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

88%

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

88%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.

An effective, actionable skill body that pairs a sequenced customization ladder with concrete code, CLI commands, and validation feedback loops for risky eject/restore operations. The main lever is splitting the contract catalog and command reference into bundled reference files to tighten the core overview.

Suggestions

Move the 9 leaf + 8 behavior component contract catalog into a references/ file (e.g. design-system-contract.md) and link to it from the design-system section to slim the inline overview.

Extract the eject/restore CLI command catalog into a references/ file, keeping only the canonical dry-run -> --apply flow inline.

Tighten explanatory sentences like 'They are ordinary React components and may use MUI-style providers...' to assume Claude's React competence unless the interop detail is load-bearing.

Dimension	Reasoning	Score
Conciseness	Dense and domain-specific throughout with no padding of concepts Claude already knows, but a few explanatory sentences ('Adapters translate the semantic Toolkit contract into company component props. They are ordinary React components...') could be trimmed, keeping it just below the leanest anchor.	4 / 5
Actionability	Provides copy-paste ready code (defineDesignSystem, assertDesignSystemConformance) and real executable commands (agent-native eject --list/inspect/--apply, eject diff/restore, rg searches) that cover the common cases with appropriate argument placeholders.	5 / 5
Workflow Clarity	A clear 6-step ordered sequence is paired with explicit validation checkpoints (dry-run by default, --apply after review, hash-gated restore that refuses edited files, 'Run the manifest verification commands plus formatter, typecheck, and focused tests') and an 'After Ejecting' checklist, giving feedback loops for a destructive/source-rewriting operation.	5 / 5
Progressive Disclosure	Well-organized into clearly signaled sections with only one-level references (related skills, source-search commands) and no nested reference chains, but some inline catalog material (the 9+8 component contract list, the full CLI command catalog) could plausibly live in reference files; no bundle files are present.	4 / 5
	Total	18 / 20 Passed

Description

87%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.

A strong, well-structured description that clearly states both capability and trigger conditions with concrete, natural language. Minor room to broaden trigger synonyms and surface 'eject'/'design system' as explicit keywords.

Dimension	Reasoning	Score
Specificity	Names the domain and three concrete actions ('configure, compose, or eject Agent-Native features into app-owned code') plus 'inspect package source'; comprehensive but a few edge actions (e.g., proposing seams) are only implied, so it sits just below the fully comprehensive anchor.	4 / 5
Completeness	Explicitly answers both what ('How to configure, compose, or eject Agent-Native features into app-owned code') and when ('Use when overriding shared components... customizing a template... adding UI...') with concrete trigger phrases, matching the top anchor.	5 / 5
Trigger Term Quality	'Use when overriding shared components or integrations, customizing a template, adding UI to chat or headless apps, or inspecting package source' gives good natural-phrase coverage a user would say, but misses some synonyms (e.g., 'eject', 'design system', 'fork') and has no file/extension tokens.	4 / 5
Distinctiveness Conflict Risk	The 'Agent-Native', 'app-owned code', and 'eject' framing carves a clear niche with distinct triggers and minimal overlap risk against generic customization skills.	5 / 5
	Total	18 / 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: a06e0ac

Reviewed: 4 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.