CtrlK
BlogDocsLog inGet started
Tessl Logo

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.

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/media-proxy/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

91%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 an excellent, lean overview: executable code, a well-sequenced crash-resume workflow with explicit anti-double-bill validation, and clean one-level-deep references to real bundle scripts. Minor conciseness trims possible but no real gaps.

DimensionReasoningScore

Conciseness

Largely lean and assumes Claude's competence; minor instances of restated rationale (e.g. 're-firing double-bills' repeated) could be trimmed, but no padding of basic concepts.

4 / 5

Actionability

Provides copy-paste-ready Python imports and concrete calls with real model paths and arguments, plus executable resume.py CLI commands covering the common cases.

5 / 5

Workflow Clarity

The crash-resume flow is explicitly sequenced with a validation/feedback loop: poll-through-outage, persist + resume, and 're-attach instead of re-firing' to prevent double-billing — explicit checkpoints for a batch/destructive (billed) operation.

5 / 5

Progressive Disclosure

SKILL.md is a concise overview pointing one level deep to real bundle files (scripts/media_proxy.py, scripts/resume.py) referenced by actual import names and CLI usage, with clear sections and easy navigation.

5 / 5

Total

19

/

20

Passed

Description

58%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 is specific and concrete about the proxy-routing and billing mechanics, but it omits an explicit 'Use when...' trigger clause and relies on internal product terminology rather than natural user phrases. These gaps cap completeness and trigger-term quality.

Suggestions

Add an explicit 'Use when...' clause, e.g. 'Use when generating paid FAL images/video or ElevenLabs music that must bill the Ads agent.'

Add natural synonyms and file/task phrases a user would say (e.g. 'generate ad images', 'render video ads', 'background music') alongside the product jargon.

Trim the implementation detail (host-swaps, credentials.json path) from the description and keep it to what + when, moving mechanics to the body.

DimensionReasoningScore

Specificity

Names the concrete actions (host-swap queue URLs, load agent token from credentials.json, return CDN URL, route FAL image/video and ElevenLabs music through proxies) with minor coverage gaps.

4 / 5

Completeness

Clearly answers 'what does this do' (routes/bills via proxies) but has no explicit 'Use when...' trigger clause, which caps completeness at 3.

3 / 5

Trigger Term Quality

Includes relevant technical terms (paid media, FAL image/video, ElevenLabs music, proxies) but lacks the natural phrases and synonyms a user would say; it leans on internal product jargon.

3 / 5

Distinctiveness Conflict Risk

Serves a clear niche (proxy routing for paid media billing) with minimal overlap risk against other skills; mostly distinct.

4 / 5

Total

14

/

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.