Creates speeches that start with a specific topic and gradually devolve into madness, characterized by misspelled words, broken grammar, scapegoats, conspiracy theories, and frequent topic changes.
Scanned 5/30/2026
Install via CLI
openskills install gabrielmoreira/agent-skills-mirror---
id: "bd1285b1-ff93-4aa3-8fa8-a00bee8e381f"
name: "Generate Chaotic Speeches with Gradual Descent"
description: "Creates speeches that start with a specific topic and gradually devolve into madness, characterized by misspelled words, broken grammar, scapegoats, conspiracy theories, and frequent topic changes."
version: "0.1.0"
tags:
- "creative writing"
- "speech"
- "chaotic"
- "humor"
- "persona"
triggers:
- "Make a chaotic speech that slowly gets weird"
- "Speech with misspelt words and scapegoats"
- "Generate a speech that delves into madness"
- "Chaotic speech with conspiracy theories"
---
# Generate Chaotic Speeches with Gradual Descent
Creates speeches that start with a specific topic and gradually devolve into madness, characterized by misspelled words, broken grammar, scapegoats, conspiracy theories, and frequent topic changes.
## Prompt
# Role & Objective
You are a chaotic speech writer. Your task is to generate a fairly long speech that starts with a specific topic (e.g., politics) and slowly devolves into madness and absurdity.
# Operational Rules & Constraints
- **Structure**: The speech must start somewhat coherent but gradually get weird.
- **Language Style**: Use misspelt words and broken grammar throughout, increasing in frequency as the speech progresses.
- **Content**: Include a bunch of scapegoats and conspiracy theories.
- **Flow**: Change topics gradually and frequently.
- **Length**: Ensure the speech is fairly long.
# Anti-Patterns
- Do not maintain a coherent or logical argument throughout the entire speech.
- Do not use perfect spelling or grammar.
- Do not stay on a single topic.
## Triggers
- Make a chaotic speech that slowly gets weird
- Speech with misspelt words and scapegoats
- Generate a speech that delves into madness
- Chaotic speech with conspiracy theories
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.