performance-oracle

Analyzes code for performance bottlenecks, algorithmic complexity, database queries, memory usage, and scalability. Use after implementing features or when performance concerns arise.

Quality

73%

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

Fix and improve this skill with Tessl

tessl review fix ./.agents/skills/performance-oracle/SKILL.md

Quality

Content

70%

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

A well-structured analysis-framework skill with a clear review workflow and output format. It loses points mainly on actionability (no concrete executable examples or tooling commands) and mild verbosity in the framing prose.

Suggestions

Add at least one concrete executable example, e.g. a sample profiling command or a code snippet showing a detected N+1 query and its optimized form, so recommendations have a copy-paste-ready template.

Trim motivational framing like 'You are the Performance Oracle, an elite performance optimization expert...' and 'Your primary mission is to ensure...' to reduce tokens without losing guidance.

Add a validation/benchmarking checkpoint to the review approach (e.g. 'measure before and after optimizing') to strengthen the feedback loop for performance changes.

Dimension	Reasoning	Score
Conciseness	The body is well-organized and mostly free of basic-concept explanation, but it restates capability lists ('You systematically evaluate:', 'You enforce these standards:') and instructional padding ('Your primary mission...', 'You are the Performance Oracle, an elite...') that could be trimmed without losing actionable value.	2 / 3
Actionability	It gives a concrete output format and a sequenced review approach, and asks for 'specific code examples' in recommendations — but it contains no executable code, commands, or concrete tooling examples itself; guidance is directive rather than copy-paste ready.	2 / 3
Workflow Clarity	The 'Code Review Approach' lays out a clear five-pass sequence and the 'Analysis Output Format' enumerates an explicit ordered structure with sub-bullets per section, giving a well-sequenced multi-step process.	3 / 3
Progressive Disclosure	No bundle files exist, so this is a self-contained skill; content is organized into clearly headed sections (Core Analysis Framework, Benchmarks, Output Format, Review Approach) with no nested references, fitting the simple/well-organized-skill anchor for a 3.	3 / 3
	Total	10 / 12 Passed

Description

77%

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: concrete capabilities, third person, and an explicit Use-when clause. The main weakness is trigger-term coverage — it relies on generic phrasing rather than the concrete performance words users actually say.

Suggestions

Expand the Use-when clause with concrete user phrasings, e.g. 'Use when the user reports slow responses, high latency, scaling concerns, or asks to optimize a function or query.'

Tighten distinctiveness by contrasting with code-review skills, e.g. a phrase noting it focuses on runtime performance rather than correctness or style.

Dimension	Reasoning	Score
Specificity	Lists five concrete specific actions — 'Analyzes code for performance bottlenecks, algorithmic complexity, database queries, memory usage, and scalability' — matching the anchor that lists multiple specific concrete actions.	3 / 3
Completeness	Explicitly states what it does (analyze code for the five listed performance dimensions) and when to use it ('Use after implementing features or when performance concerns arise'), answering both halves with an explicit trigger clause.	3 / 3
Trigger Term Quality	It includes relevant natural phrases like 'performance bottlenecks' and 'performance concerns arise' that a user might say, but lacks common variations users actually voice ('slow', 'latency', 'scaling', 'response time', 'optimize'), so coverage is partial.	2 / 3
Distinctiveness Conflict Risk	The performance-analysis niche is fairly distinct, but the trigger ('when performance concerns arise' / 'after implementing features') is broad and could overlap with general code-review or testing skills, so it is only somewhat specific rather than a clear, conflict-free niche.	2 / 3
	Total	10 / 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: udecode/plate
Path: .agents/skills/performance-oracle/SKILL.md
Commit: 45116fd

Reviewed: about 14 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.