agent-native-docs

How to find version-matched Agent Native framework docs and source bundled in node_modules. Use before implementing or answering questions about @agent-native/core APIs, generated apps, workspaces, templates, or advanced features.

Quality

87%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Failed to scan

The risk profile of this skill

Quality

Content

100%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The body is a tight, actionable, well-structured lookup workflow with executable commands, a clear fallback, and no padding. It is an instruction-only skill that fully meets the rubric across all dimensions.

Dimension	Reasoning	Score
Conciseness	The body is lean throughout: a terse Rule, a command-only How section, a compact slug lookup table, and three brief Don'ts, with no explanation of concepts Claude already knows; every line earns its place, matching anchor 3.	3 / 3
Actionability	It gives fully executable commands ("pnpm action docs-search --query", "--slug", "source-search --path") plus a concrete fallback ("search node_modules/@agent-native/core/docs directly with rg") with real paths, matching the copy-paste-ready anchor 3.	3 / 3
Workflow Clarity	Six numbered steps form a clear sequence with an explicit fallback branch in step 5 ("If the action runner is unavailable, search ... directly with rg"); this is a read-only lookup task so no validation checkpoint is required and the destructive-operations cap does not apply, matching anchor 3.	3 / 3
Progressive Disclosure	The skill is under 50 lines with no bundle files and no need for external references, and it is well-organized into Rule / How / Useful Slugs / Don't sections, satisfying the simple-skill allowance for anchor 3.	3 / 3
	Total	12 / 12 Passed

Description

75%

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 clearly communicates a specific niche and includes an explicit 'Use before...' trigger, answering both what and when. It is slightly held back by a single action verb and jargon-leaning, low-variation trigger terms.

Suggestions

Lead with an active third-person verb and enumerate discrete actions (e.g., "Looks up version-matched docs by feature, reads pages by slug, and searches source examples") to raise specificity from anchor 2 to 3.

Broaden trigger terms with natural variations users are likely to say (e.g., "Agent Native", "agent-native core", "framework docs", "find docs") alongside the package import path to improve trigger-term coverage.

Dimension	Reasoning	Score
Specificity	"look up version-matched Agent Native framework docs and source in node_modules" names the domain and a concrete action, but it is a single verb (look up) applied to two objects rather than a comprehensive list of distinct actions, matching anchor 2; not 3 because it lacks multiple discrete actions like "Extract, fill, merge", and not 1 because it is concrete and specific rather than vague.	2 / 3
Completeness	It states both what ("look up version-matched ... docs and source") and an explicit when ("Use before coding against @agent-native/core APIs or advanced features"), satisfying the anchor-3 requirement for an explicit trigger clause and avoiding the cap at 2.	3 / 3
Trigger Term Quality	Terms "@agent-native/core", "Agent Native framework", and "node_modules" are real domain keywords a user of this framework would say, but coverage is thin and leans on technical jargon with few natural variations, matching anchor 2; not 3 because it does not provide broad coverage of multiple natural terms, and not 1 because the package name is a genuine user-facing keyword.	2 / 3
Distinctiveness Conflict Risk	The description is narrowly scoped to a single named package (@agent-native/core) with distinct package-specific triggers, giving it a clear niche unlikely to conflict with unrelated skills.	3 / 3
	Total	10 / 12 Passed

Validation

100%

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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: BuilderIO/agent-native
Path: .agents/skills/agent-native-docs/SKILL.md
Commit: c1ee18b

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.