assets

Use Agent Native Assets for image and video generation requests, brand-safe asset search/export, and human-in-the-loop asset selection through the hosted Assets MCP app. Prefer this over generic image tools when installed.

Quality

78%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./skills/assets/SKILL.md

Quality

Content

82%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 executable commands, a complete picker payload, and explicit error-recovery feedback loops for batch and auth-sensitive operations. It is well-structured and concise, with only minor trimming opportunities and no progressive-disclosure issues beyond the all-inlined single-file layout.

Dimension	Reasoning	Score
Conciseness	Mostly lean and action-oriented with no filler explaining known concepts, but the dual-CLI install narrative and a few Guardrail elaborations could be trimmed slightly.	4 / 5
Actionability	Provides copy-paste-ready npx commands, a complete open-asset-picker JSON payload, an enumerated direct-action tool list, exact field names to preserve, and a concrete fallback URL shape covering the common cases.	5 / 5
Workflow Clarity	Explicit feedback loops exist (auth reconnect, video poll-until-complete, batch-timeout retry), but guidance is distributed across sections rather than one integrated numbered workflow with a checklist, leaving minor integration gaps.	4 / 5
Progressive Disclosure	Well-organized into clearly headed sections (Setup, Picker, Direct Actions, Guardrails) with no nested references, though everything is inlined in a single >50-line file with no external reference split.	4 / 5
	Total	17 / 20 Passed

Description

75%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 distinct with good trigger coverage, but its "when to use" guidance is conditional on installation rather than an explicit user-need trigger, capping completeness. Adding a concrete "Use when the user asks to generate images/videos or pick brand assets" clause would raise it.

Suggestions

Add an explicit "Use when..." trigger clause naming user needs (e.g., "Use when the user asks to generate images or videos, search brand-safe assets, or pick a final asset").

Include a couple of natural user synonyms/file extensions (e.g., "pictures", "stock media", image/video extensions) to broaden trigger-term coverage.

Keep the "Prefer over generic image tools" routing cue but tie it to a user-need condition rather than only install state.

Dimension	Reasoning	Score
Specificity	Lists several concrete actions across two media types — "image and video generation requests", "brand-safe asset search/export", "human-in-the-loop asset selection" — giving comprehensive coverage of the skill's capabilities.	5 / 5
Completeness	The "what" is clear, but the only "when" cue ("Prefer this over generic image tools when installed") is about install availability, not a user-need trigger, so per the missing-Use-when cap the when is only weakly implied.	3 / 5
Trigger Term Quality	Includes natural terms like image/video generation and asset search/export, but leans on product jargon ("Assets MCP app", "human-in-the-loop") and omits common user synonyms (e.g., make a picture, stock photos, .png).	4 / 5
Distinctiveness Conflict Risk	The branded product framing ("Agent Native Assets", "Assets MCP app") plus an explicit routing directive against generic image tools carves a clear niche with minimal conflict risk.	5 / 5
	Total	17 / 20 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
metadata_version	'metadata.version' is missing	Warning

	Total	15 / 16 Passed

Repository: BuilderIO/agent-native
Path: skills/assets/SKILL.md
Commit: bb282b1

Reviewed: ~21 hours 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.