CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

fal-ai-media

Unified media generation via fal.ai MCP — image, video, and audio. Covers text-to-image (Nano Banana), text/image-to-video (Seedance, Kling, Veo 3), text-to-speech (CSM-1B), and video-to-audio (ThinkSound). Use when the user wants to generate images, videos, or audio with AI.

Quality

84%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Passed

No findings from the security scan

SKILL.md
Quality
Evals
Security

Quality

Content

75%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 well-organized, actionable model catalog: concrete examples per modality, parameter tables, and practical tips. Weaknesses are mild — off-scope ElevenLabs/VideoDB tangents, undefined VideoDB setup, and async result handling that is listed as a tool but never explained as a workflow step.

Suggestions

Add a short 'Retrieve results' note explaining when generate returns a request_id and how to poll it with result/status, closing the main workflow gap.

Give the VideoDB snippet a one-line setup pointer (how 'coll' is obtained) or move the ElevenLabs/VideoDB sections into a reference file to keep the SKILL.md focused on fal.ai.

Trim the 'When to Activate' bullets, which restate triggers already in the description, and fold any remaining notes into the Tips section.

DimensionReasoningScore

Conciseness

Mostly dense tables, copy-ready call examples, and 'Best for:' one-liners with no explanations of known concepts; minor trimmable parts are the 'When to Activate' section restating the description's triggers and the off-scope ElevenLabs/VideoDB sections.

4 / 5

Actionability

Concrete app_ids, real parameter values, an executable ElevenLabs snippet, and an explicit upload-then-generate sequence for image editing; minor gaps are placeholders like '<uploaded_url>' and the VideoDB snippets using an undefined 'coll' with no setup guidance.

4 / 5

Workflow Clarity

Each recipe is a clear sequence, model choice is guided ('Best for', iterate on Nano Banana 2 then switch to Pro), and cost is gated via estimate_cost before expensive runs; however the async 'result'/'status' tools are listed but never woven into a generate-then-poll workflow, and there are no error-recovery checkpoints.

4 / 5

Progressive Disclosure

A single well-sectioned file (tools, image, video, audio, cost, discovery, tips) with no bundle files to reference; at ~280 lines the per-model catalog is still appropriately placed inline but is approaching the size where a references/ split would pay off, so it falls just short of a 5.

4 / 5

Total

16

/

20

Passed

Description

88%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 strong description: it names the platform, enumerates four concrete capabilities with specific model names, and includes an explicit 'Use when' clause. The main gaps are missing natural trigger synonyms and some overlap risk from broad media-generation triggers.

Suggestions

Add natural trigger synonyms users actually say — e.g. 'make a thumbnail', 'text to speech', 'voiceover', 'music', 'sound effects' — to the when-clause for broader trigger coverage.

Sharpen the when-clause to bind triggers to fal.ai (e.g. 'Use when the user wants to generate images, videos, speech, or sound effects via fal.ai models') to reduce overlap with ElevenLabs/VideoDB-style audio skills.

DimensionReasoningScore

Specificity

Lists four concrete capabilities (text-to-image, text/image-to-video, text-to-speech, video-to-audio) each with named models, covering all three media modalities — comprehensive coverage with no gaps.

5 / 5

Completeness

Explicitly answers both what ('Covers text-to-image (Nano Banana), text/image-to-video (Seedance, Kling, Veo 3), text-to-speech (CSM-1B), and video-to-audio (ThinkSound)') and when ('Use when the user wants to generate images, videos, or audio with AI') with concrete trigger phrases.

5 / 5

Trigger Term Quality

Includes natural phrases like 'generate images, videos, or audio' and 'text-to-speech', but misses common synonyms and variations users would say — 'make a thumbnail' (present in the body but not the description), 'TTS', 'voice', 'music', 'sound effects'.

4 / 5

Distinctiveness Conflict Risk

'via fal.ai MCP' plus named models carves a mostly distinct niche, but the broad when-triggers ('generate images, videos, or audio') carry minor overlap risk with closely related media-generation skills — the body itself adds ElevenLabs and VideoDB alternatives.

4 / 5

Total

18

/

20

Passed

Validation

93%

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

CriteriaDescriptionResult

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

Total

15

/

16

Passed

Repository

valeriibeck-star/claude-skills

Path

skills/fal-ai-media/SKILL.md

Revision

0bda8b8

Reviewed

Table of Contents

DiscoveryImplementationValidation

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.

Claim skill