fal-vision

Analyze images — segment objects, detect, run OCR, describe, and answer visual questions via fal.ai vision 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-vision/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.

The body is a lean catalogue entry that clearly points to an upstream bundle, but it offers no executable guidance for the skill's actual vision capabilities and defers every concrete detail to an external repo. Actionability is the weakest dimension.

Suggestions

Replace the `open <url>` placeholder with a concrete install command (e.g., `git clone <repo> <skills-dir>/fal-vision`) so the setup step is actionable.

Add a minimal executable example of invoking a fal.ai vision model (e.g., a one-line client call) so the skill carries real guidance rather than only an external pointer.

Drop the verbatim re-statement of the description in 'What it does' and the redundant 'Source' block (already in frontmatter) to tighten conciseness.

Dimension	Reasoning	Score
Conciseness	The body is short and avoids explaining concepts Claude already knows, but it restates the frontmatter description verbatim in 'What it does' and duplicates the upstream URL in 'Source', so it could be tightened further.	2 / 3
Actionability	The only command is `open https://github.com/...` which does not advance the vision task, and 'install the upstream bundle into your active agent's skills directory' gives no concrete install command or path — this describes rather than instructs.	1 / 3
Workflow Clarity	An install-then-invoke sequence is implied, but the install step lacks a concrete command and there are no checkpoints, so the sequence is present yet incomplete.	2 / 3
Progressive Disclosure	Sections are well-organized and the upstream pointer is clearly signaled, but all substantive content is deferred to an external URL with an extra 'inspect the upstream README for exact paths' hop rather than a one-level-deep local reference structure.	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 and distinct, with strong natural-term coverage from both the description text and frontmatter triggers. Its only gap is the missing explicit 'Use when...' guidance, which caps completeness at 2.

Suggestions

Add an explicit 'Use when...' clause to the description, e.g. 'Use when the user wants to analyze, segment, OCR, or ask questions about an image', to lift completeness to 3.

Consider adding layperson variations like 'photos' or 'pictures' alongside 'images' to broaden natural-term coverage.

Dimension	Reasoning	Score
Specificity	The description enumerates multiple concrete actions — 'segment objects, detect, run OCR, describe, and answer visual questions' — matching the score-3 anchor of listing several specific concrete actions rather than vague language.	3 / 3
Completeness	It clearly states what the skill does but provides no 'Use when...' clause or equivalent explicit trigger guidance, so per the judging guidelines completeness is capped at 2 rather than reaching 3.	2 / 3
Trigger Term Quality	Natural terms a user would say are well covered both in the description ('analyze images', 'OCR', 'visual questions', 'segment', 'detect') and the frontmatter triggers ('image analysis', 'object detection', 'ocr image', 'visual qa'), satisfying the good-coverage anchor.	3 / 3
Distinctiveness Conflict Risk	Scoping to 'via fal.ai vision models' with the brand-specific 'fal vision' trigger carves out a clear niche unlikely to conflict with generic image 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-vision/SKILL.md
Commit: f2760fd

Reviewed: about 14 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.