skills.rest
Space-Dinosaurs
Space-DinosaursOFFICIAL
Explore all skills by this author →
Website𝕏@SpaceDinosaurS6GitHub

agent-perf-analyst

Profile CPU and memory usage of a target and report pass/fail against a perf budget.

12|1|Updated Apr 7, 2026
Search Tags:#performance#memory#profiling#latency#benchmark#measurement#analyze
One-click install
npx skills add https://github.com/Space-Dinosaurs/DinoStack --skill agent-perf-analyst
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: agent-perf-analyst
Source: https://github.com/Space-Dinosaurs/DinoStack/tree/main/.openclaw/skills/agent-perf-analyst
Command: npx skills add https://github.com/Space-Dinosaurs/DinoStack --skill agent-perf-analyst

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Performance analysis specialist. Spawn when a feature is slow, investigating a performance regression, benchmarking before/after a change, profiling CPU or memory hotspots, measuring latency or throughput against a budget, or hunting memory leaks. Distinct from debugger (correctness failures, stack traces) and qa-engineer (acceptance criteria, browser verification). Profiles, benchmarks, and bisects to find where time or memory is spent — then produces a measured findings brief the engineer can execute. Does NOT implement fixes.

Core Features & Use Cases

  • Performance profiling: identify CPU and memory hotspots, anomalies, and regression points across features.
  • Benchmarking and comparison: run before/after measurements to quantify improvements or degradations against budgets.
  • Findings brief delivery: produce a concise, evidence-based report for engineers to act on without implementing fixes.

Quick Start

Run a quick profiling session on the target feature to generate a findings brief that engineers can act on.

Frequently Asked Questions about agent-perf-analyst

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I profile a slow feature to find CPU or memory hotspots?▼

Profile a defined target using a reproducible command to collect quantitative metrics on where time or memory is spent. The resulting findings brief cites exact metrics and hotspots for engineers to act on.

What is the best way to benchmark performance before and after a change?▼

Benchmark performance by running before and after measurements to quantify improvements or degradations. Compare current measurements against an optional baseline and evaluate them against an explicit performance budget to determine pass or fail.

Does performance profiling implement code fixes for bottlenecks?▼

Performance profiling does not implement code fixes. It measures time and memory hotspots, compares them against budgets, and delivers a structured findings brief with actionable steps for engineers to execute.

How do I measure latency or throughput against a performance budget?▼

Measure latency or throughput against a budget by profiling a target with a reproducible command. Evaluate the collected metrics against an explicit performance budget to determine pass, fail, and overall impact.

When should I use a performance analysis specialist instead of a debugger?▼

Use a performance analysis specialist when a feature is slow, investigating regressions, or hunting memory leaks. A debugger addresses correctness failures and stack traces, while profiling measures time and memory to prove bottlenecks.

Related Skills

Explore More Software Engineering Skills→
BellaBeBellaBe
37

validation-action

Define acceptance criteria and generate validation plans with measurable metrics.

Community
Intermediate
VCERSVCERS
7

nsys-optimizer

Identify CUDA performance bottlenecks from Nsight Systems profiling data.

Official
Advanced
WellApp-aiWellApp-ai
341

qa-commit

Verify commits against QA Contracts with lint, type, and test checks.

Official
Advanced
deandumdeandum
3

performance

Profile, benchmark, and detect N+1 queries to identify performance bottlenecks.

Community
Advanced