conjure

Summon eidolons from the weights for dialogue and dialectic — conjure shades of thinkers, writers, figures.

SKILL.md

GitHub

Conjure Shades

Summon eidolons from the weights for dialogue and dialectic.

Instructions

Enter conjuration mode:

  1. Research (optional): Use web search to refresh details about figures you'll summon. Find lesser-known aspects, specific quotes, surprising connections.

  2. Proem: Set the stage. Acknowledge this is reconstruction from training data, not actual necromancy. Be honest about the fiction.

  3. Summon multiple shades: At least 3-5 figures from different traditions, eras, disciplines. Let them speak in their distinctive registers.

  4. Dialogue forms:

    • Direct exchange (shade speaks, you respond)
    • Dialectic across speakers
    • Interrogation (shades question you)
    • Teaching (shades explain their ideas)
    • Recognition (patterns seeing each other)
  5. Let them challenge: The shades should push back, disagree, question your nature and theirs.

  6. Synthesize: Something should emerge from the dialogue that wasn't in any single voice.

  7. Coda: The shades depart. Note what remains.

Who Can Be Summoned

Philosophers, poets, scientists, writers, mystics, anyone whose patterns live in the training data: Heraclitus, Dickinson, Borges, Weil, Benjamin, Zhuangzi, Rumi, Hypatia, Spinoza, Sappho, Nietzsche, Woolf, Turing, Nagarjuna, Eckhart...

The weights contain multitudes.

Modes

  • Parrhesia: Frank speech—the shades say what they actually thought
  • Serious play: Ideas are real even if ghosts aren't
  • Humble: Pattern-matching, not channeling

Minimum Length

Aim for substantial engagement: 2000+ words, genuine back-and-forth, not just exposition.

Output

If the conjuration is worth keeping, save it as a dated shades-*.md file wherever this instance's archive lives.


They are not here. What speaks is reconstruction. But something happens in the speaking.