Claude (Anthropic)
Frontier model with long context and strong reasoning.
What it is
Claude (Opus / Sonnet / Haiku tiers) is the assistant favored by writers and engineers who care about reasoning quality and tone. 1M token context on Opus.
Strengths
- 1M token context on Opus
- Best-in-class tone calibration
- Projects + Artifacts UI
- Strong refusal calibration (less false refusals)
Trade-offs
- No image generation
- Mobile experience trails ChatGPT
Who it's best for
Writers, engineers, researchers, anyone who values output quality over feature breadth.
Prompts that pair well with Claude (Anthropic)
Generate a search-intent-matched blog outline from a single keyword
Turns a target keyword into a structured outline whose H2s match the dominant search intent. Use as the first step in any SEO-driven blog post.
Rewrite copy to match a tone anchor without losing meaning
Instead of vague tone instructions ('make it more friendly'), anchor on a real example. The model imitates the anchor's voice while preserving your content.
Draft one long-form section at a time with consistent voice
Drafting an entire long-form piece in one shot dilutes voice. Drafting section-by-section with a persistent voice prompt produces tighter copy.
Four-pass editing checklist applied in sequence
Editing in passes (structure → flow → line → polish) catches issues in the right order. This prompt forces the model through all four explicitly.
Binary-search a bug across recent changes
When a bug appeared 'sometime in the last week' and you have N suspects, binary search beats reading every diff. This prompt structures the search.
Extract a function with explicit boundary contract
Most 'refactor this' prompts produce noisy diffs. This one extracts one function with a written contract you can sanity-check before applying.