fal-restore

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

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/fal-restore/SKILL.md

Quality

Content

46%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 content is concise and cleanly structured, but it functions as a pointer card to an external repo rather than a self-contained skill, offering little executable guidance or workflow. It needs concrete restoration commands or local reference files to be actionable.

Suggestions

Add an executable example showing how to call a fal.ai restoration model (e.g. a Python snippet or CLI command with the model endpoint) instead of only linking to GitHub.

Provide the concrete install path/command for the upstream bundle rather than instructing the agent to 'inspect the upstream README for exact paths'.

Include a brief validation step (e.g. how to confirm the restored output meets the user's goal) given restoration is a quality-sensitive operation.

Dimension	Reasoning	Score
Conciseness	The body is short and avoids explaining concepts Claude already knows, though the 'What it does' line duplicates the frontmatter description and the Source section restates upstream/category info already in the YAML.	4 / 5
Actionability	The only concrete instruction is `open https://github.com/...` to read an external README; there is no executable code, model endpoint, or actual restoration command, leaving the agent to discover the workflow elsewhere.	2 / 5
Workflow Clarity	It gives a rough sequence (advertise in Open Design, install upstream bundle, invoke by name/trigger) but the steps are vague, the install path is unspecified, and there are no validation checkpoints.	2 / 5
Progressive Disclosure	Sections are well-organized and the skill is short, but it defers almost everything to an external GitHub repo rather than providing local one-level-deep references, so navigation points outward rather than to a bundled structure.	3 / 5
	Total	11 / 20 Passed

Description

62%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 uses natural trigger terms, but it omits an explicit 'Use when...' clause, capping its completeness. Adding a usage trigger would lift it into the top tier.

Suggestions

Append an explicit 'Use when...' clause, e.g. 'Use when restoring blurred, noisy, or damaged photos, fixing faces, or recovering old documents.'

Add common synonyms like 'sharpen' or 'upscale' to broaden natural trigger coverage.

Clarify the 'fix faces' action (e.g. 'repair distorted or low-resolution faces') to sharpen specificity.

Dimension	Reasoning	Score
Specificity	Lists several concrete restoration actions ('deblur, denoise, fix faces, and restore old documents') with the underlying mechanism (fal.ai's hosted restoration models), though each action is named without sub-step detail.	4 / 5
Completeness	It clearly states what the skill does but has no explicit 'Use when...' clause or trigger guidance, which per the judging guidelines caps completeness at 3.	3 / 5
Trigger Term Quality	Includes natural user-facing terms ('deblur', 'denoise', 'fix faces', 'restore old documents') that a user would plausibly say, though it omits common synonyms like 'sharpen' or 'upscale'.	4 / 5
Distinctiveness Conflict Risk	The image-restoration niche ('deblur, denoise, fix faces, restore old documents') is fairly distinct and unlikely to collide with unrelated skills, with only minor overlap risk against general image-generation skills.	4 / 5
	Total	15 / 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-restore/SKILL.md
Commit: 1a7a23d

Reviewed: about 4 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.