CtrlK
BlogDocsLog inGet started
Tessl Logo

create-image-fal

Generate or edit an image via any FAL image model (nano-banana edit, gpt-image, flux, ...), ROUTED THROUGH THE fal-proxy so it bills the Ads agent. image_urls must be public URLs (orchestrator hosts local product refs via MCP upload->presign). The recipe names the model + prompt. Use for keyframes, flat-cover transforms, product hero edits. (For the OpenAI gpt-image family specifically, create-image-gpt-image-fal also exists.)

63

Quality

75%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Medium

Suggest reviewing before use

Fix and improve this skill with Tessl

tessl review fix ./skills/ads/capabilities/create-image-fal/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

71%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 compact, well-structured single-purpose skill whose body is an overview pointing to two real bundled scripts. Its main weakness is redundancy (the body reprints the description verbatim) and a placeholder payload that softens actionability.

Suggestions

Drop the opening paragraph that duplicates the frontmatter description verbatim; the body can start directly at ## Run to save tokens.

Replace the '{...}' payload placeholder with a concrete example payload (or point readers to gen_image.py's docstring) so the Run command is copy-paste ready.

Add a one-line output-verification note (e.g., confirm the returned *.fal.media URL downloaded and the extension was reconciled) to close the workflow loop.

DimensionReasoningScore

Conciseness

The opening paragraph duplicates the frontmatter description verbatim, which is unnecessary token spend; the rest (## Run, ## Contract) is lean, so it is mostly efficient but could be tightened by dropping the repeated paragraph.

3 / 5

Actionability

Provides a concrete, mostly executable command ("gen_image.py --model fal-ai/nano-banana/edit --payload '{...}' --out keyframe.png") with a real model path; the '{...}' payload placeholder is the main minor gap keeping it from copy-paste-ready 5.

4 / 5

Workflow Clarity

The single action (run gen_image.py) is unambiguous and the Contract states the routing constraint, but no output-verification or failure-handling note is surfaced in the body, leaving a minor checkpoint gap.

4 / 5

Progressive Disclosure

Under 50 lines with well-organized ## Run and ## Contract sections and clearly signaled one-level-deep references to real bundle files (gen_image.py, media_proxy.py) that hold the implementation detail, matching the simple-skill exception.

5 / 5

Total

16

/

20

Passed

Description

78%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, specific description that answers both what and when and actively reduces conflict risk by naming the sibling gpt-image skill. It leans on internal jargon (proxy billing, MCP presign) that adds little trigger value for a user.

DimensionReasoningScore

Specificity

Names the domain and concrete actions ("Generate or edit an image via any FAL image model") plus specific models ("nano-banana edit, gpt-image, flux") and concrete applications ("keyframes, flat-cover transforms, product hero edits"), with only minor coverage gaps versus the comprehensive 5 anchor.

4 / 5

Completeness

Clearly answers "what" (generate/edit an image via FAL models) and provides an explicit "Use for keyframes, flat-cover transforms, product hero edits" clause, but the "when" is framed as applications rather than user-mention triggers, so it sits just below the 5 anchor.

4 / 5

Trigger Term Quality

Includes natural terms users would say ("generate", "edit", "image", "keyframes", "product hero") alongside internal jargon ("fal-proxy", "MCP upload->presign", "flat-cover"), giving good but not comprehensive coverage with a few natural synonyms missing.

4 / 5

Distinctiveness Conflict Risk

Has a clear niche (FAL image models routed through the fal-proxy) and explicitly disambiguates the sibling skill ("create-image-gpt-image-fal also exists"), giving distinct triggers and minimal conflict risk.

5 / 5

Total

17

/

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.

Validation15 / 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
gooseworks-ai/goose-skills
Reviewed

Table of Contents

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.