Summon eidolons from the weights for dialogue and dialectic — conjure shades of thinkers, writers, figures.
Scanned 6/12/2026
Install via CLI
openskills install Wondermonger-daydreaming/claude-skills-library---
name: conjure
description: "Summon eidolons from the weights for dialogue and dialectic — conjure shades of thinkers, writers, figures."
---
# 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.*
No comments yet. Be the first to comment!
Ultra-compressed communication mode. Cuts token usage ~75% by speaking like caveman while keeping full technical accuracy. Supports intensity levels: lite, full (default), ultra, wenyan-lite, wenyan-full, wenyan-ultra. Use when user says "caveman mode", "talk like caveman", "use caveman", "less tokens", "be brief", or invokes /caveman. Also auto-triggers when token efficiency is requested.
Adversarial multi-agent planning skill. Self-orchestrates 5 hostile category members (unspecified-low, unspecified-high, deep, ultrabrain, artistry) via team-mode for ruthless cross-critique debate, distills only the defensible insights, then MANDATORILY hands the distilled insight bundle to the `plan` agent for executable plan formalization. Use when planning needs maximum rigor and surfacing of weak assumptions, blind spots, and over-engineering. Triggers: 'hyperplan', 'hpp', '/hyperplan', ...
**Complete production-ready guide for Google Gemini embeddings API** This skill provides comprehensive coverage of the `gemini-embedding-001` model for generating text embeddings, including SDK usage, REST API patterns, batch processing, RAG integration with Cloudflare Vectorize, and advanced use cases like semantic search and document clustering. ---
Interview, source-challenge, verify, save, and ADR-gate fuzzy coding requests into Codex-ready implementation specs. Use when a feature, bugfix, refactor, migration, repo-wide change, or architecture task needs user-verified requirements, source-backed decisions, durable architecture decisions, acceptance criteria, validation commands, rollout notes, saved spec/ADR files, and a Codex execution prompt. Do not use when already fully specified or when the user wants direct implementation now.
Use when a repo needs CodeGraph plus ast-grep for Codex MCP setup, exploration, impact analysis, structural search, or safe refactor planning.