fal-restore

Restore and fix image quality — deblur, denoise, fix faces, and restore old documents using fal.ai's hosted restoration models.

Quality

58%

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-restore/SKILL.md

Quality

Content

35%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

This is a thin catalogue stub that advertises the skill and redirects to an upstream GitHub bundle rather than providing usable restoration guidance. It is reasonably lean but lacks executable instructions, a real workflow, and any local bundle structure.

Suggestions

Provide concrete, executable guidance — actual fal.ai model IDs/endpoints and a runnable command or code snippet for at least one restoration task — instead of 'inspect the upstream README'.

Add a real multi-step workflow with validation checkpoints (e.g., verify input image exists, run model, confirm output) rather than 'open URL then ask the agent'.

Either ship local reference files (references/scripts/assets) the body can point to one level deep, or remove the misleading 'How to use' framing so it is clearly a discovery/catalogue entry rather than a working skill.

Dimension	Reasoning	Score
Conciseness	The body is short and free of padded concept explanation, but the 'What it does' section repeats the frontmatter description verbatim and the bash block's only executable line is a comment + 'open <url>', keeping it from fully lean.	2 / 3
Actionability	Guidance is abstract — 'Inspect the upstream README for exact paths' and 'open https://...' — with no concrete executable code or commands Claude can run to actually restore an image; it describes rather than instructs.	1 / 3
Workflow Clarity	A loose two-step flow ('open the upstream README, then ask the agent to invoke this skill') is present, but there is no real sequence, no validation, and no checkpoints for what should be a multi-step restoration operation.	2 / 3
Progressive Disclosure	The body is sectioned and brief, but there are no local reference files (references/, scripts/, assets/ are absent) — it points off-skill to an external GitHub repo rather than splitting its own content into one-level-deep references.	2 / 3
	Total	7 / 12 Passed

Description

82%

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, third-person, and uses natural trigger terms with a clear niche. Its main gap is the absence of an explicit 'Use when...' clause, which caps completeness at 2.

Suggestions

Add an explicit 'Use when...' clause (e.g., 'Use when the user wants to deblur, denoise, fix faces in, or restore old/damaged images') to lift completeness to 3.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'deblur, denoise, fix faces, and restore old documents' — matching the anchor for listing several specific concrete actions, not vague language.	3 / 3
Completeness	Clearly answers 'what' the skill does but lacks any explicit 'Use when...' clause or equivalent when-to-use guidance, so per the guidelines completeness is capped at 2 rather than 3.	2 / 3
Trigger Term Quality	Natural user-facing terms ('deblur', 'denoise', 'fix faces', 'restore') are exactly what a user would say when they need this skill, with good coverage of common phrasings.	3 / 3
Distinctiveness Conflict Risk	The fal.ai image-restoration niche with distinct restoration triggers (deblur/denoise/fix faces) is unlikely to collide with other skills.	3 / 3
	Total	11 / 12 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-restore/SKILL.md
Commit: f2760fd

Reviewed: about 15 hours 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.