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

59%

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

56%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.

The skill body is well-structured and concise, framing performance analysis through a clear framework and sequenced review passes. Its main weakness is actionability: it describes what to look for but rarely gives Claude concrete, executable detection methods or code patterns.

Suggestions

Add concrete, executable detection patterns or tool commands (e.g., example SQL EXPLAIN usage, a snippet showing an N+1 vs. eager-loaded query, profiler invocation) to lift actionability.

Include explicit validation checkpoints in the review workflow (e.g., confirm a flagged O(n^2) pattern with a complexity trace before reporting) to support error recovery.

Trim persona/mission prose ('You are the Performance Oracle... Your deep expertise spans...') to tighten conciseness toward 5.

Dimension	Reasoning	Score
Conciseness	Largely efficient bullet-listed framework that assumes Claude's competence and avoids explaining basic concepts, with only minor padding like 'Your deep expertise spans...' and mission-statement prose that could be trimmed.	4 / 5
Actionability	Provides only high-level descriptive guidance ('Identify time complexity', 'Detect N+1 query patterns') with no executable code, commands, tools, or concrete detection methods, mirroring the 2-anchor 'high-level hints but missing specific steps'.	2 / 5
Workflow Clarity	The 'Code Review Approach' lays out a clear five-pass sequence and the output format structures results well, but validation checkpoints and error-recovery feedback loops are absent for what is effectively a batch analysis pass.	4 / 5
Progressive Disclosure	Well-organized with clear section headers (Core Analysis Framework, Benchmarks, Output Format) and no bundle files to misplace; content stays one level deep with minor opportunity to externalize the detailed output template.	4 / 5
	Total	14 / 20 Passed

Description

62%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 solid, third-person description that names concrete capability domains and an explicit use-trigger, distinguishing it from generic review skills. It would benefit from more granular action enumeration and more natural trigger-term coverage.

Suggestions

Add natural trigger terms users actually say (e.g., 'slow', 'latency', 'optimize', 'profiling', 'response time') to improve trigger_term_quality.

Enumerate a couple of discrete actions (e.g., 'detects N+1 queries, flags O(n^2) algorithms') rather than only naming analysis categories to lift specificity toward 5.

Broaden the 'when' clause to include proactive profiling/optimization requests, not just post-implementation and performance-concern scenarios.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete analysis actions (algorithmic complexity, database queries, memory usage, scalability) but stops at category-level rather than enumerating discrete operations like the 5-anchor example.	4 / 5
Completeness	Clearly states what (analyzes code for performance issues across five domains) and provides an explicit 'Use after implementing features or when performance concerns arise' trigger, though the when-clause is slightly narrow.	4 / 5
Trigger Term Quality	Includes relevant performance keywords (bottlenecks, performance, scalability) but lacks common natural phrasings users say ('slow', 'latency', 'optimize', 'profiling') and synonyms that would push it to 4-5.	3 / 5
Distinctiveness Conflict Risk	Has a clear performance-analysis niche with distinct triggers, though the broad 'code analysis' framing has minor overlap risk with general code-review skills.	4 / 5
	Total	15 / 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: udecode/plate
Path: .agents/skills/performance-oracle/SKILL.md
Commit: cce36d3

Reviewed: 6 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.