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, or when adding a dependency to the deployed server bundle. Covers column projection, indexing hot-path queries, avoiding N+1 and round-trip waterfalls, cheap polling, not recomputing on every read, and cold-start artifact size.

Quality

87%

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

82%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 dense, highly actionable performance skill with executable code, real measured data, and a strong shipping checklist. Its main weakness is moderate verbosity in the incident-narrative sections and no split into reference files.

Suggestions

Tighten §8 and §9 by moving the production-incident storytelling into a short measured-data table and one sentence each, keeping the rules up front.

Consider extracting the §9 cold-start measurement procedure and bundle-budget details into a referenced file so SKILL.md stays a lean overview.

Add an explicit 'diagnose → fix → re-measure' loop for the slow-list / slow-cold-start cases so the workflow has a clear retry checkpoint.

Dimension	Reasoning	Score
Conciseness	Mostly lean and assumes Claude's competence (no generic explanations of SQL or indexes), but the production-incident anecdotes in §8/§9 and the narrative framing ('This has already cost real outages ...') could be trimmed without losing the rule.	4 / 5
Actionability	Provides copy-paste-ready executable examples throughout — Drizzle projection with substr, CREATE INDEX DDL, the cold-start timing one-liner, and a guarded backfill line — covering the common cases concretely.	5 / 5
Workflow Clarity	Numbered sections §1–§9 give a clear sequence and the closing 10-item checklist is an explicit pre-ship validation checkpoint, but there is no validate→fix→retry feedback loop (acceptable here since the skill is guidance, not a destructive operation).	4 / 5
Progressive Disclosure	Well-organized into clearly headed sections with explicit cross-references to related skills and codebase files; no bundle files exist so all content is inline, and a few of the long anecdote/measurement blocks could plausibly live in separate reference files.	4 / 5
	Total	17 / 20 Passed

Description

92%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, third-person description with concrete capability coverage and an explicit 'Read when' trigger clause. It clearly distinguishes itself from adjacent skills via cross-references.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete capabilities — 'column projection, indexing hot-path queries, avoiding N+1 and round-trip waterfalls, cheap polling, not recomputing on every read, and cold-start artifact size' — giving comprehensive, specific coverage rather than vague language.	5 / 5
Completeness	Explicitly states the 'what' ('Keep apps and templates loading fast' plus the covers list) and an explicit 'Read when ...' clause with concrete trigger phrases, answering both what and when.	5 / 5
Trigger Term Quality	Natural developer triggers like 'adding a data model, a list/read action, a page or sidebar that loads data, or when something loads slowly, or when adding a dependency' are good, but a few common synonyms are missing and 'deployed server bundle' leans slightly jargon-ward.	4 / 5
Distinctiveness Conflict Risk	Occupies a clear load-performance niche and explicitly defers sibling concerns to the storing-data, real-time-sync, and authentication skills, minimizing conflict risk.	5 / 5
	Total	19 / 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/performance/SKILL.md
Commit: b0df876

Reviewed: 1 day 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.