CtrlK
BlogDocsLog inGet started
Tessl Logo

media-generation

Generate images, videos, and SVGs using x402-protected AI models at StableStudio. USE FOR: - Generating images from text prompts - Generating videos from text or images - Editing images with AI - Vectorizing images to SVG - Creating visual content TRIGGERS: - "generate image", "create image", "make a picture" - "generate video", "create video", "make a video" - "edit image", "modify image" - "vectorize", "convert to svg" - "stablestudio", "nano-banana", "sora", "veo", "grok", "flux", "seedance", "gpt-image" ALWAYS use `npx agentcash@latest fetch` for stablestudio.dev endpoints.

72

Quality

89%

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

SKILL.md
Quality
Evals
Security

Quality

Content

78%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 highly actionable with comprehensive executable commands and a clear async-job workflow, but loses points for duplicated tables and dangling references to a rules/ bundle that is not present.

Suggestions

Bundle the referenced rules/getting-started.md and rules/uploads.md files (or remove/replace the dead links) so navigation resolves, which would raise progressive_disclosure.

Consolidate the duplicated Image/Video model tables — keep the Quick Reference tables and drop or slim the redundant Model Comparison section — to tighten conciseness.

Add an explicit error-recovery loop for job polling (e.g., on failed status, inspect error, retry with adjusted options, or DELETE and resubmit) to give workflow_clarity a full checkpoint sequence.

DimensionReasoningScore

Conciseness

Largely lean and token-efficient with concrete endpoints and options assuming Claude's competence, but model tables are duplicated (Quick Reference and Model Comparison) and pricing details repeat, adding minor padding that could be trimmed. Not a 5 because the duplication is unnecessary overhead.

4 / 5

Actionability

Provides copy-paste-ready `npx agentcash@latest fetch` commands with complete JSON bodies per model, full option specs, and concrete polling commands — covering the common cases comprehensively as the score-5 anchor requires.

5 / 5

Workflow Clarity

The async job workflow is clearly sequenced (submit → jobId/pollUrl → poll at 3s/10s → retrieve URL) with a checkpoint ('do not resubmit pending jobs'), but there is no explicit error-recovery feedback loop beyond noting DELETE for failed jobs, leaving a minor validation gap. Not a 3 because polling guidance and the don't-resubmit rule are genuine checkpoints; not a 5 because a validate/fix/retry loop is absent.

4 / 5

Progressive Disclosure

Sections are well-organized with clear headers and quick-reference tables, but the two referenced files — rules/getting-started.md and rules/uploads.md — do not exist (no rules/ directory is bundled), so navigation is broken, and dense per-model option specs that could live in separate references are inlined. Not a 4 because the dangling references are a real navigation defect; not a 2 because structure and sectioning are genuinely present.

3 / 5

Total

16

/

20

Passed

Description

100%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 exemplary: it states concrete capabilities, enumerates natural trigger phrases with synonyms and product names, and cleanly separates 'what' from 'when'. No revisions needed.

DimensionReasoningScore

Specificity

Lists multiple concrete actions — 'Generate images, videos, and SVGs' plus a USE FOR list of five specific tasks (image-from-text, video, edit, vectorize, visual content) — giving comprehensive coverage comparable to the score-5 anchor.

5 / 5

Completeness

Explicitly answers both 'what' (Generate images, videos, and SVGs at StableStudio) and 'when' (a dedicated TRIGGERS list of concrete phrases), matching the score-5 anchor.

5 / 5

Trigger Term Quality

TRIGGERS provides comprehensive natural phrases including synonyms ('generate image'/'create image'/'make a picture') and product names (sora, veo, grok, flux, seedance), exceeding the score-5 example's coverage.

5 / 5

Distinctiveness Conflict Risk

Clear niche — x402-protected media generation at StableStudio — with distinct product-name triggers giving minimal conflict risk with other skills.

5 / 5

Total

20

/

20

Passed

Validation

87%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation14 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

metadata_field

'metadata' should map string keys to string values

Warning

relative_links

Relative link issues: 2 missing

Warning

Total

14

/

16

Passed

Repository
Merit-Systems/agentcash-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.