Generate multiple content variations across tone, structure, lens, and length.
npx skills add https://github.com/mishahanin/heading-os --skill burst-mishahanin
Please help me install this Agent Skill. Skill: burst Source: https://github.com/mishahanin/heading-os/tree/main/.claude/skills/burst Command: npx skills add https://github.com/mishahanin/heading-os --skill burst-mishahanin
This Skill solves the creative bottleneck of being stuck on a single draft by forcing the generation of multiple, distinct variations of your content.
Type /burst 3 to generate three distinct variations of the last assistant-produced content turn.
High-intent search queries and answers about installing and using this skill.
Content variation generation works by attacking different axes like tone, structure, lens, and length to produce 2-5 distinct drafts. This forces diverse outputs to break creative blocks and refine messaging without external dependencies.
The best way to explore different tones and structures is generating multiple variations of the same content artifact. By framing a message as a data-led declaration versus a contrarian provocation, you can evaluate impact before finalizing.
Yes, you can generate content variations directly from conversational context without external plugins. The process operates purely through LLM reasoning, requiring no external dependencies or setup to produce diverse drafts.
To iteratively refine content variants, use a convergence pattern where you pick a preferred variant and refine it further. This narrows down messaging options, allowing you to converge on the ideal output faster than editing a single draft.
You should avoid generating multiple variations for low-stakes or purely informational writing where tone and structure exploration is unnecessary. It is designed for high-stakes content or overcoming creative blocks, not for simple straightforward communication.
lucabattistiniGuide design projects through structured discovery and generate a discovery brief.
DNYoussefDiagnose ML training issues across loss divergence, NaN losses, overfitting, and slow convergence.
wwsunTransform mechanical AI-generated texts into natural, human-like language.
j7-devSuggest manual context compaction at logical task intervals.
