Adapt still-image briefs for Krea 2, using exploratory prompting for open visual search and locked prompting plus style references for production-consistent look development.
Scanned 9/9/2026
Install to Claude Code
npx -y skills add badgids/Story-Film-Skills --skill krea-2 --agent claude-codeInstalls into .claude/skills of the current project.
Are you the author of Krea 2?
Add the live security badge to your README — it updates automatically with every re-scan.
[](https://www.skillsdirectory.com/skills/badgids-krea-2)More formats (shields.io, HTML) on the badges page.
---
name: krea-2
description: Adapt still-image briefs for Krea 2, using exploratory prompting for open visual search and locked prompting plus style references for production-consistent look development.
disable-model-invocation: true
author: Alan Guice (Badgids)
license: Apache-2.0
---
# Krea 2 Prompting
Krea 2 is useful when style and aesthetic exploration are part of the task.
## Modes
### Explore
Use when the user wants possibilities. Start from a short concrete subject or scene plus only the essential constraint. Let the first batch explore style space. On later passes, add the selected style direction and production facts.
### Lock
Use when continuity matters. Write a compact but specific description of subject, composition, environment, lighting, material, palette, and selected style. Name style or moodboard references and their intended influence.
## Workflow
1. Read image brief and canon.
2. Choose `explore` or `lock` from the brief intent.
3. Keep subject and action clear before style language.
4. In lock mode, preserve the exact recurring character and environment identifiers used elsewhere.
5. Use reference images for style instead of trying to encode every stylistic property as adjectives when references exist.
6. Save under `04_generation/prompts/krea-2/<source-id>.md`.
## Done
Explore mode leaves room for deliberate variation. Lock mode removes accidental variation in facts the project already decided.
Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.
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', ...
Routes multi-tool workflows through MCP servers for large datasets and pipelines. Use when Bash tool overhead is limiting throughput on data-heavy tasks.
Recovers prior coding-agent session context by running `catchup <agent> --since-compact`, which extracts a clean summary of a previous Codex, Claude Code, Antigravity, OpenCode, or Pi Agent session. Use when the user says "catch up", "what did the last session do", "get me up to speed", "I switched agents", or asks to recover/summarize a previous session before continuing. Do NOT use for the current conversation, git history, or any non-agent log.
A comprehensive mathematical reasoning skill for AI assistants — handles arithmetic to research-level problems with rigorous step-by-step reasoning, systematic verification, and transparent uncertainty handling