fal-realtime

Real-time and streaming AI image generation via fal.ai. Suited for moodboard exploration, draft variations, and rapid creative iteration.

Quality

50%

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-realtime/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 clean, well-sectioned catalogue entry that efficiently points to an upstream repo, but it offers little executable guidance and its install/invoke workflow is vague with no validation steps.

Suggestions

Replace the browser-opening 'open <url>' with an actionable install step (e.g. a git clone or skill-install command with concrete paths) so Claude can execute rather than hand off to an external README.

Number the install → invoke sequence explicitly and add a verification checkpoint (e.g. confirm the skill appears in the agent's skills directory before invoking).

Drop the re-stated description in 'What it does' and the meta explanation of catalogue entries to tighten conciseness toward a lean overview.

Dimension	Reasoning	Score
Conciseness	The body is lean with no concept over-explanation ('Real-time and streaming AI image generation via fal.ai…' plus short Source/How-to-use sections), but the meta sentence 'This catalogue entry advertises the skill in Open Design so the agent discovers it during planning' and the re-stated description in 'What it does' are minor trims, fitting the efficient-with-minor-over-explanation score-4 anchor rather than the every-token-earns-its-place score 5.	4 / 5
Actionability	The only concrete command is 'open https://github.com/fal-ai-community/skills' (which merely opens a browser), while 'install the upstream bundle into your active agent's skills directory' and 'ask the agent to invoke this skill by name' are high-level hints with no executable steps, matching the minimal-concrete-guidance score-2 anchor and falling short of the concrete-but-incomplete score 3.	2 / 5
Workflow Clarity	A rough sequence exists (advertise → install upstream bundle → invoke by name/triggers) but it is prose rather than enumerated steps, the install step has no command and defers to 'Inspect the upstream README for exact paths', and no validation checkpoints are present, matching the rough-sequence-with-many-gaps score-2 anchor; it does not qualify for the simple-skill exception because the content itself frames a multi-step install process.	2 / 5
Progressive Disclosure	The body is under 50 lines with clear sections (What it does, Source, How to use) and a single clearly-signaled one-level reference (the upstream GitHub URL), matching the good-structure score-4 anchor; it stops short of score 5 only because the 'How to use' section mixes meta-explanation with the reference rather than cleanly splitting overview from detail.	4 / 5
	Total	12 / 20 Passed

Description

53%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 clearly states what the skill does and names a recognizable niche, but it lacks an explicit 'Use when…' trigger clause and its capability list leans on use-case language rather than distinct concrete actions.

Suggestions

Add an explicit 'Use when…' clause naming concrete triggers (e.g. 'Use when the user wants live/streaming image generation on fal.ai, moodboards, or rapid draft variations').

Reframe the capability list as distinct concrete actions (e.g. 'generate images in real time, stream iterative variations, explore moodboards') rather than application framings.

Include natural synonyms users actually say (e.g. 'fal.ai', 'live image generation', 'streaming previews') to broaden trigger coverage.

Dimension	Reasoning	Score
Specificity	Quotes 'Real-time and streaming AI image generation via fal.ai' and 'moodboard exploration, draft variations, and rapid creative iteration' name the domain plus a couple of concrete capabilities, but they read as use-case framings rather than a comprehensive list of distinct technical actions, matching the score-3 anchor and falling short of the multiple-specific-actions coverage of score 4.	3 / 5
Completeness	The 'what' is clearly stated ('Real-time and streaming AI image generation via fal.ai') but the 'when' is only weakly implied by 'Suited for moodboard exploration, draft variations, and rapid creative iteration' with no explicit 'Use when…' clause, so per the judging guideline completeness is capped at 3.	3 / 5
Trigger Term Quality	Phrases 'real-time', 'streaming', 'image generation', 'moodboard', and 'variations' are relevant natural keywords, but common synonyms and concrete signal terms (e.g. 'fal.ai', 'live preview', file/extension cues) are missing, fitting the score-3 anchor of some relevant keywords without comprehensive variations.	3 / 5
Distinctiveness Conflict Risk	The 'fal.ai' provider and 'real-time and streaming' framing carve a mostly distinct niche with only minor overlap risk against general image-generation skills, matching the score-4 anchor better than the broad score-3 anchor.	4 / 5
	Total	13 / 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-realtime/SKILL.md
Commit: 1a7a23d

Reviewed: about 5 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.