detecting-performance-bottlenecks

Execute this skill enables AI assistant to detect and resolve performance bottlenecks in applications. it analyzes cpu, memory, i/o, and database performance to identify areas of concern. use this skill when you need to diagnose slow application performance, op... Use when optimizing performance. Trigger with phrases like 'optimize', 'performance', or 'speed up'.

Install with Tessl CLI

npx tessl i github:jeremylongshore/claude-code-plugins-plus-skills --skill detecting-performance-bottlenecks

What are skills?

Quality

44%

Does it follow best practices?

Impact

Pending

No eval scenarios have been run

Optimize this skill with Tessl

npx tessl skill review --optimize ./plugins/performance/bottleneck-detector/skills/detecting-performance-bottlenecks/SKILL.md

SKILL.md

Review

Evals

Discovery

82%

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

This description has good completeness with explicit trigger guidance and decent trigger term coverage. However, it suffers from truncation (text cuts off mid-word with 'op...'), uses first-person framing ('enables AI assistant'), and could be more specific about concrete actions. The broad scope covering CPU, memory, I/O, and database performance may create overlap with more specialized skills.

Suggestions

Complete the truncated text and list specific concrete actions (e.g., 'profile code execution', 'identify memory leaks', 'analyze query execution plans')

Rewrite in third person voice - change 'enables AI assistant to detect' to 'Detects and resolves performance bottlenecks'

Add more distinctive triggers to reduce conflict risk, such as specific file types (.prof, flame graphs) or tool names (profiler, benchmark)

Dimension	Reasoning	Score
Specificity	Names the domain (performance bottlenecks) and lists some actions (analyzes cpu, memory, i/o, database performance, diagnose slow application performance), but the description is truncated and uses somewhat generic language like 'areas of concern' rather than concrete specific actions.	2 / 3
Completeness	Explicitly answers both what (detect and resolve performance bottlenecks, analyzes cpu/memory/i/o/database) and when (Use when optimizing performance, with explicit trigger phrases). Has a clear 'Use when...' clause with trigger terms.	3 / 3
Trigger Term Quality	Includes good natural trigger terms users would say: 'optimize', 'performance', 'speed up', plus domain terms like 'cpu', 'memory', 'i/o', 'database performance', 'slow application'. These are terms users naturally use when seeking performance help.	3 / 3
Distinctiveness Conflict Risk	Reasonably specific to performance optimization, but 'optimize' and 'performance' are broad terms that could overlap with other optimization skills (e.g., code optimization, database-specific tuning). The scope is somewhat broad covering multiple performance domains.	2 / 3
	Total	10 / 12 Passed

Implementation

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

This skill is almost entirely abstract description with no actionable content. It explains what bottleneck detection conceptually involves but provides zero concrete tools, commands, code examples, or diagnostic procedures. The content reads like marketing copy rather than technical guidance Claude can execute.

Suggestions

Replace abstract descriptions with concrete profiling commands (e.g., `py-spy`, `perf`, `EXPLAIN ANALYZE` for databases, memory profilers like `tracemalloc`)

Add executable code examples for each bottleneck type (CPU, memory, I/O, database) showing actual diagnostic and remediation patterns

Remove generic boilerplate sections (Prerequisites, Instructions, Output, Error Handling) that provide no specific guidance

Include specific validation steps and metrics thresholds (e.g., 'Query taking >100ms indicates indexing issue, verify with EXPLAIN')

Dimension	Reasoning	Score
Conciseness	Extremely verbose with extensive padding explaining concepts Claude already knows. Phrases like 'This skill empowers Claude' and generic sections like 'Prerequisites', 'Instructions', 'Output', and 'Error Handling' add no actionable value and waste tokens.	1 / 3
Actionability	No concrete code, commands, or executable guidance provided. The entire skill describes what it will do abstractly ('The skill will analyze...') rather than providing actual profiling commands, code snippets, or specific diagnostic steps.	1 / 3
Workflow Clarity	The 'How It Works' section lists vague phases without any concrete steps, validation checkpoints, or specific tools/commands. No actual workflow for diagnosing bottlenecks is provided—just abstract descriptions of what 'Claude will do'.	1 / 3
Progressive Disclosure	Content is organized into sections with headers, but it's a monolithic document with no references to external files for detailed guidance. The structure exists but contains mostly filler content that doesn't warrant the organization.	2 / 3
	Total	5 / 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 — 9 / 11 Passed

Validation for skill structure

Criteria	Description	Result
allowed_tools_field	'allowed-tools' contains unusual tool name(s)	Warning
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	9 / 11 Passed

Reviewed: 2 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.