fal-generate

Generate images and videos using fal.ai AI models. Production-grade catalogue covering Flux, SDXL, ideogram, and other community-hosted endpoints.

Quality

56%

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-generate/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.

A lean, well-structured catalogue-entry body that points users upstream rather than embedding a workflow. It is concise and navigable but lacks concrete executable guidance and a clearly defined install workflow, capping actionability and workflow clarity low.

Suggestions

Replace the bare 'install the upstream bundle' instruction with a concrete, runnable command (e.g. a git clone / symlink into the skills directory) so actionability reaches 4+.

Enumerate the handoff as explicit numbered steps (inspect → install → verify installed path → invoke) with a verification checkpoint that the skill is discoverable.

Remove the verbatim restatement of the frontmatter description in 'What it does' (or replace it with a genuinely additive one-line summary) to eliminate the conciseness redundancy.

Dimension	Reasoning	Score
Conciseness	The body is lean and assumes Claude's competence (e.g. 'This catalogue entry advertises the skill in Open Design'); the only padding is the 'What it does' section restating the frontmatter description verbatim — a minor redundancy that keeps it at 4 rather than 5.	4 / 5
Actionability	The only concrete command is 'open https://github.com/fal-ai-community/skills' (just inspection), while the actual instruction 'install the upstream bundle into your active agent's skills directory' gives no executable steps; not a 3 because there is no real pseudocode or partial implementation of the generation task itself.	2 / 5
Workflow Clarity	A rough sequence is implied (inspect README → install bundle → invoke by name/trigger) but steps are poorly defined with no concrete install method and no validation; the simple-skill exception does not apply because this is a loosely-defined multi-step handoff rather than a single unambiguous action.	2 / 5
Progressive Disclosure	No bundle files exist (references/, scripts/, assets/ all absent), and the body is well under 50 lines with clean sections (What it does, Source, How to use) and a single one-level reference to the upstream repo URL; not a 5 because the reference is an external GitHub URL rather than a clearly signaled local file, and the catalogue defers rather than splits content.	4 / 5
	Total	12 / 20 Passed

Description

66%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 specific, third-person description that names the platform and concrete models, giving a clear niche with low conflict risk. Its main weakness is the missing explicit 'Use when...' trigger clause, which caps completeness at 3.

Suggestions

Add an explicit 'Use when...' clause to the description (e.g. 'Use when generating images or videos with fal.ai models such as Flux, SDXL, or ideogram') to lift completeness above 3.

Include natural synonym/extension terms like 'text-to-image', 'diffusion', or '.png'/'mp4' outputs to broaden trigger-term coverage toward 5.

Enumerate a second concrete action (e.g. 'tune parameters, upscale, or batch generate') to move specificity from several actions toward comprehensive coverage.

Dimension	Reasoning	Score
Specificity	Quotes 'Generate images and videos using fal.ai AI models' plus named models 'Flux, SDXL, ideogram, and other community-hosted endpoints' list several specific outputs and concrete endpoints with only minor coverage gaps; not a 5 because the only action verb is 'Generate' and there is no enumeration of distinct capabilities.	4 / 5
Completeness	Has a clear 'what' ('Generate images and videos using fal.ai AI models') but no 'Use when...' or equivalent explicit 'when' clause, so per the rubric guideline completeness is capped at 3; not a 4 because the trigger guidance exists only in the separate frontmatter triggers list, not in the description.	3 / 5
Trigger Term Quality	Natural user terms appear directly: 'fal.ai', 'images and videos', 'Flux', 'SDXL', 'ideogram' — good keyword coverage with model-level specificity; not a 5 because common variations/synonyms and file extensions (e.g. '.png', 'text-to-image', 'diffusion') are absent.	4 / 5
Distinctiveness Conflict Risk	The platform ('fal.ai') and named models ('Flux, SDXL, ideogram') carve a clear niche distinct from generic image skills; not a 5 because 'other community-hosted endpoints' leaves overlap risk with broader generation skills, so minor overlap remains.	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-generate/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.