upgrade-agent-native

Bring an older Agent Native app or workspace current. Use when updating @agent-native/core, fixing a broken upgrade, or when tempted to patch or override core/dispatch packages to make an old branch run.

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

90%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 focused, highly actionable upgrade procedure with copy-paste commands, an explicit anti-pattern (Don't) list, and a clear error-recovery loop. The main gap is the absence of an explicit post-upgrade validation checklist on the happy path.

Suggestions

Add an explicit 'Verify' checkpoint on the happy path (e.g., after step 2: run pnpm typecheck and confirm skills update scaffold --project succeeded before proceeding) so validation is not only surfaced in the failure branch.

Consider extracting the 'Don't' list and template-sync detail into a short reference file if the skill grows, to keep SKILL.md as a lean overview.

State the expected exit condition for step 2's upgrade command (e.g., 'manifest pins rewritten to resolved versions, typecheck green') so success is unambiguous.

Dimension	Reasoning	Score
Conciseness	Lean and tightly operational throughout — no basic-concept padding, every section (Rule, Why, How, Don't, Related) earns its place, and explanatory prose is actionable guidance rather than over-explanation.	5 / 5
Actionability	Fully executable copy-paste commands cover the common cases (npx ... upgrade --codemods, template status/diff/sync, doctor --only, dry-run/partial flags) with concrete variants for installed vs npx invocation.	5 / 5
Workflow Clarity	A clearly sequenced five-step process with an error-recovery feedback loop in step 4 and a CI pre-check (migration-manifest), but the main happy path relies on the command's auto typecheck rather than an explicit validate-fix-retry checklist.	4 / 5
Progressive Disclosure	Well-organized into clear sections with one-level-deep, clearly signaled links to related skills; no nested references. It is a single self-contained file with no bundle files, so structure is good but there is no content split to reward.	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 tight, third-person description that clearly states both the capability and multiple explicit use-when triggers, with strong distinctiveness. It is slightly technical in its trigger terms rather than packed with lay synonyms.

Dimension	Reasoning	Score
Specificity	Names the domain ("older Agent Native app or workspace") and several concrete actions/situations (updating @agent-native/core, fixing a broken upgrade, patching/overriding core/dispatch), but the core 'what' is a single action (bring current) so coverage is strong rather than comprehensive.	4 / 5
Completeness	Explicitly answers both what ("Bring an older Agent Native app or workspace current") and when ("Use when updating... fixing a broken upgrade, or when tempted to patch or override...") with concrete trigger phrases.	5 / 5
Trigger Term Quality	Includes natural developer-facing phrases like "updating @agent-native/core", "broken upgrade", "patch or override core/dispatch packages" — good keyword coverage, though the terms are fairly technical/niche with a few common variations absent.	4 / 5
Distinctiveness Conflict Risk	Targets a clear, narrow niche (Agent Native upgrades, specific @agent-native packages) with distinct triggers and minimal overlap risk with other 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/upgrade-agent-native/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.