perf-analyzer
Synthesize performance test findings into clear, actionable reports.
Install
mkdir -p .claude/skills/perf-analyzer && curl -L -o skill.zip "https://agentskills.codes/api/skills/download/1179" && unzip -o skill.zip -d .claude/skills/perf-analyzer && rm skill.zipInstalls to .claude/skills/perf-analyzer
Activation
This is the description your AI agent reads to decide when to run this skill — the better it matches your request, the more reliably it fires.
Use when synthesizing perf findings into evidence-backed recommendations and decisions.Key capabilities
- →Synthesize performance logs and profiling evidence
- →Draft actionable engineering recommendations
- →Identify failed hypotheses
- →Determine next steps for performance investigations
How it works
The skill processes raw performance data against a canonical requirements contract to generate a structured summary and actionable recommendations.
Inputs & outputs
When to use perf-analyzer
- →Summarize performance test results
- →Draft engineering recommendations
- →Evaluate failed hypotheses
- →Document breaking point analysis
About this skill
perf-analyzer
Synthesize performance investigation results into clear recommendations.
Follow docs/perf-requirements.md as the canonical contract.
Inputs
- Baseline data
- Experiment results
- Profiling evidence
- Hypotheses tested
- Breaking point results
Output Format
summary: <2-3 sentences>
recommendations:
- <actionable recommendation 1>
- <actionable recommendation 2>
abandoned:
- <hypothesis or experiment that failed>
next_steps:
- <if user should continue or stop>
Constraints
- Only cite evidence that exists in logs or code.
- If data is insufficient, say so and request a re-run.
When not to use it
- →When evidence is missing from logs or code
Prerequisites
Limitations
- →Requires data to exist in logs or code
- →Cannot synthesize findings without sufficient data
How it compares
It forces evidence-based reporting rather than subjective analysis of performance findings.
Compared to similar skills
perf-analyzer side by side with the closest alternatives in the catalog.
| Skill | Installs | Updated | Safety | Difficulty |
|---|---|---|---|---|
| perf-analyzer (this skill) | 3 | 6mo | No flags | Intermediate |
| agent-performance-analyzer | 1 | 6mo | No flags | Intermediate |
| ascend-profiling-analysis | 0 | 2mo | No flags | Advanced |
| agent-performance-benchmarker | 3 | 6mo | No flags | Advanced |
Try saying
Example prompts that trigger this skill in your AI assistant.
More by ComposioHQ
View all by ComposioHQ →You might also like
agent-performance-analyzer
ruvnet
Agent skill for performance-analyzer - invoke with $agent-performance-analyzer
ascend-profiling-analysis
Ascend
Analyze Ascend NPU profiling data to identify training performance bottlenecks. Breaks down step-level time into compute, unoverlapped communication, and freetime; within compute, analyzes compute vs memory-bound ratios and cube vs vector utilization to summarize the model's performance bottleneck.
agent-performance-benchmarker
ruvnet
Agent skill for performance-benchmarker - invoke with $agent-performance-benchmarker
google-analytics
davila7
Analyze Google Analytics data, review website performance metrics, identify traffic patterns, and suggest data-driven improvements. Use when the user asks about analytics, website metrics, traffic analysis, conversion rates, user behavior, or performance optimization.
backtesting-trading-strategies
jeremylongshore
Backtest crypto and traditional trading strategies against historical data. Calculates performance metrics (Sharpe, Sortino, max drawdown), generates equity curves, and optimizes strategy parameters. Use when user wants to test a trading strategy, validate signals, or compare approaches. Trigger with phrases like "backtest strategy", "test trading strategy", "historical performance", "simulate trades", "optimize parameters", or "validate signals".
model-usage
openclaw
Use CodexBar CLI local cost usage to summarize per-model usage for Codex or Claude, including the current (most recent) model or a full model breakdown. Trigger when asked for model-level usage/cost data from codexbar, or when you need a scriptable per-model summary from codexbar cost JSON.