performance

Keep apps and templates loading fast. Read when adding a data model, a list/read action, a page or sidebar that loads data, or when something loads slowly. Covers column projection, indexing hot-path queries, avoiding N+1 and round-trip waterfalls, cheap polling, and not recomputing on every read.

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

77%

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

A dense, highly actionable body with executable examples, specific identifiers, and a verification checklist. Its main weaknesses are verbosity in the SSR and provider-wrapper sections and the absence of any file-level progressive disclosure for the longer material.

Suggestions

Tighten section 6 (SSR shell caching) and the provider-wrapper paragraphs in section 3 to directive statements, cutting prose that does not change what Claude should do — this targets the lowest dimension, conciseness.

Move the SSR cache contract detail (the AGENT_NATIVE_SSR_CACHE env var, guard:ssr-cache-shell, and ssr-handler.spec.ts reference) into a one-level-deep reference file and link to it from a short SSR section, improving progressive_disclosure.

Consider extracting the index-DDL patterns and ownable/shares/FK index recipes into a references/ file linked from section 2, keeping the SKILL.md body as a lean overview that points to detailed recipes.

Dimension	Reasoning	Score
Conciseness	Mostly efficient and free of basic-concept padding, with concrete code in the core sections, but several passages — the provider-wrapper architectural prose in section 3 and the multi-paragraph SSR discussion in section 6 — could be tightened while preserving clarity, matching the score-2 anchor.	2 / 3
Actionability	Provides fully executable Drizzle query and SQL index-DDL examples plus specific identifiers (inArray, count(), Promise.all, useActionQuery, useDbSync) and exact file paths (server/plugins/db.ts, packages/core/src/server/ssr-handler.ts), matching the copy-paste-ready score-3 anchor.	3 / 3
Workflow Clarity	A numbered 1-7 structure plus an explicit pre-shipping "Checklist — run before shipping a list/read or a new table" supplies the validation checkpoints the rubric rewards, avoiding the cap for missing verification on database/batch operations.	3 / 3
Progressive Disclosure	Well organized into clearly headed sections, but the skill is a single >50-line monolithic file with no bundle reference files, and deeper material (SSR cache contract, provider-wrapper guidance) lives inline rather than in one-level-deep referenced files, matching the score-2 anchor.	2 / 3
	Total	10 / 12 Passed

Description

100%

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, concise description that states a clear purpose, lists concrete capabilities, and gives explicit, natural trigger guidance. It is specific, actionable, and clearly distinguishes the skill's niche from related data and sync skills.

Dimension	Reasoning	Score
Specificity	Lists multiple specific concrete capabilities — "column projection, indexing hot-path queries, avoiding N+1 and round-trip waterfalls, cheap polling, and not recomputing on every read" — rather than vague abstractions, matching the score-3 anchor that enumerates concrete actions.	3 / 3
Completeness	Answers both what ("Keep apps and templates loading fast" plus the covered topics) and when with an explicit trigger clause ("Read when adding a data model... or when something loads slowly"), the equivalent of a "Use when..." clause required for a 3.	3 / 3
Trigger Term Quality	Natural trigger phrasings a developer would actually say are well covered: "adding a data model", "a list/read action", "a page or sidebar that loads data", and "when something loads slowly" — multiple variations, matching the score-3 anchor.	3 / 3
Distinctiveness Conflict Risk	The latency/load-path framing ("Keep apps and templates loading fast") carves a clear niche with distinct triggers; minor overlap with storing-data/real-time-sync is outweighed by the load-speed focus, so it is unlikely to trigger for the wrong skill.	3 / 3
	Total	12 / 12 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/performance/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.