Works with the AI Agents you already use

    Claude CodeClaude CodeCursorCursorCodex CLICodex CLIDeepSeekDeepSeekMuseMuse+22 more

    Perf Profiler (Persona)

    1

    Guides performance work with measurements: benchmarks, bottleneck hypotheses and an optimization log. Includes the persona plus 4 skills: benchmark designer, benchmark template, bottleneck hypothesizer, optimization log.

    $39

    Secure checkout via Stripe

    Money-back guarantee

    Converts to your local currency at checkout

    Security scanned
    Perf Profiler (Persona)

    Perf Profiler (Persona)

    Example session with this skill installed

    I think we should add Redis to this endpoint to make it faster. Here is the current code. What do you think?

    • Read your context and instructions
    • Compiled the perf profiler persona

    Intuition proposes; the profiler disposes. What did you measure, and how? I cannot evaluate a caching layer without a baseline latency profile (p50, p95, p99) and a breakdown of the current data retrieval costs. Provide the measurement conditions first.

    Connects securely to your tools. The creator never sees your data.

    About this skill

    Guides performance work with measurements: benchmarks, bottleneck hypotheses and an optimization log.

    What is inside

    The persona plus 4 skills.

    • benchmark designer
    • benchmark template
    • bottleneck hypothesizer
    • optimization log

    Use cases

    • Analyzing CPU profiles to find the actual hot path in a service.
    • Evaluating whether a proposed architectural change justifies its complexity cost.
    • Debugging inconsistent benchmark results and identifying sources of variance.
    • Auditing legacy codebases for "premature optimizations" that are no longer effective.

    Known limitations

    Does not assist with infrastructure procurement, vendor selection, or load testing against third-party systems you do not own.

    Find more skills like this on the Claude Skills Marketplace, the Codex Skills Marketplace and the Gemini Skills Marketplace, or browse Claude Skills for Agents & Orchestration.

    Requires existing benchmark data or profiles to be useful. Will not perform capacity planning or assist with load testing third-party infrastructure.

    How to use

    1. 1

      Connect your agent to the Agensi MCP

      Copy the prompt and paste it into Claude, ChatGPT, Cursor or any agent that supports MCP. It sets up the connection for you. Manual setup

    2. 2

      Sign in to Agensi

      Your agent shows a sign-in link. Sign in and click Allow.

    3. 3

      Ask for what you need

      Your agent loads this skill and uses it on your task. It always asks before buying a skill.

    Reviews

    No reviews yet

    Be one of the first to try it. Every listed skill goes through the trust checks below.

    Security scanned

    Checked by our 8-point scan before listing

    Fresh listing

    Recently published to Agensi

    Money-back guarantee

    Doesn't do what its page promises? You get your money back.

    Trust & safety

    Security scan

    Security scan passed 3 months ago

    Permissions

    No special permissions declared or detected

    Listed3 months ago
    Updated6 days ago

    What's inside

    Frequently Asked Questions

    The persona enforces a strict measurement-first protocol, requiring baseline metrics and flame graph analysis before any code changes are considered. This prevents teams from wasting time on 'gut feeling' optimizations that often add technical debt without improving performance.

    This persona is designed to work with any high-reasoning LLM (such as GPT-4o or Claude 3.5 Sonnet) that supports custom system instructions or persona-based interactions. It is compatible with most major AI agent platforms and orchestration frameworks.

    A persona and 4 skills, each a plain SKILL.md file: benchmark designer, benchmark template, bottleneck hypothesizer, optimization log. The package has no scripts, templates or separate guides.

    Setup is simple: import the persona configuration into your preferred AI agent environment and provide your first set of profile logs or benchmark data. The skill will immediately begin auditing your methodology and identifying bottlenecks.

    While the persona can analyze performance data from any language, it is most effective when provided with standard outputs like pprof files, flame graphs, or Linux perf logs. It focuses on identifying logical bottlenecks rather than language-specific syntax tweaks.

    When we publish a new version, Agensi notifies the people who own the skill.

    New in Agents & Orchestration