Skip to content
TrustedSkillsbeta
Back to all skills

Agent Performance Engineer

Checked
tony363·vlatest·agents·MIT

Analyzes agent interactions, identifies bottlenecks, and suggests optimizations to improve efficiency and user satisfaction.

Repository

Install on your platform

Showing Claude Code. One command installs this skill into any of the agents below.

  1. 1

    Run this in your project

    terminal
    $ npx skills add tony363/superclaude --skill agent-performance-engineer -a claude-code

  2. Uses the open-source skills CLI and needs Node.js. Add -g to install it for your user instead of this project.

What we know about this skill

Publisher

tony363

Taken from the source listing. We haven't verified who controls this account.

Install target

Live repository

Not pinned. Installing fetches whatever the repository holds at the time you run the command.

No human has reviewed this code. The checks below are a static scan of the files at one commit — nobody has run this skill or judged whether it works. A skill runs with whatever access you give your agent, so read the source before you install it.

Automated safety checks

scanned

This skill passed all 6 checks. We read its files at one commit and looked for the things that make a skill dangerous to run — not for whether it works.

  • Declares what it does: passed

    SKILL.md parses and declares a name and a description.

    SKILL.md exists, its frontmatter parses, and it declares a name and a description.

  • No undeclared network calls: passed

    Makes no network calls.

    Every host the skill dials — from its scripts, its config endpoints or the commands it tells the agent to run — is either well-known package and API infrastructure or declared in its own frontmatter. Links in documentation are not counted.

  • No obfuscated payloads: passed

    No encoded or obfuscated payloads.

    No base64, hex or compressed blob is decoded and then executed, and no encoded shell commands.

  • No credential access: passed

    Reads no keys, tokens, keychains or credential files.

    Neither the code nor the SKILL.md instructions read SSH keys, cloud credentials, keychains, token stores, browser cookie databases or dotfiles that hold secrets.

  • No pipe-to-shell installers: passed

    No pipe-to-shell or download-and-run installers.

    No `curl … | sh` pattern, in the code or in the instructions, that runs code fetched at run time.

  • Pinned to a commit: passed

    Scanned tony363/superclaude at 6634f8ef5d.

    The exact upstream commit SHA that was scanned is recorded, so the result refers to specific bytes.

Commit
6634f8ef5d
Manifest
.claude/skills/agent-performance-engineer/SKILL.md
Scanned
1 file, 40 lines
This is a static scan, not a review. It reads the skill's files; it does not run them, and it cannot tell you whether the skill is any good or whether the code does what its description says. A skill runs with whatever access you give your agent.
What each check looks for →

About this skill

What it does

The agent-performance-engineer skill analyzes and optimizes AI agent workflows. It identifies bottlenecks, suggests improvements to prompt structure and chaining, and provides data-driven recommendations for enhancing overall agent efficiency. This includes evaluating token usage, latency, and cost effectiveness of agent operations.

When to use it

  • Troubleshooting slow agents: When an agent is taking too long to complete tasks or exhibiting high latency.
  • Reducing costs: To identify areas where token consumption can be minimized without sacrificing quality.
  • Improving complex workflows: When dealing with multi-step agent processes that require careful orchestration and optimization.
  • Evaluating prompt design: When you want feedback on the efficiency of your prompts and how they impact agent performance.

Key capabilities

  • Bottleneck identification in agent workflows
  • Prompt structure analysis & suggestions
  • Token usage optimization
  • Latency reduction strategies
  • Cost-effectiveness evaluation

Example prompts

  • "Analyze this agent workflow: [paste workflow description] and identify potential bottlenecks."
  • "How can I reduce token consumption for this prompt chain: [paste prompt chain]."
  • "Evaluate the latency of this agent task and suggest improvements."

Tips & gotchas

The skill's effectiveness depends on providing detailed information about the agent’s workflow, including prompts, chains, and any relevant performance metrics. It is best used in conjunction with monitoring tools to gather baseline data for comparison after optimization.