media-proxy

Shared helper that routes ALL paid media generation (FAL image/video, ElevenLabs music) through the GooseWorks proxies so every call bills the Ads agent — never a provider SDK's default host. Host-swaps the FAL queue URLs, loads the agent token from ~/.gooseworks/credentials.json, and returns the result CDN URL. Every video-ad media capability imports this; templates never call a provider directly.

Quality

76%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Medium

Suggest reviewing before use

Fix and improve this skill with Tessl

tessl review fix ./skills/ads/capabilities/media-proxy/SKILL.md

Quality

Content

85%

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 strong, action-oriented overview with executable code, real bundle-file references, and a clearly sequenced crash-resume workflow. The only weakness is mild repetition of the double-bill invariant, which slightly undercuts token efficiency.

Dimension	Reasoning	Score
Conciseness	Mostly efficient and dense with actionable specifics, but the double-bill warning is restated across the header tagline, the body explanation, and the resume invariant, which could be tightened.	2 / 3
Actionability	Fully executable, copy-paste-ready examples — real imports, concrete calls with arguments (`fal_generate('fal-ai/nano-banana/edit', {...})`, `eleven_music(prompt, 10500, 'music.mp3', ...)`), and runnable CLI commands.	3 / 3
Workflow Clarity	The crash-resume recovery workflow is explicitly sequenced (`resume.py --list` → `--request-id <id> --out final.mp4`) with a clear error-recovery feedback loop (re-attach instead of re-firing), and the single generation action is unambiguous.	3 / 3
Progressive Disclosure	Well-organized into clear sections (Crash-resume, Use it, Contracts, Related) with one-level-deep references to real bundle files (`scripts/resume.py`, `scripts/media_proxy.py`), confirmed present in the bundle.	3 / 3
	Total	11 / 12 Passed

Description

67%

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 concrete and tightly scoped to a clear niche, but its trigger guidance is implied rather than explicit and the natural keywords are buried under product-specific jargon. Adding an explicit 'Use when...' clause with plainer trigger terms would lift completeness and trigger-term quality.

Suggestions

Add an explicit 'Use when...' trigger clause (e.g. when generating paid FAL images/videos or ElevenLabs music for video ads) so 'when to use it' is stated, not implied.

Surface the natural user-facing terms ('image', 'video', 'music generation') earlier and reduce internal jargon ('GooseWorks proxies', 'Ads agent', 'provider SDK's default host') so the description reads as a trigger, not an architecture note.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'routes ALL paid media generation', 'Host-swaps the FAL queue URLs', 'loads the agent token from ~/.gooseworks/credentials.json', 'returns the result CDN URL' — matching the multiple-specific-actions anchor.	3 / 3
Completeness	The 'what' is clearly answered, but the only 'when' is the architectural note 'Every video-ad media capability imports this' — there is no explicit 'Use when...' trigger clause, which per the guidelines caps completeness at 2.	2 / 3
Trigger Term Quality	Relevant domain terms appear ('FAL image/video', 'ElevenLabs music', 'paid media') but they sit under heavy jargon ('GooseWorks proxies', 'provider SDK's default host', 'Ads agent'), and common natural phrasings are not surfaced.	2 / 3
Distinctiveness Conflict Risk	A clear niche (paid media billing for the Ads agent via GooseWorks proxies) with distinct, domain-specific triggers, making it unlikely to fire for an unrelated skill.	3 / 3
	Total	10 / 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: gooseworks-ai/goose-skills
Path: skills/ads/capabilities/media-proxy/SKILL.md
Commit: 8866b2a

Reviewed: 1 day 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.