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

PalateKit

Menu

Request a resource

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

0 / 280

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.

Improve the agent through self-review v1.0.0

Use this resource to have the agent learn from its mistakes and your corrections

New

  • 391 downloads
  • 169 likes
  • 119 saves

Free

Install with the CLI

In a terminal, from the folder you want:

npx --yes palatekit@latest install agent-self-review-memory

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 logs the corrections you make, evaluates its own work and files what it learns into a tiered memory: hot memory, archives, per-project or per-domain memory. You get an agent that repeats fewer mistakes from one session to the next.

Mostly picked by

Updated November 2, 2026

Card for the “Improve the agent through self-review” skill

Details

Generates with
Your agent's model
Licence
MIT

Similar resources

View all

What you get

  • SKILL.md: triggers, memory architecture and promotion or demotion rules
  • boundaries.md, corrections.md, learning.md, reflections.md, scaling.md: reference files on limits, corrections, learnings, reflections and scaling

Good fit for

  • You often correct the same kind of mistake in your agent
  • You want the agent to keep what it learned from one conversation to the next

Not for

    Tags

    • self-improvement
    • memory
    • corrections
    • learning

    About

    You say

    “Remember that I prefer sentence-case headings, and apply it to future texts.”

    Card for the “Improve the agent through self-review” skill

    Skill published by aaaaqwq 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 have the agent learn from its mistakes and your corrections
    3. Review and adjust the result

    Content preview

    Files

    • _meta.json0.1 KB
    • .clawdhub/origin.json0.1 KB
    • boundaries.md2.2 KB
    • corrections.md1 KB
    • learning.md3 KB
    • LICENSE1.1 KB
    • memory-template.md1 KB
    • memory.md0.8 KB
    • NOTICE-PALATEKIT.md0.5 KB
    • operations.md3.5 KB
    • reflections.md0.9 KB
    • scaling.md3 KB
    • setup.md4.5 KB
    • SKILL.md6.7 KB

    Origin and licence

    Listed unmodified

    Author
    aaaaqwq
    Source
    github.com/aaaaqwq/agi-super-team/tree/4c7b20bc52ad8d4a89fa3f5185abc455ef9248de/skills/self-improving
    Licence
    MIT

    Notice

    « Self-Improving Agent (With Self-Reflection) » (aaaaqwq, 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.