customizing-agent-native

How to configure, compose, or eject Agent Native features into app-owned code. Use when overriding shared components or integrations, customizing a template, adding UI to chat or headless apps, or inspecting package source.

Quality

83%

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

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 an efficient, highly actionable reference: concrete TSX and CLI examples, an explicit customization precedence ladder, and ejection/restore commands with hash-gated safety. It is slightly below top marks on conciseness and workflow_clarity (the ejection flow lists verification commands but does not wire them into an explicit validate-fix-retry loop), and progressive_disclosure is good though the skill ships no bundle files to split out.

Suggestions

Add an explicit validate-fix-retry loop for destructive ejection: after `--apply`, gate on the manifest verification commands (fail -> fix -> re-run) before treating the ejection as complete, to lift workflow_clarity to 5.

Tighten the design-system section: the nine-leaf / eight-behavior component enumeration and adapter styling rationale can be condensed to the contract essentials Claude needs, trimming conciseness overhead.

If the full component contract or ejection manifest schema is long, move it into a reference file (e.g. references/design-system-contract.md) and link from the overview to strengthen progressive disclosure.

Dimension	Reasoning	Score
Conciseness	The body is dense and domain-specific with no padding of generic concepts Claude already knows; every section adds proprietary seams, contracts, and commands. A few explanatory sentences (e.g. the nine/eight component enumeration, adapter styling rationale) could be trimmed, landing it at 'efficient; minor instances of over-explanation' rather than the fully-lean 5.	4 / 5
Actionability	Provides copy-paste-ready executable guidance throughout — concrete `defineDesignSystem` TSX, `assertDesignSystemConformance` calls, and exact `agent-native eject --list / inspect / diff / restore` commands with flag semantics — covering the common configure/compose/eject cases fully.	5 / 5
Workflow Clarity	A clear 6-step precedence ladder sequences the customization paths, and the ejection flow has dry-run/`--apply`/hash-gated restore checkpoints plus 'After Ejecting' verification commands. It sits just below 5 because the destructive ejection path lacks an explicit validate-then-fix feedback loop stated inline (verification commands are listed but not wired as a gated retry sequence).	4 / 5
Progressive Disclosure	Well-organized into focused sections (Rule, Use A Company Design System, Eject A Feature, Don't, Related Skills) with a Related Skills pointer list; no bundle files exist so there is nothing to offload, and the structure is mostly appropriately placed. It is a near-monolithic overview rather than a pointer-tile to separate references, keeping it at 'good structure; minor organization gaps' rather than 5.	4 / 5
	Total	17 / 20 Passed

Description

83%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 strong: it explicitly states both what the skill does and when to use it with a concrete 'Use when' trigger clause, and uses correct third-person voice. Keyword coverage and distinctiveness are good but not maximal, missing package-name synonyms and carrying minor overlap risk with related agent skills.

Dimension	Reasoning	Score
Specificity	Names the domain (Agent Native features) and several concrete actions — 'configure, compose, or eject' plus 'overriding shared components', 'customizing a template', 'adding UI', 'inspecting package source' — with only minor coverage gaps, fitting the 'lists several specific actions' anchor above the 3.	4 / 5
Completeness	Explicitly answers both 'what' ('How to configure, compose, or eject Agent Native features into app-owned code') and 'when' via a concrete 'Use when...' clause enumerating trigger scenarios, matching the 'clearly and explicitly answers both what AND when' anchor.	5 / 5
Trigger Term Quality	Includes natural phrases a user would say ('customizing a template', 'adding UI to chat or headless apps', 'overriding shared components') but lacks the package/file-style synonyms (e.g. '@agent-native/*', eject) users would name, so it sits at 'good keyword coverage, a few natural terms missing' rather than 5.	4 / 5
Distinctiveness Conflict Risk	The 'Agent Native' niche plus eject/compose/configure framing is distinct from generic skills, but the broad 'customizing a template' / 'adding UI' phrasing could lightly overlap with adjacent agent skills, placing it at 'mostly distinct; minor overlap risk' rather than the fully-clear 5.	4 / 5
	Total	17 / 20 Passed

Validation

81%

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 — 13 / 16 Passed

Validation for skill structure

Criteria	Description	Result
metadata_version	'metadata.version' is missing	Warning
metadata_field	'metadata' should map string keys to string values	Warning
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	13 / 16 Passed

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

Reviewed: 5 days 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.