/skills`, which is a browser-open, not an executable step; there is no install/clone command, no model invocation, and no parameters — high-level hints ("install the upstream bundle", "invoke by name") without the specific steps to execute.	2 / 5
Workflow Clarity	A rough sequence exists (inspect upstream → install bundle → invoke by name or trigger), but the steps are poorly defined: no actual installation command, "your active agent's skills directory" is unspecified, and there is no checkpoint confirming the skill is installed and invocable.	2 / 5
Progressive Disclosure	No bundle files exist, and the body itself is short with clean sections and a single clearly signaled one-level reference (the upstream repo); however, all substantive content is deferred to an external URL rather than local reference files, keeping it below the top anchor.	4 / 5
	Total	12 / 20 Passed

Description

71%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 crisp, specific description that names four concrete video-editing capabilities and the provider, with good natural trigger terms. Its main gap is the absence of any explicit "when to use" guidance, and trigger coverage misses synonyms and file extensions.

Suggestions

Append a 'Use when...' clause, e.g. 'Use when the user wants to edit an existing video: upscale, restyle, remove background, or add audio.'

Add natural trigger synonyms and file formats (.mp4, .mov, 'change video style', 'make video HD') to broaden the natural-phrases users would actually say.

State that it applies to already-existing footage (not text-to-video generation) explicitly in the when-clause to further reduce overlap with video-generation skills.

Dimension	Reasoning	Score
Specificity	The description lists four concrete actions ("remix style, upscale, remove background, and add audio") scoped to "existing videos" via "fal.ai's hosted video models" — multiple specific, concrete operations with broad coverage, matching the comprehensive anchor rather than the minor-gaps anchor.	5 / 5
Completeness	The "what" is clear and concrete, but there is no "Use when..." clause or equivalent explicit trigger guidance in the description, which caps completeness at 3 per the judging guidelines.	3 / 5
Trigger Term Quality	Natural terms like "upscale", "remix style", and "remove background" are present, but common variations users would say (e.g. "style transfer" in the description body, "clean up video") and file extensions (.mp4, .mov) are missing — good coverage with a few natural terms absent.	4 / 5
Distinctiveness Conflict Risk	Editing "existing videos" via fal.ai's models is a mostly distinct niche, but it could overlap with sibling fal.ai video-generation or generic video tooling skills — minor overlap risk rather than the minimal-conflict top anchor.	4 / 5
	Total	16 / 20 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: nexu-io/open-design
Path: skills/fal-video-edit/SKILL.md
Revision: 78d5637

Reviewed: 17 days ago

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.

fal-video-edit

Table of Contents

Is this your skill?