agent-native-toolkit

Inventory and ownership rules for shared Agent-Native workspace UI. Use before building app chrome, settings, navigation, sharing, collaboration, setup, history, comments, chat rails, agent UX, or repeated workspace behavior.

Quality

80%

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

75%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.

A well-crafted, dense instruction skill with concrete ownership rules, clear numbered workflows, and explicit validation guidance. It is held back from top marks only by the absence of executable code examples and a few catalog-style sections that lean slightly long.

Suggestions

Tighten the Reusable Kits catalog — consider a one-line summary per kit with a pointer to a reference file, to reduce inlined bulk and lift conciseness.

Add a short copy-paste example (e.g. a minimal defineDesignSystem/ToolkitProvider wiring) to lift actionability for the most common adoption case.

Make the validation feedback loop in the Implementation Checklist explicit (validate -> fix -> re-validate) so the workflow-clarity checkpoint reads as an explicit loop rather than an implied one.

Dimension	Reasoning	Score
Conciseness	The body is dense and assumes Claude's competence — every line states a concrete ownership rule ('Never use sparkle, wand, magic, or robot icons', named leaf components) with no padded concept explanations. It is efficient but a couple of catalog sections (e.g. the long Reusable Kits list) could be tightened, fitting anchor 4 rather than the fully-lean 5.	4 / 5
Actionability	It gives concrete, executable guidance — specific commands ('agent-native eject --list'), API calls ('registerRequiredSecret({ kind: "api-key" })'), route paths ('/settings#account'), and a need-to-primitive table. As an instruction/decision skill it is mostly actionable with minor gaps, matching anchor 4; it is not a 5 because there are no copy-paste code blocks covering common cases.	4 / 5
Workflow Clarity	Multi-step processes are clearly sequenced (the numbered 'Discover Before Building' and 9-step 'Implementation Checklist'), and validation checkpoints are present ('Run the adapter against @agent-native/toolkit/conformance in customer CI'). This matches anchor 4 (clear sequence with most checkpoints) rather than 5, since some checkpoints are implied rather than explicit feedback loops.	4 / 5
Progressive Disclosure	The body is well-organized with clear section headers and inline-signaled references to other skills and guides ('See the agent-page skill', 'customizing-agent-native'). No bundle files exist to split content into, and the structure is good with minor organization gaps (e.g. the inlined Reusable Kits catalog), fitting anchor 4.	4 / 5
	Total	16 / 20 Passed

Description

86%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 description that clearly states both what the skill does and when to use it, with excellent natural trigger-term coverage. The only weak spot is specificity, since the stated action ('inventory and ownership rules') is abstract rather than a list of concrete operations.

Suggestions

Consider sharpening specificity by naming a couple of concrete actions the skill performs (e.g. 'classify behavior as app-local or toolkit-shared, and route it to the correct kit') alongside the domain.

Dimension	Reasoning	Score
Specificity	The description names the domain ('shared Agent-Native workspace UI') and a concrete function ('Inventory and ownership rules'), but the stated action is fairly abstract decision-making rather than multiple specific concrete actions. It sits at anchor 3 (names domain and 1-2 concrete actions) rather than 4, which would require several specific listed actions.	3 / 5
Completeness	It explicitly answers both 'what' ('Inventory and ownership rules for shared Agent-Native workspace UI') and 'when' with concrete trigger phrases ('Use before building app chrome, settings, navigation, sharing...'), matching the anchor 5 example that clearly answers both with concrete triggers.	5 / 5
Trigger Term Quality	It lists a comprehensive set of natural surface-area terms a user would actually say — 'app chrome, settings, navigation, sharing, collaboration, setup, history, comments, chat rails, agent UX' — covering synonyms and common variations, matching the anchor 5 example of comprehensive keyword coverage.	5 / 5
Distinctiveness Conflict Risk	It carves a clear niche (Agent-Native workspace UI ownership) with distinct triggers, but has minor overlap risk with closely related skills it itself cross-references (e.g. sharing, frontend-design). This fits anchor 4 (mostly distinct; minor overlap) rather than 5 (minimal conflict risk).	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/agent-native-toolkit/SKILL.md
Commit: b0df876

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.