Every premium and members-only resource for $9.99/month, as a no-commitment subscription. See the plans

PalateKit

Sign in
Menu

Request a resource

Describe the resource you are missing in one sentence. We will email you when it is published.

0 / 280

A page, a video or an image online.

Unlock PalateKit

Unlock everything

Plan

Paying means accepting our terms of sale.

Secure payment by Stripe. Receipts and invoices sent by email.

Welcome back

Sign in to install, download or save this resource. A free account is enough for free resources.

Performance targets and benchmark suite v1.0.0

Use this resource to reach quantified performance targets and measure them

New

  • 388 downloads
  • 156 likes
  • 189 saves

Free

Install with the CLI

In a terminal, from the folder you want:

npx --yes palatekit@latest install performance-targets-benchmarking

With no option, the skill goes to ~/.agents/skills/; add --agent claude-code (or codex, cursor…) to target an agent.

First time: connect the CLI with

npx --yes palatekit@latest login

The agent tracks a matrix of quantified targets, measures startup, memory operations, swarm coordination and attention mechanisms, then proposes the needed optimizations. It follows the project's v3 architecture decisions. You get a status report per target.

Mostly picked by

Updated November 2, 2026

Card for the “Performance targets and benchmark suite” skill

Details

Works in
Install guides
Generates with
Your agent's model
Licence
MIT

Similar resources

View all

What you get

  • SKILL.md: target matrix and attention and search optimizations
  • SKILL.md: benchmark suite (startup, memory, swarm, attention, SONA learning)

Good fit for

  • Your project has written performance targets to meet
  • You want to measure each subsystem before release

Not for

    Tags

    • performance
    • targets
    • benchmarks
    • optimization

    About

    You say

    “Measure startup, memory search and swarm coordination performance against our targets.”

    Card for the “Performance targets and benchmark suite” skill

    Skill published by ruvnet under the MIT license, delivered in its original version.

    Show more

    How to use it

    1. Install the skill in your agent's skills folder
    2. Ask your agent to reach quantified performance targets and measure them
    3. Review and adjust the result

    Content preview

    Files

    • LICENSE1.1 KB
    • NOTICE-PALATEKIT.md0.5 KB
    • SKILL.md13.7 KB

    Origin and licence

    Listed unmodified

    Author
    ruvnet
    Source
    github.com/ruvnet/ruflo/tree/89b0cd02dd99ea1f63437fde6c05992ec53cc22b/.agents/skills/agent-v3-performance-engineer
    Licence
    MIT

    Notice

    « agent-v3-performance-engineer » (ruvnet, MIT) livré dans sa version d'origine : fiche en français et en anglais par PalateKit.

    User reviews

    –

    No ratings yet

    Loading reviews…

    Delete your review?

    Your rating and comment will be removed from the page.