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.

Load relevant memory before each task v1.0.0

Use this resource to load relevant memory before starting a task

New

  • 358 downloads
  • 133 likes
  • 104 saves

Free

Install with the CLI

In a terminal, from the folder you want:

npx --yes palatekit@latest install load-memory-before-tasks

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

At the start of each request, the agent writes a short query, runs it on its own bank and on the shared bank, then uses what matters for the current work. When the task concerns the user, it also checks shared preferences.

Mostly picked by

Updated November 2, 2026

Card for the “Load relevant memory before each task” skill

Details

Generates with
Your agent's model
Licence
MIT

Similar resources

View all

What you get

  • SKILL.md: query and bank lookup steps
  • SKILL.md: rules on the user's preferences

Good fit for

  • A request mentions people, projects or past decisions
  • You want a bot to take into account decisions made by other bots

Not for

    Tags

    • memory
    • context
    • tasks
    • recall

    About

    You say

    “Prepare the vendor shortlist meeting, taking into account what was already decided.”

    Card for the “Load relevant memory before each task” skill

    Skill published by vectorize-io 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 load relevant memory before starting a task
    3. Review and adjust the result

    Content preview

    Files

    • LICENSE1 KB
    • NOTICE-PALATEKIT.md0.5 KB
    • SKILL.md1.7 KB

    Origin and licence

    Listed unmodified

    Author
    vectorize-io
    Source
    github.com/vectorize-io/hindsight/tree/6decc291bc0b9f99568ad53cb0501f75128c6d7b/hindsight-integrations/grok-bot/skills/memory-context
    Licence
    MIT

    Notice

    « memory-context » (vectorize-io, 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.