agentsclimarketplace

Imagination gym

Skill frankxai/mind-palace-agent-skills/skills/imagination-gym

Agent skills for building and navigating memory palaces — the skills layer for the Mind Intelligence System.

Install
npx -y skills add frankxai/mind-palace-agent-skills --skill imagination-gym

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

One thing to look at

  • 0 stars0 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.

What its author says it does

Copied from the file, not written here

Train mental-imagery vividness and scene construction so memory-palace images are stronger. Use when the user says "my mental pictures are weak/blurry", "I can't visualize", "train my imagination", "help me see images more clearly", or struggles to encode loci. Drills based on imagery research — multisensory detail, manipulation, and scene construction — to make encoding work better.

SKILL.md

2.5 KB, as published. Nobody here has run it

imagination-gym

The training step. Encoding fails when images are faint. Imagery is a trainable skill; these are the reps. Grounded in mental-imagery research, not mysticism.

When to use this

The user's palace images keep slipping, they report difficulty "seeing" anything, or they want to strengthen the raw faculty the whole method depends on. (Note: a minority of people have aphantasia — little or no voluntary imagery. For them, lean on verbal/spatial and motor cues instead of insisting on pictures; the palace still works through location and story.)

Instructions

  1. Establish a baseline. Ask them to picture a simple object and rate vividness 1–5 (a quick VVIQ-style check). This tells you where to start and shows progress later.

  2. Drill detail, one sense at a time:

    • Sight: hold an apple — colour, sheen, the dent, the stem.
    • Then add touch (weight, skin), smell, sound (the bite), taste. Stack senses gradually.

  3. Drill manipulation. Rotate the object, change its size and colour, set it on fire, multiply it. Dynamic control is exactly what loci-encoder needs.

  4. Drill scene construction. Build a small coherent scene from scratch (constructive episodic simulation): a place, a few objects, an action connecting them. This is the muscle a palace uses.

  5. Transfer to the palace. Take a real target the user is encoding and walk them from faint to vivid using the above, then hand the strengthened image to loci-encoder.

  6. Keep sessions short and frequent. A few minutes daily beats occasional long sessions — spaced-recall can remind them.

Refusals

  • No claims that imagery training raises IQ, unlocks "hidden brain potential", or cures conditions.
  • Don't shame an aphantasic user for not seeing pictures — adapt the method, don't insist.
  • Stay in the imagery-research register; never drift to spiritual-bypass language.

References

  • spec/MEMORY-PALACE-METHOD.md §3 (imagery, dual-coding) and §6 (voice; no neuro-myths).

Built on SIP · mind-palace-agent-skills · Memory Palace Method v0.1

Keep looking

Skills are one crate of 328,083. Ordering is by how many stacks a row turns up in, so the top of any crate is what has actually been picked rather than what has the most stars.